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 501–600 of 925
Long Term Activity Analysis in Surveillance Video Archives
Chen, M. (2010) · ProQuest LLC eBooks · Cited by 7
The CUDA LATCH Binary Descriptor: Because Sometimes Faster Means Better
Parker, C., Daiter, M., Omar, K., Levi, G., & Hassner, T. (2016) · ECCV Workshops · doi:10.1007/978-3-319-49409-8_57 · Cited by 7
GriMa: A Grid Mining Algorithm for Bag-of-Grid-Based Classification
Deville, R., Fromont, É., Jeudy, B., & Solnon, C. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-49055-7_12 · Cited by 8
“However, [16] has shown that randomly sampling patches on grids (called dense sampling) gave as good (and often better) results for image classification than when using complex detectors.”
ResultLandmark-Based Alzheimer’s Disease Diagnosis Using Longitudinal Structural MR Images
Zhang, J., Liu, M., An, L., Gao, Y., & Shen, D. G. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-61188-4_4 · Cited by 9
Scalable scene understanding via saliency consensus
Ramesh, B., Jian, N. L. Z., Chen, L., Xiang, C., & Gao, Z. Y. (2017) · Soft Computing · doi:10.1007/s00500-017-2939-2 · Cited by 7
“As many previous works have observed (Nowak et al. 2006; Vedaldi et al. 2009), higher codebook sizes can lead to better classification performance, however, at the cost of increasing computational time.”
BackgroundInfluentialLocal Patch Vectors Encoded by Fisher Vectors for Image Classification
Chen, S., Liu, H., Zeng, X., Qian, S., Wei, W., Wu, G., & Duan, B. (2018) · Information · doi:10.3390/info9020038 · Cited by 7
Content-Sensitive Multilevel Point Cluster Construction for ALS Point Cloud Classification
Xu, Z., Zhang, Z., Zhong, R., Chen, D., Sun, T., Deng, X., Li, Z., & Qin, C. (2019) · Remote Sensing · doi:10.3390/rs11030342 · Cited by 7
“In image processing, the BoW method [43] is generally used to quantize each extracted key point into words, then the image is represented by the histogram of the words to obtain a high level of classification or recognition effect.”
MethodScene Classification using Generalized Local Correlation
Nakayama, H., Harada, T., & Kuniyoshi, Y. (2009) · Cited by 7
An Images-Textual Hybrid Recommender System for Vacation Rental
Ng, P. C., She, J. P. M., Cheung, M., & Cebulla, A. (2016) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm.2016.71 · Cited by 7
Cloth pattern recognition with four features (RSSM)
Rao, N. D. P., Sudhavani, G., Balakrishna, P., & Gouthami, K. (2015) · International Symposium on Advanced Computing and Communication (ISACC) · doi:10.1109/isacc.2015.7377315 · Cited by 7
Tripathi, V., Gangodkar, D., Mittal, A., & Kanth, V. (2017) · Procedia Computer Science · doi:10.1016/j.procs.2017.09.094 · Cited by 8
Semi-supervised learning of visual classifiers from web images and text
Morsillo, N., Pal, C., & Nelson, R. C. (2009) · International Joint Conference on Artificial Intelligence · Cited by 6
Automated Classification of Glandular Tissue by Statistical Proximity Sampling
Azar, J. C., Simonsson, M., Bengtsson, E. W., & Hast, A. (2015) · International Journal of Biomedical Imaging · doi:10.1155/2015/943104 · Cited by 6
“As opposed to most local neighborhood sampling or bag of features methods that either are patch-based or result in orderless, histogram-based features [10, 11], the method we propose does the sampling around a given (lumen) region as opposed to a pixel, while preserving the region’s boundary shape and encoding spatial…”
BackgroundMagalhães, F., Sousa, R., Araujo, F. M. M., & Correia, M. V. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39094-4_87 · Cited by 6
“After the construction of the descriptor, an unsupervised technique is employed to construct the vocabulary that will represent our dataset, which is then concluded by a state-of-the-art bag-of-features technique [11].”
MethodMachine Identification of High Impact Research through Text and Image Analysis
Stamenovic, M., Schick, S., & Luo, J. (2017) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm.2017.63 · Cited by 6
“We chose to use SIFT features to represent the images due to their demonstrated success in similar classification tasks in the literature [4], [18], [26], [30].”
