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 401–500 of 925
Jeǵou, H. (2017) · doi:10.1145/3122865.3122871 · Cited by 14
Digital fingerprinting of microstructures
White, M., Tarakanov, A., Withers, P. J., Race, C. P., & Law, K. J. H. (2022) · Computational Materials Science · doi:10.1016/j.commatsci.2022.111985 · Cited by 13
“…for fingerprinting, which includes classical feature extraction methods from computer vision known as visual bag of words (VBOW) [23, 24, 25, 26, 13] and vector of locally aggregated descriptors (VLAD) [27, 28, 14], and more recent transfer learning with pretrained convolutional neural…”
MethodContent-based Image Retrieval by Indexing Random Subwindows with Randomized Trees
Marée, R., Geurts, P., & Wehenkel, L. A. (2009) · IPSJ Transactions on Computer Vision and Applications · doi:10.2197/ipsjtcva.1.46 · Cited by 12
“on a uniform grid [4] or even randomly [8, 11].”
BackgroundHu, R., Queen, C. M., & Zouridakis, G. (2013) · doi:10.1109/pht.2013.6461311 · Cited by 12
“Nowak [13] has demonstrated that random sampling achieves comparable or even better performance than key-point based sampling and costs less than dense sampling.”
BackgroundCombination of projectors, standard texture descriptors and bag of features for classifying images
Nanni, L., & Melucci, M. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.09.032 · Cited by 13
“We are aware that several complex and high performing bag-of-features approaches are proposed [12][33], anyway in this work we implement a quite simple approach similar to the one reported in [27].”
ResultInformative visual words construction to improve bag of words image representation
Farhangi, M. M., Soryani, M., & Fathy, M. (2014) · IET Image Processing · doi:10.1049/iet-ipr.2013.0449 · Cited by 12
“[19], is one of these methods, in which some of the feature vectors are randomly selected as visual words.”
MethodA Unifying Framework for LBP and Related Methods
Bianconi, F., & Fernández, A. (2013) · Studies in computational intelligence · doi:10.1007/978-3-642-39289-4_2 · Cited by 12
“In the first case one may either subsample the image to a grid of equally-spaced pixels [14] or even perform completely random sampling [57].”
BackgroundAnticipating movie success through crowdsourced social media videos
Singh, J., & Goyal, G. (2018) · Computers in Human Behavior · doi:10.1016/j.chb.2018.08.050 · Cited by 14
Bag of words KAZE (BoWK) with two‐step classification for high‐resolution remote sensing images
Muhammad, U., Wang, W., Hadid, A., & Pervez, S. (2019) · IET Computer Vision · doi:10.1049/iet-cvi.2018.5069 · Cited by 12
“Researchers are using multiscale key points detectors (Laplacian of Gaussian, SIFT, Harris-affine etc.) as samplers to select regions of interest within the image but surprisingly the randomly sampled or dense patches are often more discriminant than key point-based sampling methods [14].”
BackgroundA semantic region descriptor for local feature based image categorization
Li, T., & Kweon, I.-S. (2008) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2008.4517864 · Cited by 12
“Index Terms—Image classification, Image region analysis, Image texture analysis”
BackgroundMeta-tag propagation by co-training an ensemble classifier for improving image search relevance
Sharma, A., Hua, G., Liu, Z., & Zhang, Z. (2008) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2008.4562952 · Cited by 12
“For example, different sampling strategies [12] can be employed in the first step, such as using random sampled patches, or using patches generated from any interest point detectors such as Harris, DOG [7] or Harris-Laplace [9].”
MethodA Novel Language-Model-Based Approach for Image Object Mining and Re-ranking
Hsiao, J.-H., Chen, C., & Chen⋆, M.-S. (2008) · Proceedings · doi:10.1109/icdm.2008.83 · Cited by 12
“To improve the retrieval performance of visual BOW mining, several works have been proposed, ranging from higher semantic representations [31][10], patches sampling strategies [15], to scalable visual vocabularies [14][17].”
