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 701–800 of 925
Interest Point Detection and Region Descriptors
Treiber, M. A. (2010) · Advances in computer vision and pattern recognition · doi:10.1007/978-1-84996-235-3_7 · Cited by 2
Discriminating Semantic Visual Words for Scene Classification
Liu, C., Xu, D., & Feng, S. (2010) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e93.d.1580 · Cited by 2
“Since the performance of Bag-of-Visual-Words methods depends in a fundamental way on the visual words, the problem of effective design of these visual words has been gaining increasing attention in recent literature [6]–[14].”
BackgroundMining remote-image repositories with application to Mars Rover stereoscopic image datasets
Willis, A., Shadid, W., & Eppes, M. C. (2009) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.806134 · Cited by 2
Image Classification for the Painting Style with SVM.
Misumi, M., Orii, H., Sharmin, T., Mishima, K., & Tsuruoka, T. (2016) · IIAE International Conference on Industrial Application Engineering (ICIAE) · doi:10.12792/iciae2016.046 · Cited by 2
A mahout based image classification framework for very large dataset
He, J., Xue, Z.-Y., Gao, M.-W., & Wu, H. (2014) · International Conference on Cloud Computing and Internet of Things (CCIOT) · doi:10.1109/cciot.2014.7062518 · Cited by 2
“In the training phase, it consists of feature extraction, bag-of-feature model [15] and supervised learning (training).”
BackgroundLeong, S. H., & Ong, S. H. (2017) · PLoS ONE · doi:10.1371/journal.pone.0180307 · Cited by 2
Car Make and Model Recognition using Sparse Coding and Bag of Features
Kamal, I., Housni, K., & Hadi, Y. (2017) · International Conference on Big Data, Cloud and Applications (BDCA) · doi:10.1145/3090354.3090435 · Cited by 2
Obstacle avoidance of aerial vehicle based on monocular vision
Qiu, W., Bi, S., Zhong, C., Luo, Y., Li, J., & Sun, B. (2017) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber.2017.8446065 · Cited by 2
“This is the way [5], [6], [7] and [8] used to solve the classification problem.”
MethodFeature Detector-level Fusion Methods in Food Recognition
Razali, M. N., & Manshor, N. B. (2019) · International Conference on Communication Engineering and Technology (ICCET) · doi:10.1109/iccet.2019.8726897 · Cited by 2
“e feature encoding will be also become higher [17], [18].”
BackgroundImprovised Salient Object Detection and Manipulation
Maity, A. (2016) · International Journal of Image Graphics and Signal Processing · doi:10.5815/ijigsp.2016.02.07 · Cited by 8
Singh, A., Sarkhel, R., Das, N., Kundu, M., & Nasipuri, M. (2020) · Sensing and Imaging · doi:10.1007/s11220-020-00288-1 · Cited by 4
“A sampling based approach [23], proposed by Nowak et al.”
MethodLearning Distance Functions for Automatic Annotation of Images
Krapac, J., & Jurie, F. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-79860-6_1 · Cited by 1
“Patches can also be sampled randomly [24] or even densely [32] from the image.”
BackgroundSelf-citationA Study on Sampling Strategies in Space-Time Domain for Recognition Applications
Dikmen, M., Lin, D. J., Pozo, A. D., Cao, L. L., Fu, Y., & Huang, T. S. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-11301-7_47 · Cited by 2
“We build our study on a structure that mimics the experimental nature of Laptev et al.[3] and Nowak et al.[ 6 ], except that we work in the video domain instead of the image domain.”
MethodResultModeling Objects with Local Descriptors of Biologically Motivated Selective Attention
Tan, L., Cao, Y., Yang, M., & He, Q. (2008) · International Conference on Natural Computation (ICNC) · doi:10.1109/icnc.2008.649 · Cited by 2
“Average of keypoints per image shows that keypoints in saliency object regions are obviously reduced on both Caltech 101 object and TRECVID 2007 key frame datasets (See Table 1). Table 1 . Average of keypoints per image”
BackgroundMethodInfluentialImprovised Salient Object Detection and ManipulationPreprint
Maity, A. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.02999 · Cited by 2
“Examples ranges from classification of images [23], summarized collection of images [24], video retargeting as mentioned in M.”