MethodHuman interaction recognition based on sparse representation of feature covariance matrices
Wang, J., Zhou, S.-C., & Xia, L. (2018) · Journal of Central South University · doi:10.1007/s11771-018-3738-3 · Cited by 6
Akula, A., Ghosh, R., Guleria, N., Kumar, S., & Sardana, H. (2018) · Optical Engineering + Applications · doi:10.1117/12.2502154 · Cited by 1
“Nowak et al [27] have shown that number of regions sampled in an image is the most important factor for achieving better classification and thereby indicating dense sampling to be the best strategy.”
BackgroundImage Classification Using Probability Higher-Order Local Auto-Correlations
Matsukawa, T., & Kurita, T. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-12297-2_37 · Cited by 6
“Some of these methods are spatial pyramid binning to utilize location informations [7], higher level codebook creation based on local co-occurrence of codebooks [1][13][18], improvement of codebook creation[9][10][11] and region of interest based matching [14].”
MethodA Hamming Embedding Kernel with Informative Bag-of-Visual Words for Video Semantic Indexing
Wang, F., Zhao, W., Ngo, C., & Mérialdo, B. (2014) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/2535938 · Cited by 6
“A lot of efforts have been devoted to improve the performance of BoW features [Nowak et al. 2006; Quelhas et al. 2007; Sudderth et al. 2008; Tuytelaars and Schmid 2007; Winn et al. 2005; Batra et al. 2008; Jurie and Triggs 2005; Fulkerson et al. 2008; Yang et al. 2008; Alhwarin et al. 2008].”
BackgroundExploring the optimal visual vocabulary sizes for semantic concept detection
Guo, J., Qiu, Z., & Gurrin, C. G. (2013) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2013.6576565 · Cited by 7
Categorization of Multiple Objects in a Scene Using a Biased Sampling Strategy
Yang, L., Zheng, N., Chen, M., Yang, Y., & Yang, J. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0629-9 · Cited by 6
“Among these frameworks, binary 1vsAll support vector machine classifiers are commonly adopted in BoF based object categorization systems (Nowak et al. 2006; Zhang et al. 2007; Everingham et al. 2007).”
BackgroundMethodInfluentialFast Cross-Scenario Clothing Retrieval Based on Indexing Deep Features
Li, Z., Li, Y., Gao, Y., & Liu, Y. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-48890-5_11 · Cited by 6
Unseen object categorization using multiple visual cues
Ramesh, B., & Xiang, C. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.12.003 · Cited by 5
Narang, N., & Bourlai, T. (2017) · Advanced sciences and technologies for security applications · doi:10.1007/978-3-319-68533-5_7 · Cited by 6
Rahimi, S., Aghagolzadeh, A., & Ezoji, M. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.112927 · Cited by 6
France, K., & Jaya, A. (2019) · Biomedical Physics & Engineering Express · doi:10.1088/2057-1976/ab5c7c · Cited by 6
Combined cosine-linear regression model similarity with application to handwritten word spotting
Elfakir, Y., Khaissidi, G., Mrabti, M., Chenouni, D., & Boualam, M. (2020) · International Journal of Electrical and Computer Engineering (IJECE) · doi:10.11591/ijece.v10i3.pp2367-2374 · Cited by 6
“In the end, we encoding each region by a histogram using a bag-of-visual-descriptors [18, 19] instead to represent them by their descriptors.”
MethodSupervised High-Level Feature Learning With Label Consistencies for Object Recognition
Wang, Y., Zhou, X., Yang, H., Zhang, L., Liu, S., Wang, F., Li, X., & Mathiopoulos, P. T. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2955557 · Cited by 6
“tures such as scale-invariant feature transformation (SIFT) [5] and histograms of oriented gradients (HOGs) [6], and middlelevel features such as bag-of-words (BoW) [7], [8].”
BackgroundAvni, U., Goldberger, J., & Greenspan, H. K. (2008) · CLEF (Working Notes) · Cited by 6
Optical flow for dynamic facial expression recognition.
Psaltis, A. (2013) · Utrecht University Repository (Utrecht University) · Cited by 6
Ren, Q., Wang, Q., Zhang, J., & Chen, S. (2016) · World Congress on Intelligent Control and Automation · doi:10.1109/wcica.2016.7578428 · Cited by 5
“A probability of a customer sitting at the new table is proportional to γ, and a probability of customer sitting at table k is proportional to the number of customers sitting at the table k.”
