The DOI matches its Crossref record; 51 of the 52 references it cites were found in a registry or an index; none of the 22 sources its claims cite is checked for support yet.
The Pascal Visual Object Classes Challenge: A Retrospective
Open accessOverview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
50 Own result · 40 Own interpretation · 34 No basis given · 25 Own method · 21 Not checked yet
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We were not able to obtain MT bounding box annotations of sufficiently high quality to achieve this.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.3.1 Use of Mechanical Turk for initial class labelling of the images
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“However, the labels of whether a class was present or not were high enough quality to allow a balanced image set to be selected, prior to annotation by our trained annotators.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.3.1 Use of Mechanical Turk for initial class labelling of the images
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Segmentation requires substantially more annotation effort than detection -it can easily take ten times as long to segment an object than to draw a bounding box around it.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.3.3 Increased time spent on segmentation
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“From Table 15, we note that for several classes a large relative increase in performance can be obtained by combining two moderately performing methods.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 5.3 Who should collaborate?
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Between 2008 and 2012 the total number of images (objects) in the main dataset more than doubled from 4332 (12684) to 11540 (31561).”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6 Progress Through Time
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“For all classes NUS_SCM is one of the chosen collaborators, which is not entirely surprising given its dominating individual performance (see Table 5).”
- Also stated in: § 6 Progress Through Time · plain
“NUS_SCM, the best-performing individual method across all classes, is always chosen to be one of the super-classifier collaborators.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 5.3 Who should collaborate?
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 6 Progress Through Time · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The method from Oxford won on six classes.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 3.2 Detection
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In each figure, the final group is of images which none of the current methods work on -it would be interesting to focus analysis and research on this group, with the aim of teasing out properties of these images which may inspire improvements to current methods.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 4.2 Identifying easy and hard groups of images
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“In more recent work (Girshick et al, 2014), the CNN features described in Section 6.1 have been used to represent the selective search bounding boxes, and have achieved a substantial improvement in detection performance.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.2 Detection
What the sources say
- Not checked yetcites Girshick et al, 2014
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The winning method STANFORD for competition 9 is mostly described in the paper by Khosla et al (2011), and that of OXFORD_ACT for competition 10 in Hoai et al (2012).”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 3.4 Action classification
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Probably not a substantial claim. 54
- It may state two separate claims as one. 53
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The number of images and instances in all the tasks was increased up to 2011.From 2011 to 2012 the number of images in the classification, detection and person layout tasks was not increased, and only those for segmentation and action classification were augmented.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.2 Datasets
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“These criteria were relaxed from VOC 2010 on, though this task never became as popular as the others.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.4.6 Person layout
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“There were 850 annotated objects instances in 609 images for the person layout challenge.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 3 VOC 2012 Results and Rankings
plainn = 609- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The winning method for competition 1 is NUS_SCM.Its performance exceeded all other methods (including those in competition 2) for all classes in 2012, and also improved on the 2011 winning entries in all but one class ('pottedplant').”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 3.1 Classification
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: Participants followed the best practice guidelines of tuning parameters on the validation set and running algorithms only once on the test set.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In this way, errors were picked up and corrected earlier and post-hoc checking was substantially reduced.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.3.2 Interleaved annotation and checking
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“From 2009 onwards the data for all tasks consists of the previous years' images augmented with new images.Before this, in 2008 and earlier, an entirely new dataset was released each year for the classification/detection tasks.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.2 Datasets
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Other classes with large changes in rank are: 'dog' (down 5 places to 16), 'sheep' (up 5 places to 9) and 'cow' (also up 5 places to 10).”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 4.1.1 Comparing classification across classes
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Over time, the annotation period was adapted until around 50% of the time was spent on segmentation annotation and checking.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.3.3 Increased time spent on segmentation
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Teams led by Felzenszwalb were joint winners of the challenge in 2008 and 2009, and the released code meant that this method was widely used/developed by others.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.2 Detection
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The most dramatic difference is for the 'boat' class which is one of the better performing classes for classification but one of the worst for detection.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 4.1.2 Comparing detection across classes
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- The authors state this as an assumption: The number of possible object locations in an image is very large relative to differences in positive counts between classes.