BackgroundContent Based Image Retrieval for Medical Applications
Balaji, M. N. (2019) · Shodhgangotri · Cited by 2
Image-based detection and classification of allergenic pollen
Vega, G. L. (2015) · theses.fr (ABES) · doi:10.70675/198a259ez93c6z4d5bz9723z72622599823f · Cited by 2
ASA-Net: Deep representation learning between object silhouette and attributes
Yang, S., Wang, J., Yang, L., & Fei, Z. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.06.071 · Cited by 1
Spatial and temporal analysis of habitat quality
TONYALOĞLU, E. E., & ATAK, B. K. (2025) · Ege Üniversitesi Ziraat Fakültesi Dergisi · doi:10.20289/zfdergi.1527153 · Cited by 1
Open Issues on Codebook Generation in Image Classification Tasks
Piras, L., & Giacinto, G. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-08979-9_25 · Cited by 1
“Some papers such as [34], and, afterwards, [39], and [9], review and compare several techniques to sample image patches from the images, and cluster or reduce them in some way in order to create an effective short codebook.”
BackgroundBeyond thinking in common categories: Predicting obstacle vulnerability using large random codebooks
Rühle, J., Rodner, E., & Denzler, J. (2015) · Machine Vision Applications · doi:10.1109/mva.2015.7153166 · Cited by 1
“Our method is based on techniques used in image categorization, such as local features [2] and bag-ofvisual-word models [4, 9].”
MethodHuman-Machine Cooperation in Large-Scale Multimedia Retrieval: A Survey
Shirahama, K., Grzegorzek, M., & Indurkhya, B. (2015) · The Journal of Problem Solving · doi:10.7771/1932-6246.1173 · Cited by 1
Unsupervised Visual Object Categorisation with BoF and Spatial Matching
Kinnunen, T., Lankinen, J., Kämäräinen, J., Lensu, L. T., & Kalviainen, H. A. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-38886-6_37 · Cited by 1
“Detector combinations performed the best which is in correspondence with the findings in [22].”
BackgroundSemantic-enriched visual vocabulary construction in a weakly supervised context
Rizoiu, M.-A., Velcin, J., & Lallich, S. (2015) · Intelligent Data Analysis · doi:10.3233/ida-140702 · Cited by 1
An evaluation of local interest regions for non-rigid object class recognition
Altun, O., & Albayrak, S. (2011) · Expert Systems with Applications · doi:10.1016/j.eswa.2011.08.060 · Cited by 1
“This work and Nowak et al. (2006) show that using random generated regions may be actually a good idea for object class recognition.”
BackgroundInfluentialEvaluation of vocabulary trees for localization in robot applications
Hwang, S., Park, C., Choi, Y., Yoo, D., & Kweon, I. S. (2013) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.1109/iccas.2013.6704138 · Cited by 1
Image retrieval based on classified vector quantization using color local thresholding classifier
Chen, H.-H., & Ding, J. (2012) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2012.6467389 · Cited by 1
“Index Terms— Quadtree Segmentation, Vector Quantization, Classified Vector Quantization, Image Indexing, CBIR”
Bai, S., Matsumoto, T., Takeuchi, Y., Kudo, H., & Ohnishi, N. (2012) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e95.d.3060 · Cited by 1
“This result is in agreement with observations in previous works [18].”
BackgroundResultOptimal operations for visual categorization
Cheng, Y., Qu, Y., Huang, J., Fang, T., Shen, L., & Xie, Y. (2010) · International Conference on Internet Multimedia Computing and Service · doi:10.1145/1937728.1937746 · Cited by 1
“Eric et al.[15] discussed the sampling strategy and demonstrated experimentally that the number of sampling patches is important in visual categorization.”
BackgroundGreenspan, H. K. (2009) · International Journal of Healthcare Information Systems and Informatics · doi:10.4018/jhisi.2009010105 · Cited by 1
Multi-support-region image descriptors and its application to street landmark localization
Cheng, H., Liu, Z., & Yang, J. (2011) · Machine Vision and Applications · doi:10.1007/s00138-011-0323-2 · Cited by 1
“For the previous approaches, the basic image representation in object localization is bag-of-features (BoFs) [ 35 ,22].”
MethodUnsupervised image categorization with improved spectral clustering
Yang, J., Miao, Z., & Wu, H. (2014) · doi:10.1109/icosp.2014.7015226 · Cited by 1
Unsupervised place recognition for assistive mobile robots based on local feature descriptions
Karasfi, B., Tang, S. H., Samsudin, K. B., Ramli, A. R., Jalalian, A., & Motlagh, O. (2011) · Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering · doi:10.1177/0959651811406641 · Cited by 1
Natural Image Classification Based on Improved Support Vector Machine
Qi, Y. J., Ou, Z. W., Zhang, B., Liu, T. Z., & Li, Y. (2011) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.58-60.2387 · Cited by 1
“Document [7-8] used the method that found the dense sampling local area and extracted the feature vector in the region to express the image content, thus greatly improving the performance of the visual vocabulary.”