BackgroundMarkov Network-Based Unified Classifier for Face Recognition
Hwang, W., & Kim, J. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2460464 · Cited by 5
Representative selection based on sparse modeling
Wang, Y., Tang, S., Zhang, Y., Li, J., & Wang, D. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.02.013 · Cited by 5
Bai, S., Matsumoto, T., Takeuchi, Y., Kudo, H., & Ohnishi, N. (2013) · Machine Vision and Applications · doi:10.1007/s00138-012-0473-x · Cited by 5
“Later, the work in [11] showed that performance of randomly sampled patches can outperform interest point detectors in image categorization, when the number of sampled patches is large enough.”
BackgroundMethodSpeeding up multi-class texture classification by one-pass vocabulary design and decision tree
Ramanan, A., Ranganathan, P., & Niranjan, M. (2011) · IEEE International Conference on Industrial and Information Systems (ICIIS) · doi:10.1109/iciinfs.2011.6038076 · Cited by 5
Towards Robust Object Categorization for Mobile Robots with Combination of Classifiers
Mueller, C. A., Hochgeschwender, N., & Ploeger, P. G. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-32060-6_12 · Cited by 5
“In many approaches[1, 8, 5] the entire image is examined as a single entity.”
BackgroundMethodInfluentialExtended Laplacian Sparse Coding for Image Categorization
Dammak, M., Mejdoub, M., & Amar, C. B. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-12643-2_36 · Cited by 5
Improving Tracking Algorithms Using Saliency
Undurraga, C., & Mery, D. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-25085-9_16 · Cited by 5
“It can be done by: points of interest, descriptors with relevant information [9]; bags of words, areas that define the object [10]; features of a region, variance of the features of the region [11]; local appearence, attention operators based on symetry [7]; among others.”
BackgroundAutomatic ventricle detection in Computed Tomography Pulmonary Angiography
Rodríguez-López, S., Jiménez‐Carretero, D., Estépar, R. S. J., Moreno, E. F., Kumamaru, K. K., Rybicki, F. J., Ledesma‐Carbayo, M. J., & González, G. (2015) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2015.7164074 · Cited by 5
“vision, with techniques that range from simple models, such as rigid templates [3] and bag-of-features [4], to richer models such as pictorial structures [5].”
MethodImage Categorization Using Scene-Context Scale Based on Random Forests
Kang, Y., Nagahashi, H., & Sugimoto, A. (2011) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e94.d.1809 · Cited by 5
Visual Saliency Based on Local and Global Features in the Spatial Domain
Jia, C., Fang, H. X., & Duan, L. (2013) · Cited by 5
Mouton, A., & Breckon, T. P. (2018) · Journal of X-Ray Science and Technology · doi:10.3233/xst-180411 · Cited by 6
“Secondly, we present a codebook 3D object classification approach based on Extremely Randomised Clustering (ERC) forests [32], a dense feature sampling strategy [33] and an Support Vector Machine (SVM) classifier [34] (Section 1).”
Saleem, A., Awange, J. L., & Corner, R. J. (2020) · International Journal of Remote Sensing · doi:10.1080/01431161.2020.1820617 · Cited by 5
PCAH: A PCA-Based Hierarchical Clustering Method for Visual Words Construction
He, Y., Wang, J., Zhong, X., Mei, L., & Wu, Z. (2015) · IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) · doi:10.1109/ccgrid.2015.33 · Cited by 5
“At present, the methods generating the visual words can be mainly divided in two kinds: one kind is the manual annotation method which is adopted by Vogel [15]; and the other are unsupervised clustering methods [16].”
MethodNew approach for automatic medical image annotation using the bag-of-words model
Bouslimi, R., & Akaichi, J. (2015) · IEEE International Conference on Software Engineering and Service Science (ICSESS) · doi:10.1109/icsess.2015.7339241 · Cited by 5
“Many studies related to images categorization showed that the detection of regular points of interest gives the best results, especially when the vocabulary size is important [14]; [19]; we think that is the case of medical images which are characterized by a rich visual vocabulary.”
BackgroundMethodInfluentialWeighted-learning-instance-based retrieval model using instance distance
Wu, H., Li, Y., Xiong, J., Bi, X., Zhang, L., Bie, R., & Guo, J. (2018) · Machine Vision and Applications · doi:10.1007/s00138-018-0988-x · Cited by 6
“Baseline 7: sampling-based Bow model [76]”
MethodInfluentialAutomatic system recognition of Lebanese license plates
Akoum, A. H., Daya, B., & Chauvet, P. E. (2010) · International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA) · doi:10.1109/bicta.2010.5645286 · Cited by 5
“Jurie, Nowak and Triggs [2, 3, 4 ] propose the creation of visual vocabulary for objects recognition.”