Kernel Sharing With Joint Boosting For Multi-Class Concept Detection
Jiang, W., Chang, S., & Loui, A. C. P. (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.2007.383483 · Cited by 12
“A kernel computes the similarity between images and can be used to find the optimal decision boundary for classification.”
MethodAEFNet: a real-time network for detecting prohibited items in x-ray images across complex scenarios
Zhu, K., Chang, X., & Zhang, Q. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adb05d · Cited by 11
“Turcsany et al [5] construct Bag-of-Visual-Words (BoVW) [6] model for firearms detection in x-ray security images by applying a speeded-up robust features [7] detector within the support vector machine [8] classifier.”
Avni, U., Goldberger, J., Sharon, M., Konen, E., & Greenspan, H. K. (2010) · Multimedia Information Retrieval · doi:10.1145/1743384.1743414 · Cited by 11
“This simple feature detection approach has been shown to be effective [12].”
MethodExploration of complex visual feature spaces for object perception
Leeds, D., Pyles, J. A., & Tarr, M. J. (2014) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2014.00106 · Cited by 11
MILDE: multiple instance learning by discriminative embedding
Amores, J. (2013) · Knowledge and Information Systems · doi:10.1007/s10115-013-0711-1 · Cited by 11
“The number of regions considered depends on the specific algorithm used for detecting regions of interest [15,16], and this number might vary across images.”
Dense interest features for video processing
Geest, R. D., & Tuytelaars, T. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7026167 · Cited by 11
“Later, it was shown that better image classification could be obtained by sampling regularly on a dense grid in the image [3].”
BackgroundMargin-based discriminant dimensionality reduction for visual recognition
Çevıkalp, H., Triggs, B., Jurie, F., & Robi Polikar, A. (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.2008.4587591 · Cited by 12
“Experience shows that the most critical factor is the number of patches sampled not the sample selection method [19], so for simplicity we randomly sampled thousands of patches per image.”
BackgroundSelf-citationBag‐of‐features for image memorability evaluation
Lahrache, S., Ouazzani, R. E., & Qadi, A. E. (2016) · IET Computer Vision · doi:10.1049/iet-cvi.2015.0383 · Cited by 11
“BoVW technique has many advantages such as: robustness to features spatial translations, efficiency in computations and its performance in different image processing tasks such as: image classification and scene categorisation [5, 6], image retrieval [7], and so on.”
Image Classification Based on Convolutional Denoising Sparse Autoencoder
Chen, S., Liu, H., Zeng, X., Qian, S., Yu, J., & Guo, W. (2017) · Mathematical Problems in Engineering · doi:10.1155/2017/5218247 · Cited by 12
“Ideally, it should focus attention on the image regions that are the most informative for classification [22].”
BackgroundTactile Sensing and Machine Learning for Human and Object Recognition in Disaster Scenarios
Gandarías, J. M., Gómez-de-Gabriel, J. M., & Garcia-Cerezo, A. J. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-70836-2_14 · Cited by 11
DeepCarotene -Job Title Classification with Multi-stream Convolutional Neural Network
Wang, J., Abdelfatah, K. E., Korayem, M., & Balaji, J. (2019) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata47090.2019.9005673 · Cited by 14
Region Contextual Visual Words for scene categorization
Liu, C., Xu, D., & Feng, S. (2011) · Expert Systems with Applications · doi:10.1016/j.eswa.2011.03.037 · Cited by 11
Linear Discriminant Analysis for Signatures
Huh, S., & Lee, D. (2010) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2010.2090047 · Cited by 11
Addressing the ImageClef 2009 Challenge Using a Patch-based Visual Words Representation
Avni, U., Goldberger, J., & Greenspan, H. K. (2009) · Cited by 11
Montagner, C., Jesus, R. M., Correia, N. M. R., Vilarigues, M. G., Macedo, R., & Melo, M. J. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-015-3197-x · Cited by 11
“,wm}, the Bag-of-Features for the image Ik is represented by a histogram that counts the occurrences Wl,k of each word wl in the Ik picture [45]:”
BackgroundMethodContent-Based Image Retrieval Based on Late Fusion of Binary and Local DescriptorsPreprint
Ali, N., Mazhar, D. A., Iqbal, Z., Ashraf, R., Ahmed, J., & Khan, F. Z. (2017) · Preprints.org · doi:10.20944/preprints201703.0156.v1 · Cited by 11
Paschali, M., Naeem, M. F., Simson, W. A., Steiger, K., Mollenhauer, M., & Navab, N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.03127 · Cited by 11
“Decisions based on local features Our main goal, learning to classify a WSI based on local information while leveraging weak labels, can be achieved by expressing the local features within an image as a Bag-of-Features (BoF) [12].”
