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 601–700 of 925
Region-based automatic web image selection
Yanai, ., & Barnard, K. (2010) · Multimedia Information Retrieval · doi:10.1145/1743384.1743436 · Cited by 3
“Sample 3000 patches per image randomly in the same way as [19].”
BackgroundOne-shot Recognition Using Unsupervised Attribute-Learning
Guo, Z., & Wang, Z. J. (2010) · Pacific-Rim Symposium on Image and Video Technology · doi:10.1109/psivt.2010.8 · Cited by 3
“[11] shows that randomly selecting patches to compute descriptors for constructing bag-of-words model works the best in average.”
BackgroundVega, G. L., Benezeth, Y., Marzani, F. S., & Boochs, F. (2014) · Journal of Electronic Imaging · doi:10.1117/1.jei.23.5.053025 · Cited by 4
“Although typical BOW indicates that such areas are determined by salient keypoints, an alternative is to compute a dense grid of fixed patches instead [11].”
BackgroundRobust invariant descriptors for visual object recognition
Ganesharajah, B., Mahesan, S., & Pinidiyaarachchi, U. A. J. (2011) · IEEE International Conference on Industrial and Information Systems (ICIIS) · doi:10.1109/iciinfs.2011.6038059 · Cited by 3
“A codebook of 1000 elements is built because, codebook generally needs to be large to achieve the best results [13].”
BackgroundLog-Linear Mixtures for Object Class Recognition
Weyand, T., Deselaers, T., & Ney, H. (2009) · British Machine Vision Conference (BMVC) · doi:10.5244/c.23.30 · Cited by 3
“In addition to the wavelet-based interest point detector from the baseline setup, we use a difference of Gaussians detector and random extraction positions [20] in order to also capture homogeneous image regions.”
MethodEnhancing Music Information Retrieval by Incorporating Image-Based Local Features
Kaliciak, L., Horsburgh, B., Song, D., Wiratunga, N., & Pan, J. Z. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-35341-3_19 · Cited by 3
“[10] is a comparison of different techniques used in B.”
MethodSketch-based image retrieval using sketch tokens
Wang, S., & Miao, Z. (2015) · Asian Conference on Pattern Recognition · doi:10.1109/acpr.2015.7486533 · Cited by 3
“As indicated in [9], random sampling strategy works well in a bag-of-features setup for image classification, we adopt it in this work.”
MethodVisualizing the lesson process in active learning classes
Toyoura, M., Sakaguchi, M., Mao, X., Hanawa, M., & Murakami, M. (2016) · IEEE Frontiers in Education Conference (FIE) · doi:10.1109/fie.2016.7757734 · Cited by 3
“Researchers have shown that arranging only a few samples in several clusters results in a good k [26], which contributes to accurate estimation.”
BackgroundCell identification using image analysis: A literature survey
Gamarra, M., Zurek, E. E., & San-Juan-Vergara, H. G. (2017) · Iberian Conference on Information Systems and Technologies (CISTI) · doi:10.23919/cisti.2017.7975973 · Cited by 3
Saliency Deep Embedding for Aurora Image Search
Yang, X., Gao, X., Song, B., Wang, N., & Yang, D. (2018) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2018.8486466 · Cited by 3
Comparative Analysis of Different Features and Encoding Methods for Rice Image Classification
Nirmalan, V. E., Nawarathna, R. D., & Manivannan, S. (2018) · International Conference on Information and Automation for Sustainability (ICIAfS) · doi:10.1109/iciafs.2018.8913380 · Cited by 3
“Dense feature sampling seems to lead to better performance compared to interest point detectors for image classification [14].”
BackgroundMedical image classification: A comparison of various handcrafted features
Olayemi, A., Zare, & Fermi, P. M. (2019) · Figshare · Cited by 3
Severity-Oriented Multi-Objective Crowdsourced Test Reports Prioritization
Wu, Y., Xiao, L., & Liao, J. (2024) · International Journal of Image and Graphics · doi:10.1142/s0219467825500652 · Cited by 3
“Therefore, a typical image feature extraction technique, such as bag Of features (BOF)[24], which considers only the distribution of global features based on the original RGB values and ignores their location information, is not well suited for our task to obtain image feature vectors.”
