Sampling Strategies for Bag-of-Features Image Classification
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“First, it is widely accepted that denser sampling of subsequences yields a better performance [24,39], so l is set to 1.”
From Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors (2018) · cites this paper as [39]
Citations
Cites
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
Text categorization with Support Vector Machines: Learning with many relevant features
Joachims, T. (1998) · Lecture Notes in Computer Science · doi:10.1007/bfb0026683 · Cited by 7,999
Video Google: a text retrieval approach to object matching in videos
Sivic, & Zisserman (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238663 · Cited by 6,367 · cited 4×
“) as samplers [4, 1, 2, 5, 6, 7, 8, 9, 10, 11], but although such detectors have proven their value in matching applications, they were not designed to find the most informative patches for image classification and there is some evidence that they do not do so [12, 13].”
InfluentialThe Earth Mover's Distance as a Metric for Image Retrieval
Rubner, Y., Tomasi, C., & Guibas, L. J. (2000) · International Journal of Computer Vision · doi:10.1023/a:1026543900054 · Cited by 4,568
Visual categorization with bags of keypoints
Csurka, G. (2004) · Cited by 4,379
A comparison of affine region detectors
Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., & Gool, L. V. (2005) · International Journal of Computer Vision · doi:10.1007/s11263-005-3848-x · Cited by 2,939
Object class recognition by unsupervised scale-invariant learning
Fergus, R., Perona, P., & Zisserman, A. (2003) · 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings. · doi:10.1109/cvpr.2003.1211479 · Cited by 2,023
Zhang, J., Marszałek, M., Lazebnik, S., & Schmid, C. (2007) · International Journal of Computer Vision · doi:10.1007/s11263-006-9794-4 · Cited by 1,923
QBIC project: querying images by content, using color, texture, and shape:
Niblack, C. W., Barber, R., Equitz, W., Flickner, M. D., Glasman, E. H., Petkovic, D., Yanker, P., Faloutsos, C., & Taubin, G. (1993) · SPIE Proceedings · doi:10.1117/12.143648 · Cited by 1,747
Representing and Recognizing the Visual Appearance of Materials Using Three-Dimensional Textons
Leung, T., & Malik, J. (2001) · International Journal of Computer Vision · doi:10.1023/a:1011126920638 · Cited by 1,498 · cited 4×
“Patches are selected using keypoints [4, 1, 2, 5, 6, 7, 8, 9, 10, 11] or densely [3, 13, 15].”
Influential
Research works printed but not linked: 1
- Niblack, W., Barber, R., Equitz, W., Flickner, M., Glasman, D., Petkovic, D., Yanker, P.: The qbic project: Querying image by content using color, texture, and shape. SPIE 1908, 173–187 (1993)
Cited by
Items 201–300 of 925
Ordered Trajectories for Large Scale Human Action Recognition
Murthy, O. V. R., & Goecke, R. (2013) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2013.61 · Cited by 47
“[16] showed by extensive experiments that uniform random sampling can provide performances comparable to dense sampling of interest points.”
BackgroundFace recognition in the SWIR band when using single sensor multi-wavelength imaging systems
Narang, N., & Bourlai, T. (2014) · Image and Vision Computing · doi:10.1016/j.imavis.2014.10.005 · Cited by 39
“For the multiclass image classification [12], authors proposed the bag of features method to classify the images.”
MethodSpeeded-up Bag-of-Words algorithm for robot localisation through scene recognition
Botterill, T., Mills, S. J., & Green, R. (2008) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2008.4762067 · Cited by 39
“[11]).”
BackgroundSampling Strategies for GAN Synthetic Data
Bhattarai, B., Baek, S., Bodur, R., & Kim, T. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054677 · Cited by 48
“Inspired from the success of seminal work on simple yet effective, sampling strategies of bag-of-features for image classification (Nowak, Jurie, and Triggs 2006), we propose two different simple, effective and easy to implement approaches to sub-sample useful synthetic data from a large volume of…”
MethodGraph commute times for image representation
Behmo, R., Nikos Paragios, A., & Prinet, V. (2008) · 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.2008.4587840 · Cited by 39
“Bag of features approaches have been shown to be more efficient with codebook sizes of the order of a thousand [17]; however, we have seen that if K is the codebook size the dimension of the image descriptor will be K(K + 1)/2.”