- The authors state this as an assumption: The number of negative examples is roughly equal across classes even when positive counts differ.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The other two classes whose ranking drops after normalisation are 'cat' and 'dog', in both cases by three places in the ranking, reflecting the higher rate of occurrence of cats and dogs in the test set.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 4.1.2 Comparing detection across classes
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- The authors state this as an assumption: The number of possible object locations in an image is very large relative to differences in positive counts between classes.
- The authors state this as an assumption: The number of negative examples is roughly equal across classes even when positive counts differ.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The diversity in performances has gradually increased, as has the highest AP achieved.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.1 Classification
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Indeed, by 2012 there were 4588 training and validation images, with about 400 examples of people carrying out each class of action.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6 Progress Through Time
plainn = 400- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“This is the route, termed 'selective search', followed by the University of Amsterdam entry which won in 2012, and allowed them to use more computationally expensive features and classifiers.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.2 Detection
What the sources say
- Not checked yetcites Van de Sande et al, 2011
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Over time, the checking part of the annotation effort grew to take around 50% of the annotators' time.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.3.2 Interleaved annotation and checking
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For most classes the AP of the best performing method has gradually increased over the years, although this trend is less strong than for the classification task (see Fig. 21).”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.2 Detection
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Again the diversity in performances has gradually increased, as has the highest AP achieved.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.2 Detection
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For all classes we observe trends similar to those noted by Hoiem et al (2012) in that the normalised precision (see Eq. 6) increases as function of size, except that there is sometimes a drop for extra-large objects, which are often highly truncated.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.2.1 Patterns of errors through time
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In Table 14, we note that the performance of the super-classifier trained using only scores from two methods is often significantly higher than the best-performing individual method (e.g. for 'bottle', 'chair' and 'potted plant'), and for some classes higher than that of the super-classifier trained for all methods together (e.g.'bicycle').”
- Also stated in: § 6 Progress Through Time · plain
“Note that the performance of the super-classifier trained using only scores from two methods as input features (second to last column) is often significantly higher than the best-performing individual method (second column), and for some classes higher than that of the super-classifier trained all methods together (last column).”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 5.3 Who should collaborate?
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Also stated in: § 6 Progress Through Time · plain
In the paper
“Also in 2010, the MIT/UCLA team (Zhu et al, 2010) extended the DPM model by allowing a 3-layer architecture (corresponding to a root, parts and sub-parts), and by incorporating data terms involving a histogram of 'visual words' for region appearance as well as HOG features for edges.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.2 Detection
What the sources say
- Not checked yetcites Zhu et al, 2010
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“originally these tasks were treated quite independently by participants, but as the challenge progressed there was progressively more cross-fertilisation, with detection and segmentation being used to enhance the classification performance for example.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6 Progress Through Time
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In general the impact of the normalisation is less for detection than for classification, with most classes hardly changing in rank.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 4.1.2 Comparing detection across classes
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- The authors state this as an assumption: The number of possible object locations in an image is very large relative to differences in positive counts between classes.
- The authors state this as an assumption: The number of negative examples is roughly equal across classes even when positive counts differ.
None of the sources cited for this claim have been checked yet.
