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
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
“, 2009) using a bag of features approach (Nowak et al., 2006) to extract regions of interest.”
MethodImage Super-Resolution Via Sparse Representation
Yang, J., Wright, J., Huang, T. S., & Ma, Y. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2010.2050625 · Cited by 5,217
An analysis of single-layer networks in unsupervised feature learning
Coates, A., Ng, A. Y., & Lee, H. (2011) · International Conference on Artificial Intelligence and Statistics · Cited by 4,675
Action recognition by dense trajectories
Wang, H., Klaser, A., Schmid, C., & Liu, C.-L. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995407 · Cited by 2,154
“The trajectories are obtained by tracking densely sampled points using optical flow fields.”
MethodUnderstanding deep image representations by inverting them
Mahendran, A., & Vedaldi, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299155 · Cited by 1,827
Dense Trajectories and Motion Boundary Descriptors for Action Recognition
Wang, H., Kläser, A., Schmid, C., & Liu, C.-L. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-012-0594-8 · Cited by 1,669
“We show that motion boundaries provide a robust descriptor for action recognition that significantly outperforms existing state-of-the-art descriptors.”
BackgroundContext-Aware Saliency Detection
Goferman, S., Zelnik-Manor, L., & Tal, A. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.272 · Cited by 1,567
Image super-resolution as sparse representation of raw image patches
Yang, J., Wright, J., Huang, T., & Ma, Y. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587647 · Cited by 1,475
“4The competitiveness of such random patches has also been noticed empirically in the context of content-based image classification [18].”
BackgroundUnderstanding bag-of-words model: a statistical framework
Zhang, Y., Jin, R., & Zhou, Z.-H. (2010) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-010-0001-0 · Cited by 1,384
“Finally, we would like to point out that although several randomized approaches (Moosmann et al., 2007; Nowak et al., 2006; Viitaniemi and Laaksonen, 2008) have been proposed for key point quantization, none of them provides theoretical analysis on statistical consistency.”
BackgroundLocal Invariant Feature Detectors: A Survey
Tuytelaars, T., & Mikolajczyk, K. (2007) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000017 · Cited by 1,186
Semantic texton forests for image categorization and segmentation
Shotton, J., Johnson, M., & Cipolla, R. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587503 · Cited by 1,014
“[19]) or more densely; recent results in [22] suggest that densely sampling visual words improves categorization performance.”
Multimodal Distributional Semantics
Bruni, E., Tran, N. K., & Baroni, M. (2014) · Journal of Artificial Intelligence Research · doi:10.1613/jair.4135 · Cited by 908
Context-aware saliency detection
Goferman, S., Zelnik-Manor, L., & Tal, A. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539929 · Cited by 753
Multiple instance learning: A survey of problem characteristics and applications
Carbonneau, M.-A., Cheplygina, V., Granger, E., & Gagnon, G. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.10.009 · Cited by 740
“This agrees with other bag-of-words (BoW) empirical comparisons [50, 51].”
Backgroundvan Gemert, J. C., Veenman, C. J., Smeulders, A. W. M., & Geusebroek, J.-M. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.132 · Cited by 737
“Typically, a vocabulary is constructed by applying k-means clustering on image features [4], [14]– [16], [20], [23]–[26], [30], [31].”
BackgroundMethodGoing deeper into action recognition: A survey
Herath, S., Harandi, M., & Porikli, F. (2017) · Image and Vision Computing · doi:10.1016/j.imavis.2017.01.010 · Cited by 634
Towards optimal bag-of-features for object categorization and semantic video retrieval
Jiang, Y.-G., Ngo, C.-W., & Yang, J. (2007) · Proceedings of the 6th ACM international conference on Image and video retrieval · doi:10.1145/1282280.1282352 · Cited by 637
Rabinovich, A., Vedaldi, A., Galleguillos, C., Wiewiora, E., & Belongie, S. (2007) · 2007 IEEE 11th International Conference on Computer Vision · doi:10.1109/iccv.2007.4408986 · Cited by 594
Kernel Codebooks for Scene Categorization
van Gemert, J. C., Geusebroek, J.-M., Veenman, C. J., & Smeulders, A. W. M. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88690-7_52 · Cited by 585
“In contrast, a data-driven approach applies vector quantization on the features using k-means [6–11] or radius-based clustering [12].”