BackgroundMethodRemote Sensing Image Classification: No Features, No Clustering
Cui, S., Schwarz, G., & Datcu, M. P. (2015) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2015.2495267 · Cited by 41
“performance than the SIFT detector as long as the number of patches is sufficiently high [8], [9].”
BackgroundDrosophila gene expression pattern annotation using sparse features and term-term interactions
Ji, S., Yuan, L., Li, Y., Zhou, Z., Kumar, S., & Ye, J. (2009) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/1557019.1557068 · Cited by 39
“The methods for localizing patches on images can be categorized into three classes including affine-region-detector-based methods [17], sampling-based methods [19], and regular-patch-based methods [3].”
MethodLanguage-Motivated Approaches to Action Recognition
Malgireddy, M. R., Nwogu, I., & Govindaraju, V. (2017) · The Springer series on challenges in machine learning · doi:10.1007/978-3-319-57021-1_5 · Cited by 36
Toward A Discriminative Codebook: Codeword Selection across Multi-resolution
Wang, L. (2007) · 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.2007.383374 · Cited by 37
“The work in [16] conducts an experimental study about the “Bag-of-features” approach and reports that a suitable codebook size has to be sough to avoid the performance degradation.”
BackgroundTowards Zero Re-Training for Long-Term Hand Gesture Recognition via Ultrasound Sensing
Yang, X., Zhou, D., Zhou, Y., Huang, Y., & Liu, H. (2018) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2018.2867539 · Cited by 37
“overlarge codebook size might cause over-fitting and reduce the generalization ability of the BoF-model [35], [36].”
BackgroundAutomatic Detection of Rail Surface Cracks with a Superpixel-Based Data-Driven Framework
Wang, L., Li, Z., & Zhang, Z. (2018) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)cp.1943-5487.0000799 · Cited by 38
Intelligent image classification-based on spatial weighted histograms of concentric circles
Zafar, B., Ashraf, R., Ali, N., Ahmed, M., Jabbar, S., Naseer, K., Ahmad, A., & Jeon, G. (2018) · Computer Science and Information Systems · doi:10.2298/csis180105025z · Cited by 37
“The steps used in the BoVW model are (i) feature extraction using a key-point detector (ii) codebook construction (iii) representation of the image as an orderless histogram of visual words [29, 23].”
BackgroundMethodAn Efficient Algorithm for Detection of Vacant Spaces in Delimited and Non-Delimited Parking Lots
Varghese, A., & Sreelekha, G. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2934574 · Cited by 40
“al [40] shows that dense randomly sampled patches are often more discriminative than keypoint ones in classification applications.”
BackgroundCirculant Temporal Encoding for Video Retrieval and Temporal Alignment
Douze, M., Revaud, J., Verbeek, J. J., Jeǵou, H., & Schmid, C. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0875-0 · Cited by 43
“First, local SIFT descriptors [27] are extracted for each frame on a dense grid [29], every 4 pixels and at 5 scale levels.”
MethodLearning-based Face Synthesis for Pose-Robust Recognition from Single Image
Asthana, A., Sanderson, C., Gedeon, T., & Goecke, R. (2009) · British Machine Vision Conference (BMVC) · doi:10.5244/c.23.31 · Cited by 36
“The MRH approach is motivated by the concept of ‘visual words’ used in image categorisation [10], which can be briefly described as follows.”
MethodMulti-layer multi-view topic model for classifying advertising video
Hou, S., Chen, L., Tao, D., Zhou, S., Liu, W., & Zheng, Y. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.03.003 · Cited by 38
Hou, Y., Xie, X., Chen, J., Lv, P., Jiang, S., He, X., Yang, L., & Zhao, F. (2020) · European Radiology · doi:10.1007/s00330-020-07110-2 · Cited by 38
“The basic idea is to treat an image as a collection of patches and then cluster the visual features of all the patches as a characterization of the image [35].”