In the paper
“There is a marked trend that the percentage of background errors has increased between 2009 and 2012, while in general the confusions with similar and dissimilar objects have decreased.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.2.1 Patterns of errors through time
boostedcorrelationaln = 4- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The second placed method in competition 5 and the winning entry in competition 6 was BONN_JOINT which created multiple segmentations of each image and then sampled from a distribution over tilings constructed from these segments (see Ion et al, 2011a).”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 3.3 Segmentation
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“In VOC 2009, Vedaldi et al (2009) used a cascade of methods of increasing complexity using linear, quasi-linear and non-linear kernels, with the idea that the more expensive non-linear methods need only be run on a subset of locations determined by the cheaper methods.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.2 Detection
What the sources say
- Not checked yetcites Vedaldi et al (2009)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In each case the groups of images are ordered to show a steady increase in difficulty.This increase can be characterised by reduction in object size, increased truncation or occlusion, increased variation in illumination or viewpoint, increased background clutter.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 4.2 Identifying easy and hard groups of images
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Other than some participants mak-ing multiple similar submissions (which contravenes the best practice of choosing the method submitted using the validation set), there were no problems that we were aware of.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.1.2 Measuring performance on the test data
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Images identified correctly by 27% of methods on average.Still harder images with more cluttered backgrounds and smaller bicycles.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Third, has been the development of cross fertilisations between the challenges -detectors used as part of the segmentation and classification methods, and (unsupervised) segmentation used to propose windows in detection methodswhere originally methods were myopic in only applying to one of the three challenges.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Note that multiple objects from multiple classes may be present in the same image.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Each row corresponds to one of the 73 classification methods submitted since 2009.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Images identified correctly by 94% of methods on average.Slightly harder images where the aeroplane is still large but may be truncated or seen from a more unusual viewpoint.The backgrounds are still largely uncluttered.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Gold indicates the increase in performance on object classes where the superclassifier beats all other methods, averaged across the two folds.The three classes for which performance drops slightly have been highlighted in red.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“and it is better for non-truncated objects than truncated ones (except that the top three methods in 2009 and 2012 all prefer truncated over nontruncated cats).”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.2.1 Patterns of errors through time
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“In cases where this is not provided we still see many examples in papers of authors evaluating the results in different ways -for example some using micro-averaging (giving equal weight to each image) and others using macroaveraging (giving equal weight to each class) -so that results are not comparable.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.2.1 Patterns of errors through time
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The 2009 competition had probably the broadest set of entries, twelve in all, whose methods built on and extended those used in the previous year.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.2.1 Patterns of errors through time
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Both the number of images and number of objects more than doubled between 2008 and 2012.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.1.3 Augmentation of dataset each year
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Images identified correctly by 88% of methods on average.Still harder images with more cluttered backgrounds, smaller or more truncated aeroplanes and more varied lighting.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Method UP is only used in the 'person' class since it only participated in that class.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For most classes the accuracy of the best performing method has increased between 2009 and 2012, although often not monotonically with the year.In particular, in the final years from 2011 to 2012 there was substantial improvement in all classes except bus.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.2.1 Patterns of errors through time
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Images identified correctly by 52% of methods on average.Slightly harder images where the bicycle is smaller and may be seen from the rear or front.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The two dominant methods were: hierarchical random fields with a range of potentials, and the use of multiple bottom-up segmentations, combined with a classifier to predict the degree of overlap of a segment with an object.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.2.1 Patterns of errors through time
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The 2008 segmentation competition had six participants and was the first year where the segmentation methods beat the automatic entries from the detection challenge.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.2.1 Patterns of errors through time
plainn = 6- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“There is complete annotation for the twenty classes: i.e. all images are annotated with bounding boxes for every instance of the twenty classes for the classification and detection challenges.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.2 Datasets
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The motivation for this additional point annotation was that the aspect ratio of the bounding box might provide some information on the action being performed, and this was almost entirely removed if only a point was provided.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.1.4 Action classification
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Segmentation clearly is more challenging than detection and its solution tends to be more time consuming.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.1.3 Segmentation
boostedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Note, we do not release the exact numbers of object instances in the test set, but both the number of instances per class and number of images are approximately balanced with those in the trainval set.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.2 Datasets
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“In 2012 the person of interest was specified by both a bounding box and a point on the torso, and a separate competition defined for each.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.1.4 Action classification