BackgroundMethodMultiple instance classification: Review, taxonomy and comparative study
Amores, J. (2013) · Artificial Intelligence · doi:10.1016/j.artint.2013.06.003 · Cited by 557
“In this work we use KM, as it is the most widely used [5, 30].”
MethodClass-Specific Hough Forests for Object Detection
Gall, J., & Lempitsky, V. (2013) · Advances in Computer Vision and Pattern Recognition · doi:10.1007/978-1-4471-4929-3_11 · Cited by 555
Saliency-Guided Unsupervised Feature Learning for Scene Classification
Zhang, F., Du, B., & Zhang, L. (2015) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2014.2357078 · Cited by 542
“The details of our experiments and the results are presented in Section V. Finally, Section VI concludes this paper with a discussion of the results and our ideas for future work.”
MethodContent-based image retrieval using color difference histogram
Liu, G.-H., & Yang, J.-Y. (2013) · Pattern Recognition · doi:10.1016/j.patcog.2012.06.001 · Cited by 507
Visualizing Deep Convolutional Neural Networks Using Natural Pre-images
Mahendran, A., & Vedaldi, A. (2016) · International Journal of Computer Vision · doi:10.1007/s11263-016-0911-8 · Cited by 496
“Here we consider two densely-sampled versions (Nowak et al. 2006), namely DSIFT (Dense SIFT) and HOG (Dalal and Triggs 2005).”
MethodShin, H.-C., Orton, M. R., Collins, D. J., Doran, S. J., & Leach, M. O. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.277 · Cited by 488
Fast Discriminative Visual Codebooks using Randomized Clustering Forests
Moosmann, F., Triggs, B., & Jurie, F. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0128 · Cited by 467
“Our method is also faster in use – a useful property given that reliable image classification requires large numbers of subwindows to be labelled [18, 24].”
BackgroundMethodSelf-citationObject categorization using co-occurrence, location and appearance
Galleguillos, C., Rabinovich, A., & Belongie, S. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587799 · Cited by 457
“BoF is a widely used discriminative model for recognition [7, 16].”
Fisher Vector Faces in the Wild
Simonyan, K., Parkhi, O., Vedaldi, A., & Zisserman, A. (2013) · Procedings of the British Machine Vision Conference 2013 · doi:10.5244/c.27.8 · Cited by 445
“Dense feature extraction is an essential component of many state-of-the-art image classification methods [18, 23, 27].”
BackgroundDescribable Visual Attributes for Face Verification and Image Search
Kumar, N., Berg, A., Belhumeur, P. N., & Nayar, S. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.48 · Cited by 434
Robotic tactile perception of object properties: A review
Luo, S., Bimbo, J., Dahiya, R., & Liu, H. (2017) · Mechatronics · doi:10.1016/j.mechatronics.2017.11.002 · Cited by 425
Sketch-Based Image Retrieval: Benchmark and Bag-of-Features Descriptors
Eitz, M., Hildebrand, K., Boubekeur, T., & Alexa, M. (2011) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2010.266 · Cited by 413
“Instead, we perform random sampling in image space which has been shown to work well in a bag-of-features setup for image classification [17].”
MethodA Bag-of-Features Framework to Classify Time Series
Baydogan, M. G., Runger, G., & Tuv, E. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.72 · Cited by 361
Transfer Learning for Image Classification
Shaha, M., & Pawar, M. (2018) · 2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA) · doi:10.1109/iceca.2018.8474802 · Cited by 334
Learning to Localize Objects with Structured Output Regression
Blaschko, M. B., & Lampert, C. H. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88682-2_2 · Cited by 324
“This includes for example, bag of visual words methods [22], groups of contours [4], spatial pyramids [1,21], and histograms of oriented gradients [3].”