BackgroundGlobal annotation on georeferenced photographs
Kleban, J., Moxley, E., Xu, J., & Manjunath, B. S. (2009) · ACM International Conference on Image and Video Retrieval (CIVR) · doi:10.1145/1646396.1646413 · Cited by 36
“Sift Signature: The SIFT feature represents the SIFT descriptors [12] extracted at 5000 random keypoints [13] and pushed through a vocabulary tree with 4 levels and a branching factor of 10, as advanced by Nister and Stewenius [14].”
MethodAn empirical study on image bag generators for multi-instance learning
Wei, X.-S., & Zhou, Z. (2016) · Machine Learning · doi:10.1007/s10994-016-5560-1 · Cited by 46
“Mach Learn (2016) 105:155–198 157 with the conclusion in computer vision (Li and Perona 2005; Nowak et al. 2006); miGraph, MIBoosting and miFV stress the relationship between instances in MIL bags, which do not adopt the standard MIL assumption (i.”
BackgroundResultInfluentialExtremal Regions Detection Guided by Maxima of Gradient Magnitude
Faraji, M., Shanbehzadeh, J., Nasrollahi, K., & Moeslund, T. B. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2477215 · Cited by 34
“Some known works such as bag-of-features [2], multi-resolution bag-of-features [3], and”
BackgroundX-ray image categorization and retrieval using patch-based visualwords representation
Avni, U., Greenspan, H. K., Sharon, M., Konen, E., & Goldberger, J. (2009) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2009.5193056 · Cited by 34
“This work presents a classification and retrieval system that is based on the Visual Words (VW) paradigm which is a recently introduced concept that has been successfully applied to scenery image classification tasks (see e.g. [5, 3, 4]).”
MethodMedical Image Retrieval via Histogram of Compressed Scattering Coefficients
Lan, R., & Zhou, Y. (2016) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2016.2623840 · Cited by 35
Structured representations in a content based image retrieval context
Raveaux, R., Burie, J.-C., & Ogier, J.-M. (2013) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2013.08.010 · Cited by 34
Computer vision for virus image classification
dos Santos, F. L. C., Paci, M., Nanni, L., Brahnam, S., & Hyttinen, J. (2015) · Biosystems Engineering · doi:10.1016/j.biosystemseng.2015.01.005 · Cited by 33
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 38
“Another interesting result is reported in [21], where it is shown that, when the number of regions is quite large, random sampling gives equal or better classification rates than the other more complex operators that are in common use.”
BackgroundBarata, C., Marques, J. S., & Rozeira, J. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-41914-0_5 · Cited by 32
“These are usually an extension of corner, blobs or curvilinear structures detectors towards the scale invariance property [14].”
BackgroundClustering Crowdsourced Test Reports of Mobile Applications Using Image Understanding
Лю, Д., Feng, Y., Zhang, X., Jones, J. A., & Chen, Z. (2020) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2020.3017514 · Cited by 36
Hu, J., Xia, G.-S., Hu, F., & Zhang, L. (2015) · Remote Sensing · doi:10.3390/rs71114988 · Cited by 40
“Surprisingly, it has been found that random sampling, another sampling method, is often more discriminant than keypoint-based methods [18,19].”
BackgroundResultInfluentialCoarse-grained ancient coin classification using image-based reverse side motif recognition
Anwar, H., Zambanini, S., & Kampel, M. (2015) · Machine Vision and Applications · doi:10.1007/s00138-015-0665-2 · Cited by 35
“Size of visual vocabulary The size of the visual vocabulary is a major parameter as evaluated by [6,15].”
Zhang, Y., Allem, J.-P., Unger, J. B., & Cruz, T. B. (2018) · Journal of Medical Internet Research · doi:10.2196/10513 · Cited by 39
Leonardis, A., Pinz, A. J., Bischof, H., & 2006, E. (2006) · Lecture notes in computer science · doi:10.1007/11744085 · Cited by 32
FEATURE VECTOR APPROXIMATION BASED ON WAVELET NETWORK
Dammak, M., Mejdoub, M., Zaied, M., & Amar, C. B. (2012) · International Conference on Agents and Artificial Intelligence (ICAART) · doi:10.5220/0003776803940399 · Cited by 31
“Research suggests that a regular dense sampling of descriptors can provide a better representation (Lazebnik et al., 2006; Nowak et al., 2006) than the “interest” points.”