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The provision of a confidence level allows results to be ranked such that the trade-off between false positives and false negatives can be evaluated, without defining arbitrary costs on each type of classification error.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.4.3 Classification and detection
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is clear that the additional requirement to locate the instances in an image makes detection a more demanding task than classification.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.1.2 Detection
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“In addition to a bounding box for each object, attributes such as: 'orientation', 'occluded', 'truncated', 'difficult'; are specified.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.2 Datasets
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Classification could also be used to put regression methods for counting into action, which have been shown to perform well without any detection (Lempitsky and Zisserman, 2010).”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.1.2 Detection
What the sources say
- Not checked yetcites Lempitsky and Zisserman, 2010
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The success of the layout prediction depends both on: (i) a correct prediction of parts present/absent (e.g. are the hands visible or occluded); (ii) a correct prediction of bounding boxes for the visible parts.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.1.5 Person layout
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“We encouraged participants to observe the best practice guidelines, given at the Pascal VOC best practice guidelines web page (2012), that parameters should be tuned on the validation set and algorithms run only once on the test set, so that the organisers were not asked to choose the best result for them.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.4.2 Evaluation of results
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Even in cases where detection is the end goal, classification may be an appropriate initial step to guide resources towards images that hold good promise of containing the target class.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.1.2 Detection
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“In addition to withholding the test data annotation, it was also required that participants submit only a single entry per method.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.4.2 Evaluation of results
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Note, the annotations on the test set are not publicly released.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.2 Datasets
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is also true that detection can support more applications than mere classification, e.g.obstacle avoidance, tracking, etc.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.1.2 Detection
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“Even if segmentation is the goal, detection can provide a good initialization (e.g.Leibe et al, 2004).”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.1.3 Segmentation
What the sources say
- Not checked yetcites Leibe et al, 2004
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In 2011 an 'other' class was introduced (for actions different from the ten already specified).This increased the difficulty of the challenge.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.1.4 Action classification
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“To add to this encouragement, the evaluation server restricted the number of times a participant could submit results for earlier years (since performance could be partially gauged as earlier years' images are a subset of the current year's).”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.4.2 Evaluation of results
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This normalised measure will allow us to compare classification accuracy across classes meaningfully.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 4.1.1 Comparing classification across classes
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This again suggests that the normal way of reporting results may underestimate the difficulty of detecting people in images -the state-of-the-art accuracy for detecting people is in fact only slightly better than that of detecting plants and chairs, despite all the special research effort that has gone into this case.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 4.1.2 Comparing detection across classes
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- The authors state this as an assumption: The number of possible object locations in an image is very large relative to differences in positive counts between classes.
- The authors state this as an assumption: The number of negative examples is roughly equal across classes even when positive counts differ.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“All submissions since 2009 have provided predictions for the VOC 2009 test images, since images were only added to the test set over the years; thus this dataset provides a common test set for all submissions.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6 Progress Through Time
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Note that rank ranges depend on all entrants in a competition, while the individual confidence interval is a property of a single method.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 3.5 Bootstrapping AP and rank
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“For example the winning NEC/UIUC entry in 2009 used local coordinate coding (LCC, Yang et al 2009) to replace the vector quantisation step, so that a feature vector could be represented by more than one template.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.1 Classification
What the sources say
- Not checked yetcites Yang et al 2009
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The motivation was that the world is dynamic and snapshots of it still convey substantial information about these dynamics.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.1.4 Action classification
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Note, the action classes are not exclusive, for example a person can be both 'riding a bicycle' and 'phoning'.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.1.4 Action classification
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“An optimal value for the parameter C is first found by optimising classification performance on a held-out validation set (10% of the training dataset), and then the SVM is trained on all of the training data.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 5.1.2 Data preparation and classifier training
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, this is a relatively small change in rankings compared to that of the 'person' class and should not cause us to substantially re-evaluate the difficulty of these two classes.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 4.1.2 Comparing detection across classes
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- The authors state this as an assumption: The number of possible object locations in an image is very large relative to differences in positive counts between classes.