MethodTop-down visual saliency via joint CRF and dictionary learning
Yang, J., & Yang, M.-H. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247940 · Cited by 320
“The performance of BoW models highly depends on the dictionary [20] and sampling strategy [21].”
BackgroundA Linear Time Histogram Metric for Improved SIFT Matching
Pele, O., & Werman, M. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88690-7_37 · Cited by 305
“The SIFT descriptor has proven to be successful in applications such as object recognition [3, 7–9], object class detection [10–12], image retrieval [13–16], robot localization [17], building panoramas [18] and image classification [19].”
MethodMulti-Region Probabilistic Histograms for Robust and Scalable Identity Inference
Sanderson, C., & Lovell, B. C. (2009) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-01793-3_21 · Cited by 301
“The use of probabilistic histograms in MRH differs to the histograms used in [4] (for image retrieval/categorisation purposes), where a Vector Quantiser (VQ) based strategy is typically used.”
MethodComparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors
Li, F., Shirahama, K., Nisar, M., Köping, L., & Grzegorzek, M. (2018) · Sensors · doi:10.3390/s18020679 · Cited by 302
“First, it is widely accepted that denser sampling of subsequences yields a better performance [24,39], so l is set to 1.”
BackgroundGao, D., Han, S., & Vasconcelos, N. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.27 · Cited by 294
Randomized Clustering Forests for Image Classification
Moosmann, F., Nowak, E., & Jurie, F. (2008) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.70822 · Cited by 287
“This means that any “weak” information also improves the performance, which confirms the conclusion in [42] about sampling.”
BackgroundInfluentialSelf-citationA comprehensive review of current local features for computer vision
Li, J., & Allinson, N. M. (2008) · Neurocomputing · doi:10.1016/j.neucom.2007.11.032 · Cited by 280
Real-Time Visual SLAM for Autonomous Underwater Hull Inspection Using Visual Saliency
Kim, A., & Eustice, R. M. (2013) · IEEE Transactions on Robotics · doi:10.1109/tro.2012.2235699 · Cited by 263
“Alternatively to the above channel-based methods, several BoW saliency representations have recently been explored [45]–[48].”
MethodRepresentations of Keypoint-Based Semantic Concept Detection: A Comprehensive Study
Jiang, Y.-G., Yang, J., Ngo, C.-W., & Hauptmann, A. G. (2010) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2009.2036235 · Cited by 260
“In [4], binary weighting, which indicates the presence and absence of a visual word”
BackgroundInfluentialContent-based image retrieval using computational visual attention model
Liu, G.-H., Yang, J.-Y., & Li, Z. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.02.005 · Cited by 257
Action Recognition in Realistic Sports Videos
Soomro, K., & Zamir, A. R. (2014) · Advances in Computer Vision and Pattern Recognition · doi:10.1007/978-3-319-09396-3_9 · Cited by 235
“However, the more recent dense sampling [18, 51] and trajectory based [75, 76] techniques have been able to outperform them and significantly improve the overall accuracy.”
BackgroundDiscriminative spatial saliency for image classification
Sharma, G., Jurie, F., & Schmid, C. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248093 · Cited by 230
“Such regions were also used to sample small sets of salient patches from images for classification with bag-of-features representations [3], but dense (regular or random) sampling has been shown to perform better [22] and is currently the state-of-the-art [6].”
BackgroundSelf-citationA Food Recognition System for Diabetic Patients Based on an Optimized Bag-of-Features Model
Anthimopoulos, M. M., Gianola, L., Scarnato, L., Diem, P., & Mougiakakou, S. G. (2014) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2014.2308928 · Cited by 222
“2(b) and (c)] have been widely used in image classification with great success since they are able to provide a BoF-based system with the required number of image patches [19].”