BackgroundVideo face matching using subset selection and clustering of probabilistic Multi-Region Histograms
Mau, S., Shaokang Chen, A., Sanderson, C., & Lovell, B. C. (2010) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2010.6148860 · Cited by 5
“The MRH approach is motivated by the concept of ‘visual words’ (originally used in image categorisation [15]) as well as the semi-loose spatial constraints between face parts in 2D Hidden Markov Models [2].”
MethodMESH participation to TRECVID2008 HLFE
Molina, J. M. M., Mezaris, V., Villegas, P., Tolias, G., Spyrou, E., Sofou, N., Rodríguez-Benito, J., Papadopoulos, G. T., Nikolopoulos, S., Martínez-Gil, J., et al. (2008) · Cited by 5
Alqasrawi, Y., Neagu, D. C., & Cowling, P. (2009) · International Conference on Intelligent Systems Design and Applications (ISDA) · doi:10.1109/isda.2009.134 · Cited by 5
“In recent years, local invariant features or local semantic concepts [11] and the bag of visual patches (BOP) became very popular in computer vision field and have shown impressive levels of performance in scene image classification task [4,5,9, 12-15].”
BackgroundFace and texture image analysis with quantized filter response statistics
Ahonen, T. (2009) · Cited by 6
Scene Categorization from Tiny Images
Wendel, A., & Pinz, A. J. (2007) · Cited by 5
Non‐Stationary Grey Texture Images
Petrou, M., & Garcı́a-Sevilla, P. (2006) · Wiley eBooks · doi:10.1002/047003534x.ch4 · Cited by 5
Cao, R., Yang, F., Ma, S.-C., Liu, L., Li, Y., Wu, D., Zhao, Y., Wang, T., Lu, W., Cai, W.-J., et al. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.02.29.971150 · Cited by 5
M-SBIR: An Improved Sketch-Based Image Retrieval Method Using Visual Word Mapping
Niu, J., Ma, J., Lu, J., Liu, X., & Zhu, Z. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-51814-5_22 · Cited by 4
Multimedia fog computing: minions in the cloud and crowd
Hsu, C.-H., Hong, H.-J., Elgamal, T., Nahrstedt, K., & Venkatasubramanian, N. (2017) · doi:10.1145/3122865.3122876 · Cited by 4
Singh, A. K., Kumar, R., & Tripathi, R. P. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-981-13-0589-4_6 · Cited by 4
Chebbout, S., & Merouani, H. F. (2020) · International Journal of Computers and Applications · doi:10.1080/1206212x.2020.1712775 · Cited by 4
“Following a data-driven based approach, several authors [5,6,12,26,27] used the k -means clustering algorithm (KM) to learn a set of cluster centers from the feature space.”
BackgroundMethodA Dense SURF and Triangulation Based Spatio-temporal Feature for Action Recognition
Nga, D. H., & Yanai, . (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-04114-8_32 · Cited by 4
Lu, Z., & Peng, Y. (2011) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2072298.2072027 · Cited by 4
“A distinct disadvantage of BOF is that it may suffer from the redundancy of mid-level features, since typically thousands of visual keywords are generated to obtain better performance on a relatively large image dataset [9].”
BackgroundNovel local features with hybrid sampling technique for image retrieval
Kaliciak, L., Song, D., Wiratunga, N., & Pan, J. Z. (2010) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/1871437.1871671 · Cited by 4
“Nowak and others ([7]) compare different sampling techniques (corner detectors, random sampling, dense sampling).”
BackgroundContent-Based Image Retrieval in P2P Networks with Bag-of-Features
Zhang, L., Wang, Z., & Feng, D. D. (2012) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew.2012.30 · Cited by 4
“The decision is based on the fact that sampled centroids are able to achieve a comparable performance to centroids produced by clustering [9] with much lower computation cost and network cost.”
BackgroundReturn of the king: The Fourier transform based descriptor for visual object classification
Çevıkalp, H., Kurt, Z., & Onarcan, A. O. (2013) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2013.6531160 · Cited by 4
“Patches are typically sampled from the image at many different positions and scales, either densely [3,6], randomly [5], based on the output of some kind of salient region detector [1,20], or based on the output of segmentation algorithms [7,8].”
BackgroundA framework for semantic analysis of histopathological images using nonnegative matrix factorization
Roa, Á. A. C., Díaz, G. M., & Gonzalez, F. A. (2011) · Computing Colombian Conference · doi:10.1109/colomcc.2011.5936285 · Cited by 3
“[22] have reported that the application of a clustering algorithm has not a big impact in the classification of natural images, compared with a random selection of codewords, hence an exhaustive experimentation”
MethodBoundary Preserving Dense Local Regions
Kim, J., & Grauman, K. L. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2360689 · Cited by 5
“Finally, we extract a dense set of overlapping regions, each of which consists of a group of linked (neighboring) elements within the tree.”