- The authors state this as an assumption: The number of negative examples is roughly equal across classes even when positive counts differ.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“As before, an optimal value for the C parameter is found via cross-validation on 10% of the data.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 5.2 How much does each method contribute to the super-classifier?
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This enabled efficient discussion, e.g. of challenging or unusual cases, and was very flexible in allowing changes of priorities and training.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.3.4 Co-located annotators
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“The 2011 entry from the University of Amsterdam used classification-by-detection, but instead of using sliding windows they proposed candidate windows based on multiple segmentations (Van de Sande et al, 2011).”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.1 Classification
What the sources say
- Not checked yetcites Van de Sande et al, 2011
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“To ensure a fair comparison, the same two-fold evaluation is also computed for the individual methods.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 5.1.1 Training, test data, and evaluation
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“In addition, some experienced annotators were always included at each remote site to train novices.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 2.3.4 Co-located annotators
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“One idea to go beyond the simple bag-of-words (BOW) representation was to use histograms on regions of the image, e.g.spatial pyramid matching (SPM, Lazebnik et al 2006), where representations for a nested pyramid of regions are computed.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.1 Classification
What the sources say
- Not checked yetcites Lazebnik et al 2006
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In this section we review the results of the VOC 2012 challenge to give a snapshot of the state-of-the-art in the final year of the challenge.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 3 VOC 2012 Results and Rankings
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Rests on an assumption: The submitted methods are representative of the state of the art in 2012.
In the paper
“First, has been the development of a new class of object category detector, the DPM of Felzenszwalb et al (2010), with open source code provided to the community.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
What the sources say
- Not checked yetcites Felzenszwalb et al (2010) source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Annotation was performed according to a set of guidelines distributed to all annotators.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Segmentations are annotated at the object and object class level.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“These changes may have reduced but not eliminated another type of reduction in diversity: that methods may end up overfitting to the particular evaluation metrics selected for each competition.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.2.1 Multiple evaluation metrics
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The Pascal VOC challenges and workshops have certainly contributed to the surge in interest in category recognition in the computer vision community over the last decade, and have been mentioned in thousands of papers.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds. It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“They have been partially annotated with people, bounding boxes, reference points and their actions.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This had a number of useful consequences: first, it has mitigated overfitting to the data (which might have happened if the data had not changed from year to year); and second, since the earlier year's data is available as subsets, progress can be measured from 2008 to 2012 using the same test set.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.1.3 Augmentation of dataset each year
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“A subset of images are also annotated with pixel-wise segmentation of each object present, to support the segmentation competition.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In 2012 the number of participating organisations was down to three, suggesting that the methods used were performing so well it was difficult for a new participant to enter the competition with an original method and get competitive results.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 6.2.1 Patterns of errors through time
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Annotation was performed according to a set of guidelines distributed to all annotators.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Images for the action classification task are disjoint from those of the classification, detection and segmentation tasks.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Images for the person layout taster, where the test set is disjoint from the main tasks, have been additionally annotated with parts of the people (head, hands and feet).”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Since the data consists of images, there is still some danger that performance of different parameter choices will be assessed by eye on the test data.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.1.2 Measuring performance on the test data
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“For example, the 2009 dataset is a subset of 2010, 2011 and 2012, and as the assignments to training, validation and test are maintained, performance of all methods can be measured each year using the same 2009 test data (albeit with different training and validation data each year).”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.1.3 Augmentation of dataset each year
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Each image has an annotation file giving a bounding box and object class label for each object in one of the twenty classes present in the image.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Here it should be added that in case of multiple submissions, participants were forced to select a single submission without knowing the respective test scores.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.1.2 Measuring performance on the test data
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper relies on this without support.
Participants followed the best practice guidelines of tuning parameters on the validation set and running algorithms only once on the test set.