MethodXu, Z., Nan, F., Qi, J., Yang, Y., Wang, X., & Yang, P. (2023) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads60453.2023.00139 · Cited by 3
“Within this paradigm, commonly implemented techniques include Simple MI [24] and Vocabulary-based methods [25], [26], However, these methods often lose key instance information within bags.”
MethodA survey of classification accuracy using multifeatures and multi-kernels
Nguyen-Duc, H., Do-Hong, T., Le-Tien, T., & Bui-Thu, C. (2013) · International Conference on Advanced Technologies for Communications · doi:10.1109/atc.2013.6698197 · Cited by 3
Towards optimal vlad for human action recognition from still images
Lei Zhang, A., Zhen, X., & Han, J. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7471995 · Cited by 3
Convolutional Shape-Aware Representation for 3D Object Classification
Ghodrati, H., Luciano, L., & Hamza, A. B. (2018) · Neural Processing Letters · doi:10.1007/s11063-018-9858-9 · Cited by 3
“Other global shape descriptors are constructed by aggregating the local descriptors using the bag-of-features (BoF) paradigm [19], which quantizes each local descriptor to its nearest cluster center usingK-means clustering and then encodes each shape as a histogram over cluster centers by counting the number of assign…”
MethodLine Model-Based Drift Estimation Method for Indoor Monocular Localization
Feng, G., Ma, L., & Tan, X. (2018) · IEEE Vehicular Technology Conference · doi:10.1109/vtcfall.2018.8690676 · Cited by 3
Wang, X. (2011) · Springer eBooks · doi:10.1007/978-1-4419-9482-0_3 · Cited by 3
“Results in [ 26 ] showed that dense sampling improved the performance because it captured the most information, but its computation was expensive.”
Idiap on Medical Image Classification
Tommasi, T., & Orabona, F. (2010) · The Kluwer international series on information retrieval · doi:10.1007/978-3-642-15181-1_24 · Cited by 3
Toennies, K. D. (2012) · Advances in computer vision and pattern recognition · doi:10.1007/978-1-4471-2751-2_12 · Cited by 3
Fabián, J., Pires, R., & Rocha, A. D. R. (2013) · Pattern Recognition Letters · doi:10.1016/j.patrec.2013.09.011 · Cited by 3
“Here, we use a dense-sampling approach following an idea proposed by Nowak et al. (2006) to extract low-level features.”
MethodDistributional Learning of Appearance
Griffin, L. D., Wahab, M. H., & Newell, A. J. (2013) · PLoS ONE · doi:10.1371/journal.pone.0058074 · Cited by 5
“operationally, rather than semantically, specified categories of local image structure; and typical systems have used hundreds or thousands of textons [65].”
BackgroundLiu, K., & Yang, J. (2010) · Optical Engineering · doi:10.1117/1.3281668 · Cited by 3
A local spectral distribution approach to face recognition
Pothos, V. K., Theoharatos, C., & Economou, G. (2012) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2012.01.006 · Cited by 3
“In accordance with other researchers’ findings working on related applications [45], best results were obtained by means of the dense sampling approach, filtering the face image with a single pixel overlapping sliding window.”
ResultRandom-sampling-based spatial-temporal feature for consumer video concept classification
-, A. X. W., Pei, Y., & Zha, H. (2012) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2012.6467246 · Cited by 3
“[9] employed random sampling for bag-of-features based image classification with nice results.”
MethodText and image subject classifiers
Vreeswijk, D. T. J., Huurnink, B., & Smeulders, A. W. M. (2011) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2072298.2072037 · Cited by 3
“However attractive this model may be from a conceptual point of view, the state-of-the-art in both image concept classification and text subject classification is to use as many raw features as possible [5, 7].”