BackgroundScale coding bag of deep features for human attribute and action recognition
Khan, F. S., van de Weijer, J., Anwer, R. M., Bagdanov, A. D., Felsberg, M., & Laaksonen, J. T. (2017) · Machine Vision and Applications · doi:10.1007/s00138-017-0871-1 · Cited by 35
“The standard approach for feature detection is to use dense multi-scale feature sampling [23,43,52] by scanning the image at multiple scales at fixed locations on a grid of rectangular patches.”
A Leaf Recognition Approach to Plant Classification Using Machine Learning
Ali, R. A., Hardie, R. C., & Essa, A. E. (2018) · IEEE National Aerospace and Electronics Conference (NAECON) · doi:10.1109/naecon.2018.8556785 · Cited by 31
“in the computer vision community because of the simplicity, robustness, and good practical performance [10].”
BackgroundA biased sampling strategy for object categorization
Yang, L., Zheng, N., Yang, J., Chen, M., & Chen, H. (2009) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2009.5459349 · Cited by 31
“dom sampling [19], and concurrency context saliency based sampling [23] on two different data sets: Graze-02 [20] and VOC2005 [7].”
BackgroundMethodInfluentialSpatial-DiscLDA for visual recognition
Niu, Z., Hua, G., Gao, X., & Tian, Q. (2011) · doi:10.1109/cvpr.2011.5995426 · Cited by 30
A novel image retrieval method based on multi-features fusion
Niu, D., Zhao, X., Lin, X., & Zhang, C. (2020) · Signal Processing Image Communication · doi:10.1016/j.image.2020.115911 · Cited by 32
Comparing visual representations across human fMRI and computational vision
Leeds, D., Seibert, D., Pyles, J. A., & Tarr, M. J. (2013) · Journal of Vision · doi:10.1167/13.13.25 · Cited by 40
“…SIFT and Gabor filter bank, despite the overlap of their corresponding match regions in neuroimaging data, may reflect the removal of image location-specific information encoded in the Gabor filter bank but discarded in the bag-of-features evaluation of SIFT descriptors (Nowak et al., 2006).”
BackgroundMethodInfluentialSpace-Time Shapelets for Action Recognition
Batra, D., Chen, T., & Sukthankar, R. (2008) · IEEE Workshop on Motion and Video Computing · doi:10.1109/wmvc.2008.4544051 · Cited by 30
“[16] 3Ke et al.”
On the Generality of Codebook Approach for Sensor-Based Human Activity Recognition
Shirahama, K., & Grzegorzek, M. (2017) · Electronics · doi:10.3390/electronics6020044 · Cited by 29
“In image/video classification, it is widely accepted that denser sampling leads to a better performance [45,47].”
BackgroundA review of object representation based on local features
Cao, J., Mao, D., Cai, Q., Li, H., & Du, J. (2013) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/jzus.cide1303 · Cited by 31
“In comparison with the detectors described above, Nowak et al. (2006) found that random sampling gives equal or better classifiers.”
ResultYang, F., Lu, H., & Chen, Y. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.46 · Cited by 29
“The merit of random sampling is testified in [10].”
BackgroundMethodAC-Net: Assessing the Consistency of Description and Permission in Android Apps
Feng, Y., Chen, L., Zheng, A., Gao, C., & Zheng, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2912210 · Cited by 30
“For feature engineering-based studies, most of them use Bag Of Words [57] or Vector Space Model [58] for text representation.”
MethodMachine learning method for cosmetic product recognition: a visual searching approach
Umer, S., Mohanta, P. P., Rout, R. K., & Pandey, H. M. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09079-y · Cited by 39
“– BoW :- BoW stands for Bag-of-words model [35] which is widely used in various challenging computer vision problems.”