BackgroundAesthetic quality classification of photographs based on color harmony
Nishiyama, M., Okabe, T., Sato, I., & Sato, Y. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995539 · Cited by 208
Pyramid of Spatial Relatons for Scene-Level Land Use Classification
Chen, S., & Tian, Y. (2015) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2014.2351395 · Cited by 211
“In this paper, we apply SIFT feature on gray images with densely sampled interest points, which is the most popular approach in both computer vision and remote sensing communities [28], [30], [42]–[44].”
MethodX-ray Categorization and Retrieval on the Organ and Pathology Level, Using Patch-Based Visual Words
Avni, U., Greenspan, H., Konen, E., Sharon, M., & Goldberger, J. (2011) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2010.2095026 · Cited by 195
Enhanced Patterns of Oriented Edge Magnitudes for Face Recognition and Image Matching
Vu, N.-S., & Caplier, A. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2166974 · Cited by 194
Histopathology Image Classification Using Bag of Features and Kernel Functions
Caicedo, J. C., Cruz, A., & Gonzalez, F. A. (2009) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-02976-9_17 · Cited by 192
“In addition, a large number of blocks may be extracted from different image scales, and that sample is a good approximation of the probability distribution of visual patterns in the image [16].”
BackgroundGeorgiou, T., Liu, Y., Chen, W., & Lew, M. (2020) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-019-00183-w · Cited by 187
“Wang et al. [298,299], inspired by the success of the aforementioned methods as well as the dense sampling of features in images [196], proposed a combination, the dense trajectories.”
BackgroundStratified sampling for feature subspace selection in random forests for high dimensional data
Ye, Y., Wu, Q., Zhexue Huang, J., Ng, M. K., & Li, X. (2013) · Pattern Recognition · doi:10.1016/j.patcog.2012.09.005 · Cited by 186
“, SIFT [38]) is used to extract local features by sampling subwindows at random from the training images, either at sparse points of interest or within dense regions [39].”
MethodUniversal and Adapted Vocabularies for Generic Visual Categorization
Perronnin, F. (2008) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.70755 · Cited by 185
“Many approaches have been suggested: The segmentation of the image [3] and the extraction of patches at keypoints [7], [11], [25], [31], [37] (cf. [24] for an in-depth comparison of keypoints detectors), on regular grids [6], [13], [34], or at random [17], [22], [27].”
MethodAlzheimer's Disease Diagnosis Using Landmark-Based Features From Longitudinal Structural MR Images
Zhang, J., Liu, M., An, L., Gao, Y., & Shen, D. (2017) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2017.2704614 · Cited by 179
Gaussian Processes for Object Categorization
Kapoor, A., Grauman, K., Urtasun, R., & Darrell, T. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0268-3 · Cited by 179
“The cubic cost of the optimal matching makes it prohibitive for recognition with a large number of local image features, yet rich image descriptions comprised of densely sampled local features are known to often yield better recognition accuracy (Nowak et al. 2006).”
BackgroundLearning semantic visual vocabularies using diffusion distance
Liu, J., Yang, Y., & Shah, M. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206845 · Cited by 169
“SIFT features for scene classification: It has been shown that the dense features can achieve a better classification rate than sparse interest point features for the scene classification [31,8] problem.”
BackgroundLearning Visual Similarity Measures for Comparing Never Seen Objects
Nowak, E., & Jurie, F. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.382969 · Cited by 173
“This means that any “weak” information also improves the performance, which confirms our previous works [18] about sampling strategies.”
ResultSelf-citationWang, Z., Zhang, L., Fang, T., Mathiopoulos, P. T., Tong, X., Qu, H., Xiao, Z., Li, F., & Chen, D. (2015) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2014.2359951 · Cited by 172
“In [19], the EGIs [5] and spin image databases are used to implement the recognition.”
MethodHigh-level event recognition in unconstrained videos
Jiang, Y.-G., Bhattacharya, S., Chang, S.-F., & Shah, M. (2013) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-012-0024-2 · Cited by 172
“, DoG [88]) with a competitive recognition performance [101].”