BackgroundAccurate visual word construction using a supervised approach
Fernando, B., Fromont, É., Muselet, D., & Sebban, M. (2010) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2010.6148844 · Cited by 3
“Recently, dense sampling strategy has been reported to be better than sparse sampling [2].”
BackgroundWavelet-based salient points with scale information for classification
Teynor, A., & Burkhardt, H. (2008) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2008.4761088 · Cited by 3
“Nowak et al. [10] have shown that a sufficient number of interest points is crucial for a bagof-features image classification.”
BackgroundLocal Part Model for Action Recognition in Realistic Videos
Shi, F. (2014) · doi:10.20381/ruor-3757 · Cited by 3
“This is consistent with the results of random sampling for image classification [76].”
BackgroundMethodResultInfluentialAn experimental study of employing visual appearance as a phenotype
Wolf, L., & Donner, Y. (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.2008.4587624 · Cited by 3
“Keypoints are selected at random locations [13].”
Modeling Time Series Data for Supervised Learning
Baydoğan, M. G. (2012) · ProQuest LLC eBooks · Cited by 3
Incremental on-line semantic indexing for image retrieval in dynamic databases
Karthik, S., Pulla, C., & Jawahar, C. V. (2009) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2009.5204246 · Cited by 3
Codebook+: A New Module for Creating Discriminative Codebooks
Zhang, Z., Chan, S., & Chia, L.-T. (2007) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2007.4284775 · Cited by 3
“However, different image sampling methods lead to different document-word pairs, which can affect the performance [6].”
BackgroundImage Retrieval based on VA-File and Multi-Resolution BOW
Lipin, W., & Pu, J. (2014) · Applied Mathematics & Information Sciences · doi:10.12785/amis/090152 · Cited by 3
Rule based optimization of type-2 fuzzy inference system used at impulse noise removing
Soytürk, M. A., Baştürk, A., & Yüksel, M. E. (2011) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2011.5929780 · Cited by 3
Image retrieval using extended bag-of-visual-words
Bhattacharya, N., & Sil, J. (2016) · International Conference on Advances in Computing, Communications and Informatics (ICACCI) · doi:10.1109/icacci.2016.7732340 · Cited by 3
“Different sampling techniques [10] are applied for extraction of features from the images.”
MethodA Survey On Sketch Based Image Retrieval Technique
Deore, A. A., & Gunjal, B. L. (2016) · International journal of advance research and innovative ideas in education · Cited by 3
Moniruzzaman, M., & Islam, S. M. S. (2018) · International Conference on Machine Learning and Data Engineering (iCMLDE) · doi:10.1109/icmlde.2018.00025 · Cited by 4
“Finally, the image is characterised by the distribution of the samples in descriptor space [17].”
BackgroundSocial-sensed multimedia computing
Cui, P. (2017) · doi:10.1145/3122865.3122872 · Cited by 3
Hybrid Featured based Pyramid Structured CNN for Texture Classification
Liu, H., Kamata, S., & Li, Y. (2019) · IEEE International Conference on Signal and Image Processing Applications (ICSIPA) · doi:10.1109/icsipa45851.2019.8977773 · Cited by 3
“Bags of features (BoF) [7], vector of locally aggregated descriptors (VLAD) [8], and Fisher Vector (FV) Encoding [9] methods are three widely used traditional methods on texture recognition: BoF is simply using the k-means methods to cluster image features like scale-invariant feature transform (SIFT) features and the…”
MethodHe, D., Li, S., He, X., Chang, L., Zhang, N., & Jiang, Q. (2020) · Journal of Medical and Biological Engineering · doi:10.1007/s40846-020-00532-9 · Cited by 3
“The bag of visual word (BoVW) model [10, 11] was proposed to design a codebook to integrate the descriptors by k-means clustering method.”
MethodBag-of-Features in Microscopic Images Classification
Beagum, S., Ashour, A. S., & Dey, N. (2016) · IGI Global eBooks · doi:10.4018/978-1-5225-0571-6.ch017 · Cited by 3
Abnormal behavior detection based on the motion-changed rules
Liu, S., Hao, X. U. E., Xu, C., & Fang, K. (2020) · International Conference on Signal Processing · doi:10.1109/icsp48669.2020.9321012 · Cited by 3
“Hence, this paper uses bag-of-words [9] approach to model the normal motion-changed rules.”