BackgroundChia, A. Y., Rajan, D., Leung, M. K. H., & Rahardja, S. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.220 · Cited by 29
“Several other authors [33], [34] have also independently concluded that a single interest region detector cannot provide sufficient regions to represent an object class and have instead resorted either to using a wide plethora of region detectors or to densely sampling image regions at every pixel location as done in…”
BackgroundMaking Visual Object Categorization More Challenging: Randomized Caltech-101 Data Set
Kinnunen, T., Kämäräinen, J., Lensu, L. T., Lankinen, J., & Kalviainen, H. A. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.124 · Cited by 29
“In the second stage, we cluster the descriptors with the self-organising map (SOM) [7] instead of, for example, K-Means [11] [17].”
Keuper, J., & Pfreundt, F. (2015) · doi:10.1145/2834892.2834893 · Cited by 31
“A common approach is to extract low level image features and then to generate a “Codebook” of universal image parts, the so-called Bag of Features [14].”
BackgroundA visual analysis of the relationship between word concepts and geographical locations
Yanai, ., Kawakubo, H., & Qiu, B. (2009) · ACM International Conference on Image and Video Retrieval (CIVR) · doi:10.1145/1646396.1646414 · Cited by 28
“Sample 3000 patches per image randomly in the same way as [17].”
BackgroundEfficiently searching for similar images
Grauman, K. L. (2010) · Communications of the ACM · doi:10.1145/1743546.1743570 · Cited by 31
“Compounding that cost is empirical evidence showing how much recognition accuracy improves when larger and denser feature sets are used [34].”
A scalable pattern spotting system for historical documents
En, S., Petitjean, C., Nicolas, S., & Heutte, L. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.01.014 · Cited by 32
“Patches may be obtained via dense sampling, sampling with key-point detectors or by random sampling [35].”
Learning group-based dictionaries for discriminative image representation
Hao, L., Mei, K., Zheng, N., Dong, P., Zhou, N., & Jianping Fan, B. (2013) · Pattern Recognition · doi:10.1016/j.patcog.2013.07.016 · Cited by 26
Accurate HEp-2 cell classification based on Sparse Coding of Superpixels
Ensafi, S., Lu, S., Kassim, A. A., & Tan, C. L. (2016) · Pattern Recognition Letters · doi:10.1016/j.patrec.2016.02.007 · Cited by 27
Santoso, F., & Finn, A. (2023) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2023.3302807 · Cited by 31
An Image Classification Algorithm Based on Bag of Visual Words and Multi-kernel Learning
Lou, X., Huang, D., Lu-ming, F. A. N., & Xu, A. (2014) · Journal of Multimedia · doi:10.4304/jmm.9.2.269-277 · Cited by 31
“In [13] a method derived from Spatial Pyramid Matching was proposed.”
MethodPlace recognition based on deep feature and adaptive weighting of similarity matrix
Li, Q., Li, K., You, X., Bu, S., & Liu, Z. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.03.029 · Cited by 27
“The method is termed Bag-of-Words (BoW) [11], which has achieved excellent performances on many vision applications, such as the object recognition, content-based image retrieval (CBIR), and image classification and annotation [12,13].”
MethodRecognizing white blood cells with local image descriptors
López-Puigdollers, D., Traver, V. J., & Pla, F. (2018) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.08.029 · Cited by 28
SUPER: towards real-time event recognition in internet videos
Jiang, Y. (2012) · International Conference on Multimedia Retrieval · doi:10.1145/2324796.2324805 · Cited by 27
“Dense sampling has been shown to produce comparable or even better performance in visual recognition tasks [17].”
BackgroundRepresentations and Techniques for 3D Object Recognition & Scene Interpretation
Hoiem, D., & Savarese, S. (2011) · Cited by 28
Classifying advertising video by topicalizing high-level semantic concepts
Hou, S., Zhou, S., Liu, W., & Zheng, Y. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-5801-3 · Cited by 27
“3 Histogram-of-object representation At present, image representation are becoming high-level oriented [19, 23, 28, 30].”