MethodScale-Optimized Textons for Image Categorization and Segmentation
Kang, Y., & Sugimoto, A. (2011) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2011.48 · Cited by 1
“Recently image categorization frameworks have shown that the dense sampling of visual words [14] and their combinations with image cues can improve their performance significantly [15].”
BackgroundProduct search framework with categorization and identification
Park, C., & Kweon, I. S. (2008) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.1109/iccas.2008.4694513 · Cited by 1
“The evaluation with parameters of categorization based on bag of words[ 13 ] concludes a large codebook and random sampling give a good result.”
MethodThe Comparison of Classifiers for Object Categorization Based on Bag-of-Word Technology
Huang, J., Qu, Y., Li, C., & Hu, M.-J. (2009) · Chinese Conference on Pattern Recognition · doi:10.1109/ccpr.2009.5344138 · Cited by 1
“[18] E. Nowak, F. Jurie and B. Triggs.”
InfluentialImpact of SVM multiclass decomposition rules for recognition of cancer in gastroenterology images
Sousa, R., Dinis-Ribeiro, M. J., Pimentel‐Nunes, P., & Coimbra, M. T. (2013) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms.2013.6627827 · Cited by 1
“Feature extraction following a dense sampling strategy usually outperform the ones extracted according an interest point detector [8].”
MethodEfficient Multi-resolution Histogram Matching for Bag-of-Features
Cui, J., Tang, J., & Jiang, L. L. (2011) · International Conference on Image and Graphics · doi:10.1109/icig.2011.137 · Cited by 1
“Recently studies have shown that SIFT is one of the best descriptors for keypoints [6, 17].”
BackgroundSparse Representation and Learning-Based Classifiers
Cheng, H. (2015) · Advances in computer vision and pattern recognition · doi:10.1007/978-1-4471-6714-3_8 · Cited by 1
Proximity Clustering for Revealing a Semantically Dominant Class
Sandhan, T., Yun, K., & Choi, J. Y. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14364-4_7 · Cited by 1
“It has shown excellent performance for various visual classification tasks [20].”
BackgroundImproving automatic image annotation: Approach by Bag-Of- Key Point
Boudia, M., Abdel-Aziz, M. H., Zaoui, L., & Boudiaf, M. A. (2012) · Cited by 1
Experimental Evaluation of the Bag-of-Features Model for Unsupervised Learning of Images
Afonso, M., & Teixeira, L. F. (2015) · British Machine Vision Conference (BMVC) · doi:10.5244/c.29.146 · Cited by 1
“Similarly to [16], in order to test whether the clustering performance is influenced by the keypoint detection algorithm, a random generator of patches (RANDOM) was also used.”
BackgroundMethodResultInfluentialDraft: Deep Learning in Neural Networks: An Overview
Idsia, L. (2014) · Cited by 3
Hierarchical Learning for Large-Scale Image Classification via CNN and Maximum Confidence Path
Lu, C. H., Qu, Y., Shi, C., Jianping Fan, B., Wu, Y., & Wang, H. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24078-7_23 · Cited by 1
Discriminative FaceTopics for face recognition via latent Dirichlet allocation
Dhamecha, T. I., Sharma, P. K., Singh, R., & Mayank Vatsa, A. (2016) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2016.7477451 · Cited by 1
“Such mapping has been explored by researchers in various contexts [10, 19, 26, 31].”
BackgroundBag-of-Features in Microscopic Images Classification
Beagum, S., Ashour, A. S., & Dey, N. (2016) · Advances in medical technologies and clinical practice book series · doi:10.4018/978-1-5225-0140-4.ch001 · Cited by 1
Modeling the impact of keypoint detection errors on local descriptor similarity
Araújo, A. D. M., Lakshman, H., Angst, R., & Girod, B. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532368 · Cited by 1
“Index Terms— local descriptors, keypoint detection, histogram of gradients”
BackgroundMahale, V. A., & Yawalkar, P. M. (2016) · IJARCCE · doi:10.17148/ijarcce.2016.5130 · Cited by 1
“Although interest operators work well for small numbers of samples, the single most important factor governing performance is the number of patches sampled from the test image and ultimately interest operators cannot provide enough patches to compete [2].”