MethodSemantic Image Understanding: From Pixel to Word
Fu, H. (2012) · UPT. Syiah Kuala University Library (Syiah Kuala University) · Cited by 3
Spatial Fisher Vectors for Image Categorization
Krapac, J., Verbeek, J. J., & Jurie, F. (2011) · HAL · Cited by 3
Self-citationCombined Feature Extraction from Global/Local Statistics of Visual Words using Relevant Operations
Matsukawa, T., & Kurita, T. (2010) · 대한전자공학회 기타 간행물 · Cited by 3
Visual Concept Detection and Real Time Object DetectionPreprint
Ran, T. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1104.0582 · Cited by 3
“[4] showed that sampling on a regular dense grid outperforms complex salient point detectors[7] simply because dense sampling produces much more image patches than interest point operators.”
BackgroundMethodCombining Features to a Class-Specific Model in an Instance Detection Framework
Lara, A. C., & Hirata, R. (2011) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi.2011.9 · Cited by 2
Cost-sensitive learning in social image tagging: review, new ideas and evaluation
Li, Z., & Lew, M. S. (2012) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-012-0022-4 · Cited by 2
Robust information fusion in the DOHT paradigm for real-time action detection
Vaquette, G., Achard, C., & Lucat, L. (2016) · Journal of Real-Time Image Processing · doi:10.1007/s11554-016-0660-5 · Cited by 6
“To exploit the discriminative ability of trajectories and in order to benefit from dense sampling, which has shown to improve results in the image classification field [41], Wang et al.”
MethodLi, X., Zhang, L., Jian, Z., & Zuo, L. (2021) · Neural Processing Letters · doi:10.1007/s11063-021-10502-0 · Cited by 2
Gesture Recognition of Subway Drivers Based on Improved Dense Trajectory Algorithm
Suo, D., Wei, X., & Wei, D. (2021) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc52312.2021.9602082 · Cited by 2
Handcrafted vs. Learned Features for Automatically Detecting Violence in Surveillance Footage
da Silva, A. V. B., & Pereira, L. F. A. (2022) · Anais do Seminário Integrado de Software e Hardware (SEMISH) · doi:10.5753/semish.2022.222887 · Cited by 2
“It is mainly based on the bag-of-features technique [Nowak et al. 2006] associated with two types of image descriptors: (i) traditional handcrafted features and (ii) learned features automatically extracted using Deep Learning models, such as the VGG-19 [Simonyan and Zisserman 2014].”
MethodReconstructing Façade Details Using MLS Point Clouds and Bag-of-Words Approach
Froech, T., Wysocki, O., Ludwig Hoegner, B., & Stilla, U. (2024) · Lecture notes in geoinformation and cartography · doi:10.1007/978-3-031-43699-4_21 · Cited by 2
Chonglun, L. (2016) · International Conference on Information Science and Control Engineering · doi:10.1109/icisce.2016.118 · Cited by 2
“To solve the problem of dependence on image segmentation, researchers build the BOF Algorithm[7,8] by combining the image segmentation and detection algorithm, 2016 3rd International Conference on Information Science and Control Engineering 978-1-5090-2534-3 /16 $31.00 © 2016 IEEE DOI 10.1109/ICISCE.2016.118 5195 0/16…”
MethodInfluentialMachines as an assistants for humans' creativity: A conceptual model
Osipyan, H., Vedadi, S., & Cheok, A. D. (2017) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon.2017.8216561 · Cited by 2
“For example, in the domain of image retrieval, there are different approaches for extracting the features from images, such as extraction of color and texture descriptors [38], bag-of-features representation of local descriptors [39], GIST features [40], etc.”