BackgroundEffective image database search via dimensionality reduction
Dahl, A. B., & Aanæs, H. (2008) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2008.4562957 · Cited by 10
“The bagof-words approach have shown promising results for large scale image search [8, 16, 17, 18, 20] and for image categorization [6, 22, 23].”
BackgroundShah, M., Shah, A., Patel, K., Kshirsagar, A., Sanghvi, S., & Sojitra, V. (2025) · Machine learning for computational science and engineering · doi:10.1007/s44379-025-00017-z · Cited by 17
“Hence, they implemented Bag-of-fea-tures [127] methodology for image classification.”
Stanciu, S. G., Tranca, D. E., & Coltuc, D. (2015) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2015.08.008 · Cited by 10
SmartVisionApp: A framework for computer vision applications on mobile devices
Casanova, C., Franco, A., Lumini, A., & Maio, D. (2013) · Expert Systems with Applications · doi:10.1016/j.eswa.2013.04.037 · Cited by 14
Mixture Distributions for Weakly Supervised Classification in Remote Sensing Images
Bordes, J.-B., & Véronique Prinet, A. (2008) · British Machine Vision Conference (BMVC) · doi:10.5244/c.22.77 · Cited by 10
“A large literature in recent years has been dedicated to modeling the image via a bag of words/features/textons representation [19, 24, 18, 23].”
BackgroundLearning reconfigurable hashing for diverse semantics
Mu, Y., Chen, X., Chua, T., & Yan, S. (2011) · International Conference on Multimedia Retrieval · doi:10.1145/1991996.1992003 · Cited by 12
“We extract 5000 SIFT descriptors from each image whose locations and scales are determined in a random manner (see [13] for more details).”
MethodImage retrieval and classification on deep convolutional SparkNet
Li, H., Su, P., Chi, Z., & Wang, J. (2016) · IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) · doi:10.1109/icspcc.2016.7753615 · Cited by 10
Multiple object cues for high performance vector quantization
Ramesh, B., Xiang, C., & Lee, T. H. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.02.024 · Cited by 11
Griffin, L. D. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2777856 · Cited by 10
“whose bins are driven by their utility at inferring semantic labels when part of a larger recognition system [45].”
BackgroundTexture Feature Extraction for Batik Images Using GLCM and GLRLM with Neural Network Classification
Chandraprabha, K. S., & Akila, S. (2019) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit195322 · Cited by 10
Bag-of-Features Codebook Generation by Self-Organisation
Kinnunen, T., Kämäräinen, J., Lensu, L. T., & Kalviainen, H. A. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-02397-2_15 · Cited by 10
“Many other successful methods, however, use directly the c-means [ 8 ,9].”
MethodA hierarchical statistical model for object classification
Bakhtiari, A., & Bouguila, N. (2010) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2010.5662071 · Cited by 10
“Following the introduction of the bag of visual words model several authors have proposed their improvements to the original model e.g. [9] [10] [11].”
MethodInfluentialEberle, O., Büttner, J., El-Hajj, H., Montavon, G., Müller, K., & Valleriani, M. (2024) · Science Advances · doi:10.1126/sciadv.adj1719 · Cited by 23
Does one size really fit all? Evaluating classifiers in bag-of-visual-words classification
Hentschel, C., & Sack, H. (2014) · International Conference on Knowledge Management and Knowledge Technologies · doi:10.1145/2637748.2638424 · Cited by 10
“A comparison of feature sampling strategies for BoVW vectors has shown that when using enough samples, dense random sampling exceeds the performance of interest point operators [17].”