BackgroundMethodModeling spatial layout with fisher vectors for image categorization
Krapac, J., Verbeek, J., & Jurie, F. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126406 · Cited by 163
“Performance of the BOW model is often reported to increase with the size of the dictionary [6, 25, 26] and the number of regions sampled from images [16].”
BackgroundSelf-citationMulti-class image segmentation using conditional random fields and global classification
Plath, N., Toussaint, M., & Nakajima, S. (2009) · International Conference on Machine Learning · doi:10.1145/1553374.1553479 · Cited by 157
“Current state-of-the-art methods for image classi.cation (Zhang et al., 2007; Nowak et al., 2006) put much emphasis on de.ning good global image features which can then be mapped, using large-scale statistical Machine Learning methods such as SVMs, to the desired classi.cation.”
MethodInfluentialTurcsány, D., Mouton, A., & Breckon, T. P. (2013) · IEEE International Conference on Industrial Technology (ICIT) · doi:10.1109/icit.2013.6505833 · Cited by 163
“Traditionally, image classification using the BoW representation of an image is composed of the following steps [8]: 1) feature detection and description; 2) visual codebook generation; 3) BoW representation and 4) classification.”
BackgroundMethodRoa, Á. A. C., Gilmore, H. L., Basavanhally, A. N., Feldman, M. D., Ganesan, S., Shih, N. N. C., Tomaszewski, J., Madabhushi, A., & Gonzalez, F. A. (2018) · PLoS ONE · doi:10.1371/journal.pone.0196828 · Cited by 162
Contextual Bag-of-Words for Visual Categorization
Li, T., Mei, T., Kweon, I.-S., & Hua, X. (2010) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2010.2041828 · Cited by 148
“Recent research shows that extracting local patches densely can yield better performance [27].”
BackgroundLemaître, G., Rastgoo, M., Massich, J., Cheung, C. Y.-L., Wong, T. Y., Lamoureux, E. L., Miléa, D., Mériaudeau, F., & Sidibé, D. (2016) · Journal of Ophthalmology · doi:10.1155/2016/3298606 · Cited by 158
“[25] pointed out that randomly generated codebooks can be used at the expense of accuracy.”
BackgroundTactile-Object Recognition From Appearance Information
Pezzementi, Z. A., Plaku, E., Reyda, C., & Hager, G. D. (2011) · IEEE Transactions on Robotics · doi:10.1109/tro.2011.2125350 · Cited by 165
Material-specific adaptation of color invariant features
Burghouts, G. J., & Geusebroek, J. (2008) · Pattern Recognition Letters · doi:10.1016/j.patrec.2008.10.005 · Cited by 153
“ping of image features onto a codebook of feature representatives (Jurie and Triggs, 2005; Nowak et al., 2006) has received extensive treatment.”
BackgroundIntegrated feature selection and higher-order spatial feature extraction for object categorization
Liu, D., Hua, G., Viola, P. A., & Chen, T. (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.2008.4587403 · Cited by 150
“Another scheme is to abandon the use of interest point detectors [13] and sample image patches uniformly from the image.”
BackgroundEvent detection and recognition for semantic annotation of video
Ballan, L., Bertini, M., Bimbo, A. D., Seidenari, L., & Serra, G. (2010) · Multimedia Tools and Applications · doi:10.1007/s11042-010-0643-7 · Cited by 159
Computer-aided colorectal tumor classification in NBI endoscopy using local features
Tamaki, T., Yoshimuta, J., Kawakami, M., Raytchev, B., Kaneda, K., Yoshida, S., Takemura, Y., Onji, K., Miyaki, R., & Tanaka, S. (2012) · Medical Image Analysis · doi:10.1016/j.media.2012.08.003 · Cited by 158
“The use of bag–of–visual–words for generic visual categorization (Csurka et al., 2004, Lazebnik et al., 2006, Nowak et al., 2006) and instance recognition (Chum et al., 2007, Sivic and Zisserman, 2003) has been motivated by the success of the bag–of–words method for text classification (Cristianini…”
BackgroundMethodInfluentialEvent Retrieval in Large Video Collections with Circulant Temporal Encoding
Revaud, J., Douze, M., Schmid, C., & Jegou, H. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.318 · Cited by 133
Visual pattern mining in histology image collections using bag of features
Cruz-Roa, A., Caicedo, J. C., & González, F. A. (2011) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2011.04.010 · Cited by 133
Real-Time Visual Concept Classification
Uijlings, J., Smeulders, A. W. M., & Scha, R. J. H. (2010) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2010.2052027 · Cited by 146
“[26] showed that using more descriptors is better.”