BackgroundMethodA Generic Framework for Semantic Annotation of Images
Helmy, T. (2018) · International Journal of Image and Graphics · doi:10.1142/s0219467818500134 · Cited by 2
Action Recognition Combining Trajectory Feature with KNR
Hu, Y., & Liu, B. (2018) · IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) · doi:10.1109/imcec.2018.8469609 · Cited by 2
Intelligent Content Based X-Ray Image Retrieval using Speeded up Robust Feature Descriptors
Lahari, M. V., & Krupa, B. (2017) · IEEE International WIE Conference on Electrical and Computer Engineering · doi:10.1109/wiecon-ece.2017.8468926 · Cited by 2
“Here, features are extracted from the enhanced images using three methods explained below: 1) PCA: In this method, for all the images in the dataset, dense sampling [17] is applied, where the interest points in an image are considered at every nineth pixel.”
MethodGao, Y., & Dai, Q. (2014) · Elsevier eBooks · doi:10.1016/b978-0-12-802419-5.00005-x · Cited by 2
New Color Image Histogram-Based Detectors
Rassem, T. H., & Khoo, B. E. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-25191-7_15 · Cited by 2
“[3] proved that important factor to achieve high accuracy in the classification and recognition systems is extracting the features densely.”
BackgroundUnveiling the hand of a 19 th century artist with binary image classification and bag-of-features
Montagner, C., Jesus, R. M., Correia, N. M. R., Melo, M. J., Vilarigues, M. G., Macedo, R., & de Freitas, H. (2012) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) · Cited by 2
Real-Time Object Segmentation Using a Bag of Features Approach
Aldavert, D., Arnau Ramisa, A., Ramon, L. D. M., & Toledo, R. (2010) · Frontiers in artificial intelligence and applications · doi:10.3233/978-1-60750-643-0-321 · Cited by 2
Vision-based probabilistic absolute position sensor
Paris, R., Melik-Merkumians, M., & Schitter, G. (2015) · IEEE International Instrumentation and Measurement Technology Conference · doi:10.1109/i2mtc.2015.7151601 · Cited by 2
Efficient Development of User-Defined Image Recognition Systems
Moehrmann, J., & Heidemann, G. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-37410-4_21 · Cited by 2
An efficient image classifier using discrete cosine transform
Kekre, H. B., Sarode, T., & Ugale, M. (2011) · International Conference & Workshop on Emerging Trends in Technology · doi:10.1145/1980022.1980096 · Cited by 2
“Recently, a popular technique for representing image content for image category recognition is the bag of visual word model [10, 6].”
MethodWang, Q., Qi, X., & Xu, J. (2010) · doi:10.1145/1877911.1877920 · Cited by 2
“By looking for the peaks in the spatial geo-tag distribution, they build the landmark classification model with multi-class support vector machines (SVM) and bag of features (BOF) [6].”
MethodCategory-specific incremental visual codebook training for scene categorization
Qin, J., & Yung, N. H. C. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5652347 · Cited by 2
Bag of words for semantic automatic medical image annotation
Akaichi, J. (2014) · Network Modeling Analysis in Health Informatics and Bioinformatics · doi:10.1007/s13721-014-0061-2 · Cited by 2
“Some approaches use a binary weighting of visual words by considering the occurrence or non-occurrence of words in images (Nowak et al. 2006).”
BackgroundMethodInfluentialCompact codebook design for visual scene recognition by Sequential Input Space Carving
Mayurathan, B., Pinidiyaarachchi, U. A. J., & Niranjan, M. (2013) · Machine learning for signal processing ... · doi:10.1109/mlsp.2013.6661992 · Cited by 2
Image classification using adapted codebook
Lin, C., Li, S., & Su, S. (2009) · International Conference on Information Technology in Medicine and Education · doi:10.1109/itime.2009.5236269 · Cited by 2
“There are various methods for creating visual codebooks, K-means clustering is currently the most common [1, 2, 3, 4] but mean-shift [12] and”
MethodYang, K., Zhang, L., Wang, M., & Zhang, H.-J. (2011) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2072298.2071976 · Cited by 2
“Actually, many recent studies have shown that the simplest dense sampling method, which provides a more complete image representation, is able to perform much better than interest point detector in many image classification tasks [10].”