“We encouraged participants to observe the best practice guidelines, given at the Pascal VOC best practice guidelines web page (2012), that parameters should be tuned on the validation set and algorithms run only once on the test set, so that the organisers were not asked to choose the best result for them.”
The paper relies on this without support.
The submitted methods are representative of the state of the art in 2012.
“In this section we review the results of the VOC 2012 challenge to give a snapshot of the state-of-the-art in the final year of the challenge.”
The authors state this as an assumption.
The number of possible object locations in an image is very large relative to differences in positive counts between classes.
“Instead, we assume that the number of possible places is very large compared to the variation in the number of positives across classes.”
The authors state this as an assumption.
The number of negative examples is roughly equal across classes even when positive counts differ.
“This allows us to assume that the number of negatives is approximately equal across classes, even when they have different numbers of positives.”
The authors state this as an assumption.
Participants will not hand-annotate the test data; the organisers rely on participants' honesty and the limited time between test data release and result submission to prevent this.
“It is also theoretically possible for participants to hand-annotate the test data, though we rely on participants' honesty and to some extent also the limited time available between the release of the test data and submission of the results to prevent this.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Existing segmentation datasets can hardly support LUSS due to the large image complexity but small data scale.”
From Large-Scale Unsupervised Semantic Segmentation (2023) · cites this paper as [10]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The use of public databases such as PASCAL [72], MS-COCO [73], or autonomous driving [74-76] simplifies the performance of experiments to compare sampling methods.”
From Ten Years of Active Learning Techniques and Object Detection: A Systematic Review (2023) · cites this paper as [72]
Experimental — accuracy not yet measuredIn the citing paper
“PASCAL VOC Everingham et al. (2010, 2015) is a multiyear effort devoted to the creation and maintenance of a series of benchmark datasets for classification and object detection, creating the precedent for standardized evaluation of recognition algorithms in the form of annual competitions.”
From Deep Learning for Generic Object Detection: A Survey (2020) · cites this paper as Everingham et al. 2015
In the citing paper
“Current state-of-theart detectors employ fully supervised models learned from labeled data with object bounding boxes or segmentation masks (Everingham et al. 2015;Lin et al. 2014;Russakovsky et al. 2015;Lin et al. 2014).”
From Deep Learning for Generic Object Detection: A Survey (2020) · cites this paper as Everingham et al. 2015
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
“| aeroplane | 97.34 | UP | 6.00 | NUS_SCM | 97.34 | 97.34 | 97.41 |”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 7.3 Conclusions and impact
“Method UP is only used in the 'person' class since it only participated in that class.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 3.2 Detection
“Table 7: Segmentation results.For each object class and submission, the AP score (%) is shown.”
§ The PASCAL Visual Object Classes Challenge: A Retrospective > 3.5 Bootstrapping AP and rank
“For classification, detection, and action classification this will be the AP score, while for segmentation it is the segmentation accuracy (see Eq. 2).”