BackgroundFast genre classification of web images using global and local features
Liu, G., Wang, R. L., Yin, F., Ogier, J.-M., & Liu, C. (2018) · CAAI Transactions on Intelligence Technology · doi:10.1049/trit.2018.1018 · Cited by 9
Unsupervised object category discovery via information bottleneck method
Lou, Z., Ye, Y., & Liu, D. (2010) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/1873951.1874098 · Cited by 9
“In the experiments, 1000 local features are randomly extracted from each image [2], and the visual vocabulary is constructed by K-means algorithm with 1000 visual words.”
BackgroundMethodLi, R., Zhang, W., & Ji, S. (2014) · BMC Bioinformatics · doi:10.1186/1471-2105-15-209 · Cited by 9
“In many of the current image classification systems, key-point extractors are typically not used [24,25].”
BackgroundActivities of daily living recognition using optimal trajectories from motion boundaries
Avgerinakis, K., Briassouli, A., & Kompatsiaris, I. Y. (2015) · Journal of Ambient Intelligence and Smart Environments · doi:10.3233/ais-150347 · Cited by 12
Kobe University and Muroran Institute of Technology at TRECVID 20112 Semantic Indexing Task.
Shirahama, K., & Uehara, K. (2012) · TRECVID · Cited by 9
Physics-Inspired Models for Detecting Abnormal Behaviors in Crowded Scenes
Mohammadi, S., Galoogahi, H. K., Perina, A., & Murino, V. (2017) · Elsevier eBooks · doi:10.1016/b978-0-12-809276-7.00013-8 · Cited by 9
Part-Level Sketch Segmentation and Labeling Using Dual-CNN
Zhu, X., Xiao, Y., & Zheng, Y. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-04167-0_34 · Cited by 9
Aerial image classification by learning quality-aware spatial pyramid model
Huang, F., Qi, X., Li, C., & Hu, W. (2020) · Future Generation Computer Systems · doi:10.1016/j.future.2020.04.047 · Cited by 11
Image Retrieval using Bag-of-Features for Lung Cancer Classification
Bhatt, S. D., & Soni, H. B. (2021) · International Conference on Inventive Computation Technologies (ICICT) · doi:10.1109/icict50816.2021.9358499 · Cited by 11
Markov random field based fusion for supervised and semi-supervised multi-modal image classification
Xie, L., Pan, P., & Lu, Y. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-014-2018-y · Cited by 9
Computing Invariants for Structural Change Detection in Urban Areas
Tang, F., & Véronique Prinet, A. (2007) · Joint Urban Remote Sensing Event (JURSE) · doi:10.1109/urs.2007.371772 · Cited by 9
“Harris detector), or randomly distributed over the image [8], [9].”
BackgroundTowards optimal VLAD for human action recognition from still images
Zhang, L., Li, C., Peng, P., Xiang, X., & Song, J. (2016) · Image and Vision Computing · doi:10.1016/j.imavis.2016.03.002 · Cited by 11
“For local descriptors, we extract dense SIFT descriptors with 3 × 3 grids for the better performance of dense sampling on image classification than sparse interest points [15].”
MethodStudy of Image Analysis Algorithms for Segmentation, Feature Extraction and Classification of Cells
Gamarra, M., Zurek, E. E., & San-Juan-Vergara, H. G. (2017) · Journal of Information Systems Engineering & Management · doi:10.20897/jisem.201720 · Cited by 9
Content-Based Image Retrieval Based on Late Fusion of Binary and Local DescriptorsPreprint
Ali, N., Mazhar, D. A., Iqbal, Z., Ashraf, R., Ahmed, J., & Khan, F. Z. (2017) · Preprints.org · doi:10.20944/preprints201703.0156.v2 · Cited by 9
Learning Motion Primitives for the Quantification and Diagnosis of Mobility Deficits
Yan, F., Gong, J., Zhang, Q., & He, H. (2024) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2024.3404357 · Cited by 10
Object-level saliency detection based on spatial compactness assumption
Zhang, C., & Wang, W. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738510 · Cited by 8
“image cropping [17], image classification [18] and contentaware image resizing [19], etc.”