BackgroundWeb image gathering with region-based bag-of-features and multiple instance learning
Yanai, . (2009) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2009.5202531 · Cited by 2
“Sample 3000 patches per image randomly in the same way as [11].”
BackgroundClass-Specific Binary Correlograms for Object Recognition
Amores, J., Sebe, N., & Radeva, P. I. (2007) · British Machine Vision Conference (BMVC) · doi:10.5244/c.21.35 · Cited by 2
“In this sense, using CSBCs can be considered as an efficient post-processing step after after obtaining a set of class-specific features used in many recent works [13, 14, 12, 16].”
BackgroundMethodInfluentialComparing Feature Matching for Object Categorization in Video Surveillance
Wijnhoven, R. G. J., & de With, P. H. N. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-04697-1_38 · Cited by 2
“This is in line with earlier findings [4,5,6].”
BackgroundMethodResultInfluentialResearch on object recognition using bag of word model for mobile robot navigation
Yang, J., Wang, K., Li, M., & Liu, L. (2011) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2011.5986295 · Cited by 2
GPU computing with orientation maps for extracting local invariant features
Ichimura, N. (2010) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2010.5543742 · Cited by 2
“Because of these advantages, local invariant features have been widely used as fundamental elements for image matching and object recognition[21, 12, 15, 16, 4, 6, 8, 13, 18, 14, 24, 10].”
BackgroundBeyond Bag-of-Words: combining generative and discriminative models for scene categorization
Li, Z., & Yap, K. (2012) · Multimedia Tools and Applications · doi:10.1007/s11042-012-1245-3 · Cited by 2
“In recent years, many BoW-based methods have been developed [7, 8, 10, 15, 16].”
MethodA Fuzzy Associative Classification Approach to Visual Concept Detection
Mangalampalli, A., & Pudi, V. (2014) · International Journal of Uncertainty Fuzziness and Knowledge-Based Systems · doi:10.1142/s0218488514500214 · Cited by 2
Spectral Shape Analysis of the Hippocampal Structure for Alzheimer’s Disease Diagnosis
Initiative, F. T. A. D. N., Maicas, G., Muñoz, A. I., Galiano, G., Hamza, A. B., & Schiavi, E. (2016) · SEMA SIMAI Springer series · doi:10.1007/978-3-319-32013-7_2 · Cited by 2
“In order to assist the diagnosis of Alzheimer we merge the spectral analysis into a Bag of Features (BoF) (see [13] for details) framework proposed in [11] for shape retrieval.”
BackgroundMethodA New Database and Protocol for Image Reuse Detection
Isikdogan, F., Adıyaman, İ., Salah, A. A. A., & Salah, A. A. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46604-0_62 · Cited by 2
“’s work on the evaluation of sampling strategies [27].”
BackgroundSpecial object extraction from medieval books using superpixels and bag-of-features
Yang, Y., & Rushmeier, H. (2016) · Journal of Electronic Imaging · doi:10.1117/1.jei.26.1.011008 · Cited by 2
THE FOURIER TRANSFORM BASED DESCRIPTOR FOR VISUAL OBJECT CLASSIFICATION
Çevıkalp, H., & Kurt, Z. (2017) · Anadolu University Journal of Science and Technology-A Applied Sciences and Engineering · doi:10.18038/aubtda.300419 · Cited by 2
“Many studies [2,8] show that dense sampling significantly outperforms other sampling types in the context of object classification, so we use dense sampling in our experiments.”
BackgroundA Multiple-Instance Learning Approach to Sentence Selection for Question Ranking
Romeo, S. O., Martino, G. D. S., Barrón‐Cedeño, A., & Moschitti, A. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-56608-5_34 · Cited by 2
“, a vector where the i-th element corresponds to the number of instances represented by the i-th cluster [28].”