BackgroundImage classification using SURF and bag of LBP features constructed by clustering with fixed centers
Srivastava, D., Bakthula, R., & Agarwal, S. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6793-8 · Cited by 26
“These constructed Bag Of FeaturesCD1B , CD 2 B, ..., CD 10 B for all the 10 categories are used to train SVM to form Trained Category (T C).”
BackgroundInfluentialBoSR: A CNN-based aurora image retrieval method
Yang, X., Wang, N., Song, B., & Gao, X. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.04.012 · Cited by 28
Muñoz-Rodenas, J., García-Sevilla, F., Coello-Sobrino, J., Martínez-Martínez, A., & Miguel-Eguía, V. (2023) · Applied Sciences · doi:10.3390/app13063479 · Cited by 23
Hu, J., Xia, G.-S., Hu, F., Sun, H., & Zhang, L. (2015) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2015.7326290 · Cited by 27
“Although this work has been done by [3] in the field of natural image classification, one can not just borrow the conclusions from natural images to HRRS imagery as there is much difference between them, e.”
BackgroundHazelhoff, L., Creusen, I. M., & de With, P. H. N. (2012) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2012.6163006 · Cited by 26
“Then, SIFT features [11] are extracted using dense sampling, which is shown to outperform the use of interest point operators [14].”
MethodA comparison of feature detectors and descriptors for object class matching
Hietanen, A., Lankinen, J., Kämäräinen, J., Buch, A. G., & Krüger, N. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.08.106 · Cited by 31
“This is justified as some works claim that “the more the merrier” [25].”
BackgroundRepresentations and Techniques for 3D Object Recognition and Scene Interpretation
Hoiem, D., & Savarese, S. (2011) · Synthesis lectures on artificial intelligence and machine learning · doi:10.2200/s00370ed1v01y201107aim015 · Cited by 28
Learning Midlevel Image Features for Natural Scene and Texture Classification
Borgne, H. L., Guérin-Dugué, A., & O'Connor, N. E. (2007) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2007.890635 · Cited by 26
“One could think this feature is not adapted to the type of image that is classified here, since a large part of the work using these feature focussed on object classification (for instance [ 51 ]).”
MethodIndexing of the CNN features for the large scale image search
Liu, R., Wei, S., Zhao, Y., & Yang, Y. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6210-3 · Cited by 28
“[68] utilize inverted table in the vision task that indexes images described by hand-crafted local features via the bog-of-word (BoW) model [59, 60].”
Learning structured visual dictionary for object tracking
Yang, F., Lu, H., & Yang, M. (2013) · Image and Vision Computing · doi:10.1016/j.imavis.2013.09.008 · Cited by 24
“[19] show that random sampling with bag of features hasmore discriminative power than that with interest point detectors when a large number of patches are used.”
BackgroundImproving Deep Forest by Screening
Pang, M., Ting, K. M., Zhao, P., & Zhou, Z. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.3038799 · Cited by 27
The Visual Extent of an Object
Uijlings, J., Smeulders, A. W. M., & Scha, R. J. H. (2011) · International Journal of Computer Vision · doi:10.1007/s11263-011-0443-1 · Cited by 25
“In the final step, the quantity of visual words was found to be more important than the quality of the location of the visual words (Jurie and Triggs 2005; Nowak et al. 2006 ).”
BackgroundMethodInfluentialRealistic human action recognition by Fast HOG3D and self-organization feature map
Li, N., Cheng, X., Zhang, S., & Wu, Z. (2014) · Machine Vision and Applications · doi:10.1007/s00138-014-0639-9 · Cited by 25
“Although [7] points out that dense sampling can achieve comparable or better performance in image classification, the authors admit that it would not outperform STIPs if the number of patches is limited.”
BackgroundRecognizing clothes patterns for blind people by confidence margin based feature combination
Yang, X., Yuan, S., & Tian, Y. (2011) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2072298.2071947 · Cited by 25
“The bag-ofwords model [7] is then used to quantize local image descriptors to visual words in finite vocabularies.”