BackgroundCar recognition using the bag of features method
Kamal, I., & Oubaha, J. (2016) · doi:10.1109/icmcs.2016.7905554 · Cited by 1
“This process maps the input pixels into feature vectors[36], the map may usually be gradient based like SIFT[22], SURF[23] and HOG[24] descriptors or statistically based like PCA[25] or LDA[26][27].”
MethodActivity recognition for asd children based on joints estimation
Gao, D., Ju, Z., Fang, Y., Cao, J., Yang, C., & Liu, H. (2017) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2017.8123076 · Cited by 1
Multimodal analysis of free-standing conversational groups
Alameda-Pineda, X., Ricci, E., & Sebe, N. (2017) · doi:10.1145/3122865.3122869 · Cited by 1
Transactional Support for Visual Instance Search
Lejsek, H., Ásmundsson, F. H., Jónsson, B. Þ., & Amsaleg, L. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-02224-2_6 · Cited by 1
“strategies exist to determine (i) where local features should be extracted ([21, 26]), and (ii) what information each local feature should encode ([22, 3]).”
BackgroundAudio-Based Human Activity Recognition with Robots
Stork, J. A., Silva, J., Spinello, L., & Arras, K. O. (2011) · International Conference on Social Robotics · Cited by 2
WCE Polyp Detection Based On Locality-Constrained Linear Coding With A Shared Codebook
Zhu, T., Li, S., He, X., Yu, M., & Yang, J. (2020) · IEEE Data Driven Control and Learning Systems Conference (DDCLS) · doi:10.1109/ddcls49620.2020.9275193 · Cited by 1
Comparison of deep learning and hand crafted features for mining simulation data
Georgiou, T., Schmitt, S., Bäck, T., Pu, N., Chen, W., & Lew, M. S. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9413165 · Cited by 1
“Moreover, we tested extracting features from a regular grid instead of detected keypoints, as this strategy has proven to be superior in several applications that require global image description [22], [25].”
MethodCorro, L. M. (2021) · Cited by 1
Mobile crowdsourced test report prioritization based on text and image understanding
Wu, Y., Tong, Y., Liu, A., Zhao, L., & Zhang, X. (2023) · Journal of Software Evolution and Process · doi:10.1002/smr.2541 · Cited by 1
“Bag of features (BOF), 22 as a traditional image retrieval method, only focuses on the region with the most significant amount of information in the image while ignoring the location information of the features.”
BackgroundGrinin, L. E., Леонидович, Г. А., & Леонидович, Г. И. (2023) · Философия и общество · doi:10.30884/jfio/2023.04.01 · Cited by 4
Image Labeling by Integration of Local Co-Occurrence Histogram and Global Features
Omiya, T., & Hotta, K. (2014) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2014.p0511 · Cited by 1
A topology-based approach to computing neighborhood-of-interest points using the Morse complex
da Silva, R. D., Schwartz, W. R., Pedrini, H., Pulido, J., & Hamann, B. (2015) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2015.05.001 · Cited by 1
“Image R. journal homepage: www.elsevier .com/ locate/ jvc i A topology-based approach to computing neighborhood-of-interest points using the Morse complex q http://dx.doi.org/10.1016/j.jvcir.2015.05.001 1047-3203/ 2015 Elsevier Inc.”
MethodInfluentialA FWCL-based method for visual vocabulary formation
Zhang, S., Zhang, J., Guo, P., Chu, M., & Chang, K. H. (2014) · Multimedia Tools and Applications · doi:10.1007/s11042-014-2313-7 · Cited by 1
“At present time, studies of BOV model are mostly in the local primitive extraction [30, 27, 2], visual word formation [37, 16, 36, 19, 10, 20, 23, 24, 14, 29, 32] and image classification [26, 5, 12, 25, 22, 31, 17, 33, 40].”
Hassner, T., Mayzels, V., & Zelnik‐Manor, L. (2015) · Springer eBooks · doi:10.1007/978-3-319-23048-1_3 · Cited by 1
Confidence-based human action recognition with different-level features
Hu, X., & Jing, Y. (2016) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc.2016.7860939 · Cited by 1
“Most studies [5-6, 14-17, 21-23] focus on this kind of methods due to its satisfying performance in classifying simple actions (e.”