BackgroundA Spatio-temporal Feature Based on Triangulation of Dense SURF
Nga, D. H., & Yanai, . (2013) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2013.62 · Cited by 8
“Empirical results have shown that dense features perform better for complex videos [2, 11, 12, 13].”
BackgroundOptimizing visual dictionaries for effective image retrieval
Arun, K. S., & Govindan, V. K. (2015) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-015-0076-1 · Cited by 8
Learning Tree-structured Quantizers for Image Categorization
Krapac, J., Verbeek, J. J., & Jurie, F. (2011) · British Machine Vision Conference (BMVC) · doi:10.5244/c.25.47 · Cited by 12
“For the stages (i), (ii), and (v), a consensus seems to be reached, i.e . the use of dense sampling [20], the representation of local features by SIFT like descriptors [32], and the combination of different non-linear kernels [28], possibly using explicit embeddings [17].”
Self-citationObject classification using a local texture descriptor and a support vector machine
Ferraz, C. T., & Gonzaga, A. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-4003-0 · Cited by 8
“a multiscale key point to detect RoIs [21], but dense or random sampling often outperforms the key point methods [12, 27].”
BackgroundDetecting Buildings in Historical Photographs Using Bag-of-Keypoints
Batista, N. C., Lopes, A. P. B., & Araújo, A. D. A. (2009) · Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI) · doi:10.1109/sibgrapi.2009.31 · Cited by 8
“Ideally, the representation must be flexible enough to cope with a large variety of visually different instances of the same class, yet keeping the discriminative power between classes [16].”
BackgroundMethodEngagement Prediction in the Adaptive Learning Model for Students with Dyslexia
Hamid, S. S. A., Admodisastro, N. I., Manshor, N. B., Ghani, A., & Kamaruddin, A. B. (2018) · International Conference on Human-Computer Interaction and User Experience in Indonesia (CHIuXiD) · doi:10.1145/3205946.3205956 · Cited by 13
“In this research, we compare the codebook with multiple size {500, 800 and 1000} to see the influence of the dictionary size of this model [27].”
MethodDrift-Aware Monocular Localization Based on a Pre-Constructed Dense 3D Map in Indoor Environments
Feng, G., Ma, L., Tan, X., & Qin, D. (2018) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi7080299 · Cited by 8
“The Bag‐Of‐Features (BOF) [29] approach is used in the visual map construction to determine a closed loop of the database camera trajectory [10].”
MethodInfluentialGround Texture Based Localization: Do We Need to Detect Keypoints?
Schmid, J. F., Simon, S. F., & Mester, R. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9340996 · Cited by 8
“Keypoints can be sampled uniformly [14] or randomly [15].”
BackgroundAttribute-Aware Feature Encoding for Object Recognition and Segmentation
Yang, S., Wang, Y., Chen, K., Zeng, W., & Fei, Z. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3103605 · Cited by 9
Suneetha, M., Prasad, M. V. D., & Kishore, P. V. V. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12646-0 · Cited by 9
“We found methods such as random forests [68], fuzzy distances [42], linear discriminant analysis [23], dictionary learning [63], K- SVD [63], extreme learning machine [26] and Hidden Markova Models (HMM) [12].”
MethodBiomedical Imaging Informatics
Rubin, D. L., Greenspan, H. K., & Hoogi, A. (2021) · Springer eBooks · doi:10.1007/978-3-030-58721-5_10 · Cited by 9
Action Recognition Using Canonical Correlation Kernels
Nagendar, G., Bandiatmakuri, S. G., Tandarpally, M. G., & Jawahar, C. V. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-37431-9_37 · Cited by 8
“Motivated by the success of dense features for object recognition [8, 9], we do a further dense feature extraction on a regular grid of pixels which helps us in obtaining a rich and robust set of descriptors.”