MethodIntroduction to the Bag of Features Paradigm for Image Classification and RetrievalPreprint
O′Hara, S., & Draper, B. A. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1101.3354 · Cited by 228
“Continuing along the same lines as their earlier work, Nowak, Jurie, and Triggs further explore sampling strategies and other factors impacting BoF-based image classification (Nowak et al, 2006).”
BackgroundInfluentialDeep learning for video classification and captioning
Wu, Z., Yao, T., Fu, Y., & Jiang, Y.-G. (2017) · doi:10.1145/3122865.3122867 · Cited by 174
Foreground Focus: Unsupervised Learning from Partially Matching Images
Lee, Y. J., & Grauman, K. L. (2009) · International Journal of Computer Vision · doi:10.1007/s11263-009-0252-y · Cited by 131
“Recent work on sampling strategies shows that the single most important criterion for recognition performance tends to be the number of patches detected in each image (Nowak et al. 2006).”
BackgroundVisual Words on Baggage X-Ray Images
Baştan, M., Yousefi, M. R., & Breuel, T. M. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23672-3_44 · Cited by 127
“Several techniques have been suggested for the detection of local image patches [ 12 ]:”
MethodGrauman, K., & Leibe, B. (2011) · Synthesis Lectures on Artificial Intelligence and Machine Learning · doi:10.2200/s00332ed1v01y201103aim011 · Cited by 126
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 136
“The importance of interest point detectors versus dense sampling is much researched (Mikolajczyk et al. 2005; Marszalek et al. 2007; Nowak et al. 2006) and is not further investigated in this pa- per.”
BackgroundPersistence diagrams with linear machine learning models
Obayashi, I., Hiraoka, Y., & Kimura, M. (2018) · Journal of Applied and Computational Topology · doi:10.1007/s41468-018-0013-5 · Cited by 125
“In particular, we note that the performance of our method is better than the bag of keypoints approach with sift feature, which is one of the standard techniques for image classifications (Lowe 1999; Sivic and Zisserman 2003; Csurka et al. 2004; Nowak et al. 2006).”
MethodA Novel Image Retrieval Based on Visual Words Integration of SIFT and SURF
Ali, N., Bajwa, K. B., Sablatnig, R., Chatzichristofis, S. A., Iqbal, Z., Rashid, M., & Habib, H. A. (2016) · PLoS ONE · doi:10.1371/journal.pone.0157428 · Cited by 122
“The features percentage to construct the visual vocabulary from the training dataset is a major parameter that affects the performance [51].”
BackgroundAutomated characterization of flowering dynamics in rice using field-acquired time-series RGB images
Guo, W., Fukatsu, T., & Ninomiya, S. (2015) · Plant Methods · doi:10.1186/s13007-015-0047-9 · Cited by 117
Ensemble of convolutional neural networks for bioimage classification
Nanni, L., Ghidoni, S., & Brahnam, S. (2018) · Applied Computing and Informatics · doi:10.1016/j.aci.2018.06.002 · Cited by 132
“The main difference between CLM and the other widely used dense sampling method, such as the BoF approach [52], is the absence of a codebook.”