BackgroundAudition for multimedia computing
Friedland, G., Smaragdis, P., McDermott, J. H., & Raj, B. (2017) · doi:10.1145/3122865.3122868 · Cited by 1
Situation recognition using multimodal data
Singh, V. K. (2017) · doi:10.1145/3122865.3122873 · Cited by 1
Universiti Putra Malaysia, M., & bin Razali, M. N. (2019) · International Journal of Advanced Trends in Computer Science and Engineering · doi:10.30534/ijatcse/2019/1181.42019 · Cited by 1
The impact of the image processing in the indexation system
Elfakir, Y., Khaissidi, G., Mrabti, M., & Chenouni, D. (2019) · International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering · doi:10.11591/ijece.v9i5.pp4311-4320 · Cited by 1
“To solve the problem of computer memory caused by descriptor's dimension, we propose to use bag-of-features approach [25], the SIFT descriptors have been used to create the histograms, and K-Means clustering has been applied for clustering to create the bag-of-visual-descriptors [27, 28].”
BackgroundMethodCabezas, H., & Sarmiento, W. J. (2019) · TecnoLógicas · doi:10.22430/22565337.1513 · Cited by 1
“Las bolsas de palabras (BoW del inglés bag-of-words) son un modelo que permite simplificar el procesamiento de documentos al hacer un conteo de frecuencia de aparición de un conjunto finito de palabras claves (diccionario) para cada documento [35].”
BackgroundTwo Efficient Image Bag Generators for Multi-instance Multi-label Learning
Bhagat, P. K., Choudhary, P., & Singh, K. M. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-4015-8_36 · Cited by 1
RETRACTED ARTICLE: A hybrid encoding strategy for classification of medical imaging modalities
Sundarambal, B., Subramanian, S., & Muthukumar, B. (2020) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-02129-1 · Cited by 1
“In many related works, SIFT features are encoded using popular Bag of Words (Rodríguez et al. 2015; Zheng et al. 2019) and Fisher vector (Nowak et al. 2006) representations.”
MethodRetractedLogo Based Amphetamines Classification using SURF and Bag-of-features model
Nitijiramon, T., Cooharojananone, N., & Saiseng, S. (2020) · International Conference on Mathematics and Computers in Science and Engineering (MACISE) · doi:10.1109/macise49704.2020.00023 · Cited by 1
Factors Affecting the Cost to Accuracy Balance for Real-Time Video-Based Action Recognition
Govender, D., & Tapamo, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58799-4_58 · Cited by 1
Zhu, M., Wan, S., Jin, P., & Xu, J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87355-4_35 · Cited by 1
SIFTpack: A Compact Representation for Efficient SIFT Matching
Gilinsky, A., & Zelnik‐Manor, L. (2015) · Springer eBooks · doi:10.1007/978-3-319-23048-1_6 · Cited by 1
Sketch recognition based on attention mechanism and improved residual network
Fang, Q., Li, Q., Su, L., & Yang, Y. (2022) · International Conference on Communication, Image and Signal Processing (CCISP) · doi:10.1109/ccisp55629.2022.9974584 · Cited by 1
“Traditional sketch feature extraction strategies rely on manual feature extractors, such as scale invariant feature transform [3] and Histogram of Orientated Gradient (HOG) [4].”
MethodFreytag, A., Rühle, J., Bodesheim, P., Rodner, E., & Denzler, J. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1408.4692 · Cited by 1
“Later on, [10] showed that this is not the case and that dense and random selection of local features allows for larger BoW descriptors and also for higher recognition rates.”
BackgroundImproving Classification and Retrieval of Illuminated Manuscript with Semantic Information
Grana, C., Borghesani, D., & Cucchiara, R. (2010) · Communications in computer and information science · doi:10.1007/978-3-642-15850-6_18 · Cited by 1
Face recognition based on multi-scale local features
Geng, C. (2012) · doi:10.32657/10356/50725 · Cited by 1
“Although they result in far less compact representations than the interest points, random and dense sampling provide good results which confirms the coverage requirements of recognition methods [95].”
BackgroundCue Integration for Medical Image Annotation
Tommasi, T., Orabona, F., & Barbara Caputo, B. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-85760-0_72 · Cited by 1
“To build the visual vocabulary, we used SIFT features [8], computed around interest points detected via random sampling [9].”
MethodVisual codebook construction for class-specific recognition
Gao, J., Sang, N., Gao, C., Tang, Q., & Jun, S. (2009) · Optical Engineering · doi:10.1117/1.3160333 · Cited by 1
Carneiro, G., & Costeira, J. P. (2011) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.872026 · Cited by 1
UThe Vision Research Lab of UCSB at TRECVID 2007.