Sanderson, C., Bigdeli, A., Shan, T., Shaokang Chen, A., Berglund, E., & Lovell, B. C. (2007) · ELCVIA Electronic Letters on Computer Vision and Image Analysis · doi:10.5565/rev/elcvia.140 · Cited by 8
Partitioned K-Means Clustering for Fast Construction of Unbiased Visual Vocabulary
Wei, S., Wu, X., & Xu, D. (2012) · Springer eBooks · doi:10.1007/978-1-4614-3501-3_40 · Cited by 8
“Recently, Bag-of-Words model has become popular in multimedia search area due to its simplicity and effectiveness [10].”
Fuzzy indexing for Bag of Features scene categorization
Bouachir, W., Kardouchi, M., & Belacel, N. (2010) · International Symposium on I/V Communications and Mobile Network (ISIVC) · doi:10.1109/isvc.2010.5656164 · Cited by 8
“Since previous works relied on binary weights (bxx) [ 2 ] and term frequency (txx) [10] for image classification, we applied these two schemes and the Fuzzy method to index the image collection in three ways.”
MethodInfluentialRGB-D based place representation in topological maps
Karaoğuz, H., Erkent, Ö., & Bozma, H. I. (2014) · Machine Vision and Applications · doi:10.1007/s00138-014-0595-4 · Cited by 8
Nanni, L., Lumini, A., & Brahnam, S. (2013) · Journal of King Saud University - Science · doi:10.1016/j.jksus.2013.11.001 · Cited by 13
“Another interesting result in region description is reported in Nowak et al. (2006), where it is shown that random sampling, in the case where a large number of regions is available, gives equal or better classification rates than the other more complex operators that are in common use.”
BackgroundImplementing Word Retrieval in Handwritten Documents Using a Small Dataset
Liang, Y., Guest, R., & Fairhurst, M. C. (2012) · International Conference on Frontiers in Handwriting Recognition · doi:10.1109/icfhr.2012.220 · Cited by 10
“The grapheme spectrum approach to character modelling uses the same underlying principle in a technique known as bag-offeatures (BOF) [19] in that a word image is decomposed into a number of areas (i.”
MethodInfluentialFusion of tf.idf weighted bag of visual features for image classification
Moulin, C., Barat, C., & Ducottet, C. (2010) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2010.5529901 · Cited by 8
“idf and binary normalizations for the two sizes of vocabulary and several numbers of visual words per image, as the study conducted in [11].”
BackgroundMethodResultInfluentialEvent detection in consumer videos using GMM supervectors and SVMs
Kamishima, Y., Inoue, N., & Shinoda, K. (2013) · EURASIP Journal on Image and Video Processing · doi:10.1186/1687-5281-2013-51 · Cited by 8
“SIFT [19] has been effective in several image (e.g., [21]) and video application (e.g., [20]).”
Matsukawa, T., & Kurita, T. (2011) · Pattern Recognition · doi:10.1016/j.patcog.2011.07.018 · Cited by 8
“It is known that a large number of codebooks improves the classification performance [8], and a hundreds to thousands number of codebooks is generally used.”
Color constancy using stage classification
Lu, R., Gijsenij, A., Gevers, T., van de Sande, K. E. A., Geusebroek, J., & Xu, D. (2009) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2009.5414083 · Cited by 8
Expanded bag of words representation for object classification
Liu, T., Liu, J., Liu, Q., & Lu, H. (2009) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2009.5413588 · Cited by 8
Group sparse representation for image categorization and semantic video retrieval
Liu, Y., Wu, F. Q., & Zhuang, Y. (2011) · Science China Information Sciences · doi:10.1007/s11432-011-4344-2 · Cited by 8
“That is to say, image keypoints are the visual equivalents of independent “words” that comprise the image as an unordered “bag” [ 41 ].”