BackgroundAutomated visual classification of indoor scenes and architectural styles
Solmaz, B., Yücesoy, V., & Koç, A. (2017) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2017.7960205 · Cited by 2
“Bu kapsamda araştırmacılar değişik türde öznitelikler ve betimleyiciler tabanlı yöntemler geliştirmiştir [1]–[3].”
Discriminative Dictionary Design for Action Classification in Still Images
Roy, A., Banerjee, B., & Murino, V. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68548-9_15 · Cited by 3
Fine-grained visual marine vessel classification for coastal surveillance and defense applications
Koç, A., Solmaz, B., Gündoğdu, E., Yücesoy, V., & Karaman, K. (2017) · Electro-Optical Remote Sensing · doi:10.1117/12.2278864 · Cited by 2
Learning visual codebooks for image classification using spectral clustering
Hong, Y., & Zhu, W. (2017) · Soft Computing · doi:10.1007/s00500-017-2937-4 · Cited by 2
“We then scale them into the same size through bicubic interpolation (Keys 1981) and adopt the dense sampling operator (Nowak et al. 2006) to collect a batch of local image patches from each image.”
BackgroundMethodInfluentialSilva, C., Welfer, D., & Dornelles, C. (2018) · INTELIGENCIA ARTIFICIAL · doi:10.4114/intartif.vol21iss61pp1-13 · Cited by 2
Supervised Saliency Mapping for First-Person Videos With an Inverse Sparse Coding Framework
Li, Y., Akaho, S., Asoh, H., & Tan, B. (2019) · IEEE Access · doi:10.1109/access.2019.2892945 · Cited by 2
“Efficient saliency mapping plays a significant role for preprocessing in many computer vision tasks, such as classification [2], [3], compression [4], recognition [5], and segmentation [6], [7]; many attempts to understand and predict salient positions have been undertaken with applications in, e.”
BackgroundUEC at TRECVID 2008 High Level Feature Task.
Tang, Z., Noguchi, A., & Yanai, . (2008) · Cited by 2
Supervised Two-Stage Transfer Learning on Imbalanced Dataset for Sport Classification
Bi, T., Jarnikov, D., & Lukkien, J. J. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30642-7_32 · Cited by 2
Toennies, K. D. (2017) · Advances in computer vision and pattern recognition · doi:10.1007/978-1-4471-7320-5_12 · Cited by 2
Dense Segmentation-Aware Descriptors
Trulls, E., Kokkinos, I., Sanfeliu, A., & Moreno-Noguer, F. (2015) · Springer eBooks · doi:10.1007/978-3-319-23048-1_5 · Cited by 4
Machine Learning Approaches for Classification of Ultra High Carbon Steel Micrographs
Muñoz-Ródenas, J., Miguel, V., García‐Sevilla, F., Coello, J., & Martínez-Martínez, A. (2023) · Key engineering materials · doi:10.4028/p-2sqo8w · Cited by 2
“This approach is named bag-of-features [10,11,12] and its aim is constructing a set of visual data by extracting features descriptors from representative images of each category.”
BackgroundMedical Image Classification at Tel Aviv and Bar Ilan Universities
Avni, U., Goldberger, J., & Greenspan, H. K. (2010) · The Kluwer international series on information retrieval · doi:10.1007/978-3-642-15181-1_23 · Cited by 2
“Nowak et al (2006) focused on comparing the performance of various competing strategies for image representation in the BoW approaches to visual categorization.”
BackgroundMethodObject localization using positive features
Lei, H., Jiang, G., Wang, R., & Quan, L. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.06.061 · Cited by 2
An Image Recognition Method Based on Scene Semantics
Zhang, Y., & Ma, Y. (2013) · Lecture notes in electrical engineering · doi:10.1007/978-1-4471-4850-0_58 · Cited by 2
Video Retrieval Based on Uncertain Concept Detection Using Dempster–Shafer Theory
Shirahama, K., Kumabuchi, K., Grzegorzek, M., & Uehara, K. (2015) · Springer eBooks · doi:10.1007/978-3-319-14998-1_12 · Cited by 2
“reported that the performance is improved as more descriptors are sampled from images [38].”
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.