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599
Self-citationVisualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839
Robust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097
Libsvm : A library for support vector machines
Ferrari, V. (2008) · Medical Entomology and Zoology · Cited by 10,123
Object Detection with Discriminatively Trained Part-Based Models
Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.167 · Cited by 9,853
Introduction to Modern Information Retrieval
Salton, G., & McGill, M. J. (1983) · Virtual Defense Library (Ministerio de Defensa) · Cited by 9,743
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
Lazebnik, S., Schmid, C., & Ponce, J. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.68 · Cited by 7,916
Introduction to modern information retrieval
Dillon, M. (1983) · Information Processing & Management · doi:10.1016/0306-4573(83)90062-6 · Cited by 5,981
Selective Search for Object Recognition
Uijlings, J. R. R., van de Sande, K. E. A., Gevers, T., & Smeulders, A. W. M. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0620-5 · Cited by 5,980
Visual categorization with bags of keypoints
Csurka, G. (2004) · Cited by 4,379
LabelMe: A Database and Web-Based Tool for Image Annotation
Russell, B. C., Torralba, A., Murphy, K. P., & Freeman, W. T. (2008) · International Journal of Computer Vision · doi:10.1007/s11263-007-0090-8 · Cited by 4,210
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013) · arXiv · doi:10.48550/arxiv.1310.1531 · Cited by 4,019
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
Oquab, M., Bottou, L., Laptev, I., & Sivic, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.222 · Cited by 3,150
Linear spatial pyramid matching using sparse coding for image classification
Yang, J., Yu, K., Gong, Y., & Huang, T. S. (2009) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2009.5206757 · Cited by 2,895
Torralba, A., & Efros, A. A. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995347 · Cited by 2,440
Describing objects by their attributes
Farhadi, A., Endres, I., Hoiem, D., & Forsyth, D. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206772 · Cited by 1,917
All of Statistics: A Concise Course in Statistical Inference
Wasserman, L. (2004) · Springer Texts in Statistics · doi:10.1007/978-0-387-21736-9 · Cited by 1,090
Learning To Count Objects in Images
Lempitsky, V., & Zisserman, A. (2010) · Cited by 1,063
Self-citationCombined Object Categorization and Segmentation With An Implicit Shape Model
Leibe, B., Leonardis, A., & Schiele, B. (2004) · Cited by 810
Alexe, B., Thomas Deselaers, B., & Ferrari, V. (2010) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2010.5540226 · Cited by 791
Multiple kernels for object detection
Vedaldi, A., Gulshan, V., Varma, M., & Zisserman, A. (2009) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2009.5459183 · Cited by 784
Self-citationSegmentation as selective search for object recognition
van de Sande, K. E. A., Uijlings, J. R. R., Gevers, T., & Smeulders, A. W. M. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126456 · Cited by 739
Visualizing and Understanding Convolutional Networks
Zeiler, M. D., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1311.2901 · Cited by 522
Diagnosing Error in Object Detectors
Hoiem, D., Chodpathumwan, Y., & Dai, Q. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33712-3_25 · Cited by 520
Semantic Segmentation with Second-Order Pooling
Carreira, J., Caseiro, R., Batista, J. P., & Sminchisescu, C. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33786-4_32 · Cited by 468
Combining randomization and discrimination for fine-grained image categorization
Yao, B., Khosla, A., & Fei-Fei, L. (2011) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2011.5995368 · Cited by 291
Wasserman, L. (2021) · Cited by 289
Color attributes for object detection
Khan, F. S., Anwer, R. M., van de Weijer, J., Bagdanov, A. D., Vanrell, M., & López, A. M. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6248068 · Cited by 277
Latent hierarchical structural learning for object detection
Zhu, L., Chen, Y., Yuille, A., & Freeman, W. T. (2010) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2010.5540096 · Cited by 255
Contextualizing object detection and classification
Zheng, S., Chen, Q. K., Huang, Z., Yang, H., & Yan, S. (2011) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2011.5995330 · Cited by 187
Object-Centric Spatial Pooling for Image Classification
Russakovsky, O., Lin, Y., Yu, K., & Fei-Fei, L. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33709-3_1 · Cited by 181
Best practice guidelines: Fetal surgery