Gelasca, E. D., Joshi, S., Kleban, J. T., Mangiat, S., Manjunath, B. S., Moxley, E., Sarkar, A., & Xu, J. (2007) · TRECVID · Cited by 1
Loose shape model for discriminative learning of object categories
Osadchy, M., & Morash, E. (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.2008.4587601 · Cited by 1
“The winners of the classification part of the competition (depending on the category) were different variations of bagof-features representations that discard shape information (QMUL-HSLS [4], INRIA-NOWAK [ 17 ], XRCE [19]), and the best average performance was shown by QMUL-LSPCH[4], whichapplies a two-layer SVM clas…”
BackgroundMethodInfluentialModeling context for image understanding: When, for what, and how?
Parikh, D. (2009) · Cited by 1
Conceptual Image Retrieval over the Wikipedia Corpus.
Popescu, A., Borgne, H. L., & Moëllic, P.-A. (2008) · Cited by 1
Dynamicity and Durability in Scalable Visual Instance SearchPreprint
Lejsek, H., Jónsson, B. Þ., Amsaleg, L., & Ásmundsson, F. H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.10942 · Cited by 1
“Extracting powerful local features from images has been widely studied and many strategies exist to determine (i) where local features should be extracted in images ([42, 48]), and (ii) what information each local feature should encode ([43, 1, 7]).”
BackgroundMethodAutomatic Handgun Detection in X-ray Images using Bag of Words Model with Selective SearchPreprint
Piñol, D. C., & Reyes, E. J. M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.01322 · Cited by 1
“Como también se ha reportado un incremento en la precisión de la clasificación a mayor cantidad de puntos extraídos [27] [28].”
BackgroundThe CUDA LATCH Binary Descriptor: Because Sometimes Faster Means BetterPreprint
Parker, C., Daiter, M., Omar, K., Levi, G., & Hassner, T. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.03986 · Cited by 1
Mathuria, A., & Hammerstrom, D. W. (2019) · International Conference on Neuromorphic Systems (ICONS) · doi:10.1145/3354265.3354286 · Cited by 1
“However, due to the complexity of working with graphs, traditional Computer Vision techniques mostly use a ”bag of features” [27], [28] approach and so are missing information on object structure.”
MethodEffective Utilization of Whitening for Person IdentificationPreprint
Vinay, A., Kailasam, S., Bharadwaj, A., Murthy, K. N. B., & Natarajan, S. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3356197 · Cited by 1
Mathuria, A. (2000) · doi:10.15760/etd.7453 · Cited by 1
Saikia, S. (2021) · Buleria (Universidad de León) · doi:10.18002/10612/15059 · Cited by 1
Graph Mining and Graph Classification : application to cadastral map analysis
Raveaux, R. (2010) · theses.fr (ABES) · doi:10.70675/4c5b9ac8za52az4f9ez93d2zc0ae80dfd3e3 · Cited by 1
Quality of variant and invariant features
Burghouts, G. J. (2007) · TNO Repository · Cited by 1
Hoedt, A. M. D. (2013) · doi:10.17077/etd.4bcwhpmp · Cited by 3
“Using this technique, image feature vectors are expressed by a histogram of the occurrences of representative descriptors within the image [21].”
MethodLocal Regularization for Multiclass Classification Facing Significant Intraclass Variations
Wolf, L., & Donner, Y. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88693-8_55 · Cited by 1
“Keypoints are selected at random locations [20].”
Web Image Gathering with a Part-Based Object Recognition Method
Yanai, . (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-77409-9_28
“Many researches [1, 6 ] show the SIFT descriptor is the best as representation of image patches for object recognition.”
BackgroundMethodResultInfluentialDescritor de bordas e quantização espacial flexível aplicados a categorização de objetos
Lara, A. C. (2013) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.45.2013.tde-29042013-111855
TOWARDS INTENT DEPENDENT IMAGE ENHANCEMENT - State-of-the-art and Recent Attempts
Bressan, M., Csurka, G., & Favre, S. (2007) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0002068202080218
“…obtained by image segmentation as above, by applying specific interest point detectors (Csurka et al., 2004; Quelhas et al., 2005), by considering a regular grid (Carbonetto et al., 2004; Fei-Fei and Perona, 2005) or simply random sampling of image patches (Marée et al., 2005; Novak et al., 2006).”
BackgroundMethod
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.