MethodEfficient segmentation-free keyword spotting in historical document collections
Rusiñol, M., Aldavert, D., Toledo, R., & Lladós, J. (2014) · Pattern Recognition · doi:10.1016/j.patcog.2014.08.021 · Cited by 117
“In the related literature it has been noted that the larger is the amount of descriptors extracted from an image, the better the performance is [23].”
BackgroundSliding-Windows for Rapid Object Class Localization: A Parallel Technique
Wojek, C., Dorkó, G., Schulz, A., & Schiele, B. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-69321-5_8 · Cited by 131
“While interest point detectors o er a smart way for pre-sampling possible locations and therefore provide a sparser set for learning and recognition, the advantage of dense random sampling, or sampling on a regular lattice has been shown [1, 2] to outperform sparse representations.”
BackgroundA Discriminative Representation of Convolutional Features for Indoor Scene Recognition
Khan, S. H., Hayat, M., Bennamoun, M., Togneri, R., & Sohel, F. A. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2567076 · Cited by 132
“Note that the idea of dense patch extraction is analogous to dense key-point extraction [28], which has shown very promising performance over well-designed key-point extraction methods in a number of tasks (e.g., action recognition [47]).”
BackgroundTuytelaars, 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.2010.5539911 · Cited by 122
“[13, 4 ]), but this does not seem to have any advantage over regular grids, and equally ignores the actual image content during the feature”
BackgroundAudio-based human activity recognition using Non-Markovian Ensemble Voting
Stork, J. A., Spinello, L., Silva, J., & Arras, K. O. (2012) · IEEE RO-MAN · doi:10.1109/roman.2012.6343802 · Cited by 127
“The approach recognizes audio snippets in a large database of songs that makes use of a hash-based voting.”
BackgroundMethodInfluentialKernel Methods in Computer Vision
Lampert, C. H. (2009) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000027 · Cited by 133
Scene Modeling Using Co-Clustering
Liu, J., & Shah, M. A. (2007) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2007.4408866 · Cited by 111
“The performance of BOV can vary with the patch sampling [13], and the number of visterms [22].”
BackgroundGoldfeder, C., & Allen, P. K. (2011) · Autonomous Robots · doi:10.1007/s10514-011-9228-1 · Cited by 120
“Instead, for the SIFT-based CapSets we use binary histograms, using the simple absence/presence rule that was shown to perform well in Nowak et al. (2006).”
MethodInfluentialSampling Strategies for Real-Time Action Recognition
Shi, F., Petriu, E. M., & Laganière, R. (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.2013.335 · Cited by 116
“Nowak et al. [21] have shown that the most important factor governing performance is the number of patches sampled.”
InfluentialRetrieval and classification of food images
Farinella, G. M., Allegra, D., Moltisanti, M., Stanco, F., & Battiato, S. (2016) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2016.07.006 · Cited by 122
Object class detection: A survey
Zhang, X., Yang, Y., Han, Z., Wang, H., & Gao, C. (2013) · ACM Computing Surveys · doi:10.1145/2522968.2522978 · Cited by 131
Fast nearest neighbor retrieval for bregman divergences
Cayton, L. (2008) · International Conference on Machine Learning · doi:10.1145/1390156.1390171 · Cited by 133
“Each point is a histogram of quantized SIFT features as suggested in (Nowak et al., 2006).”
BackgroundNovel Tactile-SIFT Descriptor for Object Shape Recognition
Luo, S., Mou, W., Althoefer, K. A., & Liu, H. (2015) · IEEE Sensors Journal · doi:10.1109/jsen.2015.2432127 · Cited by 104
Tracking people in 3D using a bottom-up top-down detector
Spinello, L., Luber, M., & Arras, K. O. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980085 · Cited by 117
“Similar e ects have been noticed in the field of computer vision [ 24 ].”
BackgroundShape Vocabulary: A Robust and Efficient Shape Representation for Shape Matching
Bai, X., Rao, C., & Wang, X. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2336542 · Cited by 102
“The BoW paradigm have demonstrated its power in many image related applications, such as image retrieval [14]–[16] and classification [46]–[48].”
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.