Sudhakaran, N., Sothinathan, U., & Patel, S. (2011) · Early Human Development · doi:10.1016/j.earlhumdev.2011.11.006 · Cited by 166
Modulating Shape Features by Color Attention for Object Recognition
Khan, F. S., van de Weijer, J., & Vanrell, M. (2011) · International Journal of Computer Vision · doi:10.1007/s11263-011-0495-2 · Cited by 125
Nonparametric confidence intervals for receiver operating characteristic curves
Hall, P., Hyndman, R. J., & Fan, Y. (2004) · Biometrika · doi:10.1093/biomet/91.3.743 · Cited by 60
Image segmentation by figure-ground composition into maximal cliques
Ion, A., Carreira, J., & Sminchisescu, C. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126486 · Cited by 43
Probabilistic Joint Image Segmentation and Labeling
Ion, A., Carreira, J., & Sminchisescu, C. (2011) · Cited by 36
Heterogeneous bag-of-features for object/scene recognition
Nanni, L., & Lumini, A. (2013) · Applied Soft Computing · doi:10.1016/j.asoc.2012.12.013 · Cited by 34
On Recognizing Actions in Still Images via Multiple Features
Şener, F., Bas, C., & İkizler-Cinbiş, N. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33885-4_27 · Cited by 30
Object Reading: Text Recognition for Object Recognition
Karaoğlu, S., van Gemert, J. C., & Gevers, T. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33885-4_46 · Cited by 30
Composite Statistical Inference for Semantic Segmentation
Li, F., Carreira, J., Lebanon, G., & Sminchisescu, C. (2013) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2013.424 · Cited by 27
van Gemert, J. C. (2011) · International Conference on Multimedia Retrieval · doi:10.1145/1991996.1992010 · Cited by 27
Wang, X., Lin, L., Huang, L., & Yan, S. (2013) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2013.428 · Cited by 21
Segmentation over Detection by Coupled Global and Local Sparse Representations
Xia, W., Zheng, S., Feng, J., Cheong, L., & Yan, S. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33715-4_48 · Cited by 19
On Bootstrapping the ROC Curve
Bertail, P., Clémençon, S., & Vayatis, N. (2008) · Cited by 15
Zisserman, A., Winn, J. M., Fitzgibbon, A. W., Gool, L. V., Šivic, J., Williams, C., & Hogg, D. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.204 · Cited by 4
Self-citationEfficient Kernels Couple Visual Words Through Categorical Opponency
Alexiou, I., & Bharath, A. A. (2012) · British Machine Vision Conference (BMVC) · doi:10.5244/c.26.82 · Cited by 2
Research works printed but not linked: 2
- Chen, Q., Song, Z., Hua, Y., Huang, Z., & Yan, S. (2012). Generalized hierarchical matching for image classification. In Proceedings of Conference on Computer Vision and Pattern Recognition.
- Hoai, M., Ladicky, L., & Zisserman, A. (2012). Action Recognition from Still Images by Aligning Body Parts. http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2012/workshop/segmentation_action_layout.pdf . Slides contained in the presentation by Luc van Gool on Overview and results of the segmentation challenge and action taster.
Cited by
Sorted by citations
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
Self-citationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
“We implement this model as a convolutional neural network and evaluate it on the PASCAL VOC detection dataset [9].”
MethodImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
Metadata
- Authors
- Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A.
- Affiliations
- University of Leeds (GB)
- Microsoft Research (United Kingdom) (GB)
- University of Edinburgh (GB)
- University of Oxford (GB)
- Corresponding author
- Eslami, S. M. Ali
- Venue
- International Journal of Computer Vision
- Published
- 2014-06-25
- Volume
- 111
- Issue
- 1
- Pages
- 98-136
- ISSN
- 0920-5691 (ISSN-L)
- 1573-1405
- OpenAlex
- W2037227137
- Semantic Scholar
- 616b246e332573af1f4859aa91440280774c183a
- Cited by
- 7,139
- References
- 52
- Citations by year
- 2026: 339 · 2025: 572 · 2024: 685 · 2023: 822 · 2022: 747 · 2021: 879 · 2020: 767 · 2019: 676 · 2018: 482 · 2017: 325 · 2016: 287 · 2015: 223 · 2014: 163
- FWCI
- 297.57
- Type
- journal article
- Language
- en
- Open access
- Licence
- other-oa
- www.springer.com/tdm (tdm)
- Locations
- International Journal of Computer Vision (publishedVersion)
- Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, other-oa)
- Lirias (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- image classification, object detection, image segmentation, action classification, evaluation metrics, bootstrapping, algorithm comparison, error analysis, challenge design
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-06, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-06 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