MethodImproving Bag-of-Words model with spatial information
Zhang, E., & Mayo, M. (2010) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2010.6148795 · Cited by 25
Images as sets of locally weighted features
de Campos, T. E., Csurka, G., & Perronnin, F. (2011) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2011.07.011 · Cited by 27
“Corresponding author: Teófilo E. de Campos, t.decampos@st-annes.oxon.org Gabriela Csurka and Florent Perronnin are with Xerox Research Centre Europe, 6, chemin de Maupertuis, 38240 Meylan, France”
Background3D object classification in baggage computed tomography imagery using randomised clustering forests
Mouton, A., Breckon, T. P., Flitton, G. T., & Megherbi, N. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7026053 · Cited by 28
Segmentation-based multi-class semantic object detection
Vieux, R., Benois‐Pineau, J., Domenger, J., & Braquelaire, A. J. P. (2010) · Multimedia Tools and Applications · doi:10.1007/s11042-010-0611-2 · Cited by 25
“[21] have shown that random sampling of interest points gives equal or better classifiers than”
BackgroundInstance search retrospective with focus on TRECVID
Awad, G., Kraaij, W., Over, P., & Satoh, S. (2017) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-017-0121-3 · Cited by 30
“In an image categorization scenario, it is known that interest point detection is not very helpful, but instead, sampling strategy especiallywith high density (sometimes called dense sampling) is more effective [49,75].”
Frontiers of Multimedia Research
Chang, S.-F. (2017) · doi:10.1145/3122865 · Cited by 27
CLEF2007 Image Annotation Task: an SVM-based Cue Integration Approach
Tommasi, T., Orabona, F., & Barbara Caputo, B. (2007) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · Cited by 25
Filtering Internet image search results towards keyword based category recognition
Wnuk, K., & Soatto, S. (2008) · 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.2008.4587621 · Cited by 25
“To reflect current trends in computer vision, we used a simple bag-of-features approach, as proposed by [11, 12], the implementation of which has been made available at [18].”
MethodShirahama, K., & Grzegorzek, M. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-014-2292-8 · Cited by 24
“Indeed, the performance is improved as the number of sampled local descriptors increases [84].”
BackgroundA New Bag of Words LBP (BoWL) Descriptor for Scene Image Classification
Banerji, S., Sinha, A., & Liu, C. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40261-6_59 · Cited by 24
Enhanced bag of visual words representations for content based image retrieval: a comparative study
Arun, K. S., Govindan, V. K., & Kumar, S. D. M. (2019) · Artificial Intelligence Review · doi:10.1007/s10462-019-09715-6 · Cited by 28
Lightweight FaceNet Based on MobileNet
Xu, X., Du, M., Guo, H., Chang, J., & Zhao, X. (2020) · International Journal of Intelligence Science · doi:10.4236/ijis.2021.111001 · Cited by 24
“At present, there are some tasks such as image classification [7], face recognition [8] [9] [10] and object detection [11] in the field of computer vision.”
BackgroundSuneetha, M., Prasad, M. V. D., & Kishore, P. V. V. (2021) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2021.103161 · Cited by 28
Coelho, L. P., Pato, C., Friães, A., Neumann, A., von Köckritz‐Blickwede, M., Ramirez, M., & Carriço, J. A. (2015) · Bioinformatics · doi:10.1093/bioinformatics/btv156 · Cited by 27
An Informed System Development Approach to Tropical Cyclone Track and Intensity Forecasting
Roy, C. (2016) · Linköping studies in science and technology. Dissertations · doi:10.3384/diss.diva-123198 · Cited by 24
Micro‐structural tissue analysis for automatic histopathological image annotation
Díaz, G. M., & Romero, E. (2011) · Microscopy Research and Technique · doi:10.1002/jemt.21063 · Cited by 23
“Such selectors have proven their effectiveness in matching and classifying natural scenes (Jiang et al., 2007; Nowak et al., 2006; Yang et al., 2009), but they were not designed at all for capturing the relevant patches of histopathology images.”