BackgroundLocal part model for action recognition
Shi, F., Laganière, R., & Petriu, E. M. (2016) · Image and Vision Computing · doi:10.1016/j.imavis.2015.11.010 · Cited by 8
Performance Assessment of Feature Detector-Descriptor Combination
Madbouly, A. M. M., & Mostafa, M.-S. M. (2015) · Cited by 8
Vaidyan, V. M., & Tyagi, A. K. (2022) · IEEE IAS Global Conference on Emerging Technologies (GlobConET) · doi:10.1109/globconet53749.2022.9872410 · Cited by 8
“Prior to the invention of GPUs, numerous handcrafted features including the scale-invariant features transform (SIFT) [31] as well as the histogram of oriented gradients (HOG) were devised and grouped to produce a bag-of-features (BoF) [32] to be used in classical machine learning models and functional image classific…”
MethodMemory efficient recognition of specific objects with local features
Kise, K., Kazuto, N., & Iwamura, M. (2008) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2008.4761711 · Cited by 8
Object localisation using the Generative Template of Features
Allan, M., & Williams, C. K. I. (2009) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2009.02.002 · Cited by 8
Video face matching using subset selection and clustering of probabilistic multi-region histograms
Mau, S., Shaokang Chen, A., Sanderson, C., & Lovell, B. C. (2010) · Cited by 8
Image Processing Methods Applied to Landmine Detection in Ground Penetrating Radar
Sakaguchi, R. T. (2013) · DukeSpace (Duke University) · Cited by 12
Content-based image retrieval for categorized dataset by aggregating gradient and texture features
Srivastava, D., Rajitha, B., & Agarwal, S. (2021) · Neural Computing and Applications · doi:10.1007/s00521-020-05614-y · Cited by 7
Probabilistic Inference over Image Networks
Taranto, C., Mauro, N. D., & Esposito, F. (2011) · Communications in computer and information science · doi:10.1007/978-3-642-27302-5_1 · Cited by 9
“The Bag of Words model [22] (BOW) has been inherited from the area of document analysis.”
BackgroundMotion dense sampling and component clustering for action recognition
Aihara, K., & Aoki, T. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-014-2112-1 · Cited by 7
“However, past studies [8, 19] show non-grid interest points are not always effective for classification.”
BackgroundLearning Visual Dictionaries from Class-Specific Superpixel Segmentation
Castelo-Fernández, C., & Falcão, A. X. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-29888-3_14 · Cited by 8
Beyond Bag-of-Concepts: Vectors of Locally Aggregated Concepts
Grootendorst, M., & Vanschoren, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-46147-8_41 · Cited by 8
Dense Simple Features for Fast and Accurate Medical X-Ray Annotation
Avni, U., Greenspan, H. K., & Goldberger, J. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15751-6_29 · Cited by 7
“Nowak et al. [ 3 ] showed that the number of patches is the single most influential parameter governing performance.”
BackgroundEfficient Object Pixel-Level Categorization Using Bag of Features
Aldavert, D., Arnau Ramisa, A., Toledo, R., & de Mántaras, R. L. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-10331-5_5 · Cited by 10
“However, various works [10, 3] show that large dictionaries typically obtain better classification results.”
BackgroundObject retrieval using configurations of salient regions
Wang, W., Luo, Y., & Tang, G. (2008) · ACM International Conference on Image and Video Retrieval (CIVR) · doi:10.1145/1386352.1386365 · Cited by 7
“This has been proved to be effective especially in image categorization application [11, 12 ]; however, spatial configuration is such valuable information that it cannot be discarded for many other applications using salient regions, including the object retrieval problem.”
BackgroundMethodDense sampling low-level statistics of local features
Nakayama, H., Harada, T., & Kuniyoshi, Y. (2009) · ACM International Conference on Image and Video Retrieval (CIVR) · doi:10.1145/1646396.1646419 · Cited by 7
“[4] compared image classification performance achieved by various keypoints detection methods on several datasets.”
BackgroundMethodInfluentialRecognition of People Reoccurrences Using Bag-Of-Features Representation and Support Vector Machine
Liu, K., & Yang, J. (2009) · Chinese Conference on Pattern Recognition · doi:10.1109/ccpr.2009.5344034 · Cited by 7
“In the study of Nowak et al. [ 11 ], it is shown that random sampling gives equal or better classification than the sophisticated multi-scale interest operators that are in common use.”
Background
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.