BackgroundInfluentialA Gestalt inference model for auditory scene segregation
Chakrabarty, D., & Elhilali, M. (2019) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1006711 · Cited by 26
Anwar, H., Zambanini, S., Kampel, M., & Vondrovec, K. (2015) · IEEE Signal Processing Magazine · doi:10.1109/msp.2015.2409331 · Cited by 23
“[29] E.”
MethodScene Classification Using Spatial Pyramid of Latent Topics
Ergül, E., & Arıca, N. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.879 · Cited by 23
“BoW approaches are still the most promising methods in the previous works for general scene classification [6, 9].”
MethodPixel-Wise Spatial Pyramid-Based Hybrid Tracking
Lu, H., Lu, S., Wang, D., Wang, S., & Leung, H. (2012) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2012.2201794 · Cited by 24
“Owing to its simplicity and outstanding performance, bag of visual words (bag of features) [24], [25] representations have become popular in content-based image classification and object localization.”
BackgroundKIRMES: kernel-based identification of regulatory modules in euchromatic sequences
Schultheiß, S. J., Busch, W., Lohmann, J. U., Kohlbacher, O., & Rätsch, G. (2009) · Bioinformatics · doi:10.1093/bioinformatics/btp278 · Cited by 23
Improving Bag of Visual Words Image Retrieval: A Fuzzy Weighting Scheme for Efficient Indexation
Bouachir, W., Kardouchi, M., & Belacel, N. (2009) · International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) · doi:10.1109/sitis.2009.43 · Cited by 23
“We have also seen the use of normalized term frequency (txc) [17] and binary weights (bxx) [ 18 ] for image classification.”
MethodSketch recognition using transfer learning
Sert, M., & Boyacı, E. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-018-7067-1 · Cited by 23
Let the kernel figure it out; Principled learning of pre-processing for kernel classifiers
Gehler, P., & Nowozin, 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.2009.5206592 · Cited by 23
“We test the codebook learning approach on four datasets Brodatz, KTH-TIPS, UIUCTex and Graz-02, some of which were also used in [14] to investigate the influence of codebook generation and sampling methods.”
MethodResultMeasuring the Coverage of Interest Point Detectors
Ehsan, S., Kanwal, N., Clark, A. F., & McDonald-Maier, K. D. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-21593-3_26 · Cited by 23
“However, it has been emphasized that repeatability is not the only characteristic that guarantees performance in a particular vision application [5,9]; other attributes, such as efficiency and the density of detected features, are also important.”
BackgroundRandomized Locality Sensitive Vocabularies for Bag-of-Features Model
Mu, Y., Sun, J., Han, T. X., Cheong, L., & Yan, S. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15558-1_54 · Cited by 26
“Unlike the traditional dense sampling strategy on a uniform 2-D image grid, we determine both the locations and scales of each SIFT feature in a random way [23], ignoring more complex and effective sampling schemes such as [24].”
BackgroundMultimedia semantics-aware query-adaptive hashing with bits reconfigurability
Mu, Y., Chen, X., Liu, X., Chua, T., & Yan, S. (2012) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-012-0003-7 · Cited by 23
Metadata
- Authors
- Nowak, E., Jurie, F., & Triggs, B.
- Affiliations
- Centre National de la Recherche Scientifique (FR)
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Berlin Heidelberg
- Published
- 2006
- Volume
- 3954
- Pages
- 490-503
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W2171896402
- Cited by
- 927
- References
- 26
- Citations by year
- 2026: 1 · 2025: 3 · 2024: 7 · 2023: 10 · 2022: 11 · 2021: 17 · 2020: 35 · 2019: 44 · 2018: 55 · 2017: 59 · 2016: 73 · 2015: 77 · 2014: 78 · 2013: 82 · 2012: 56
- FWCI
- 42.67
- Type
- conference paper
- Language
- en
- Open access
- green
- hal.science
- Licence
- other-oa
- www.springer.com/tdm (tdm)
- Locations
- Lecture notes in computer science (publishedVersion)
- HAL (submittedVersion, other-oa)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Keywords
- bag of visual words, content-based image classification, patch sampling, random sampling, image descriptors, codebook size, histogram normalization, texture analysis
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.
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.