BackgroundMethodKawakubo, H., & Yanai, . (2009) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2009.5202835 · Cited by 4
“Sample 3000 patches per image randomly in the same way as [6].”
BackgroundFusing Global and Local Scale for Semantic Image Segmentation
Boix, X., Gonfaus, J. M., van de Weijer, J., Bagdanov, A. D., Serrat, J., & Gonzàlez, J. (2011) · Cited by 4
3D spatial pyramid: descriptors generation from point clouds for indoor scene classification
Romero-González, C., Martínez-Gómez, J., García-Varea, I., & Rodríguez-Ruiz, L. (2016) · Machine Vision and Applications · doi:10.1007/s00138-015-0744-4 · Cited by 4
“A major contribution in the field of image descriptors was the adoption of the Bag ofWords (BoW) technique [12,15,33], which allows to generate a global descriptor from any type of local feature.”
MethodEnsemble Methods for Robust 3D Face Recognition Using Commodity Depth Sensors
Schimbinschi, F., Schomaker, L., & Wiering, M. (2015) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci.2015.36 · Cited by 5
A VHR scene classification method integrating sparse PCA and saliency computing
Chaib, S., Gu, Y., Yao, H., & Zhao, S. (2016) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2016.7729708 · Cited by 4
Stacked Overcomplete Independent Component Analysis for Action Recognition
Liu, Z., Tian, Y., & Wang, Z. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-54184-6_23 · Cited by 4
Hannat, M., Zrira, N., Raoui, Y., & Bouyakhf, E. H. (2016) · doi:10.1109/icmcs.2016.7905537 · Cited by 4
Action Recognition by Jointly Using Video Proposal and Trajectory
Qi, L., Lu, X., & Li, X. (2018) · International Conference on Vision, Image and Signal Processing (ICVISP) · doi:10.1145/3271553.3271563 · Cited by 4
“For example, inspired by the idea of local descriptors computed in a 3D video volume around interest points [10], the DT ( Dense trajectories ) and iDT improved dense trajectories methods compute the HOG, HOF and MBH feature of video volumes around the extracted trajectories.”
MethodEnsemble of Handcrafted and Deep Learned Features for Cervical Cell Classification
Nanni, L., Ghidoni, S., Brahnam, S., Liu, S., & Zhang, L. (2020) · Intelligent systems reference library · doi:10.1007/978-3-030-42750-4_4 · Cited by 8
Chen, K.-T., Cai, W., Shea, R., Huang, C., Liu, J., Leung, V. C. M., & Hsu, C.-H. (2017) · doi:10.1145/3122865.3122877 · Cited by 7
Anomaly detection using local regions in road images acquired from a hand-held camera
Kamitani, T., Fujimoto, S., Yoshimura, H., Nishiyama, M., & Iwai, Y. (2018) · IEEE Global Conference on Consumer Electronics (GCCE) · doi:10.1109/gcce.2018.8574660 · Cited by 4
“As described in [14], a grid sampling technique divides the reference image using equal intervals and defines a local region around each intersection.”
BackgroundImage classification with ant colony based support vector machine
Zhao, B., & Qi, Y. (2011) · Cited by 4
Learning with Few Examples using a Constrained Gaussian Prior on Randomized Trees.
Rodner, E., & Denzler, J. (2008) · Vision Modeling and Visualization · Cited by 5
Systematic bone infection detection in axial diabetic foot MRI
Maftouni, M., Turksen, I. B., Zarandi, M. H. F., & Yazdi, N. A. (2015) · IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB) · doi:10.1109/cibcb.2015.7300276 · Cited by 4
“The midfoot bones are less commonly involved unless foot deformity (from neuropathic osteoarthropathy, for example) has caused ulceration [7].”
From text vocabularies to visual vocabularies: what basis?
Martinet, J. (2014) · HAL · Cited by 4
Semantic lattices for multiple annotation of images
Tousch, A.-M., Herbin, S., & Audibert, J.-Y. (2008) · Multimedia Information Retrieval · doi:10.1145/1460096.1460152 · Cited by 7
Dense Sampling Low-Level Statistics of Local Features
Nakayama, H., Harada, T., & Kuniyoshi, Y. (2010) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e93.d.1727 · Cited by 5
Categorization of Multiple Objects in a Scene without Semantic Segmentation
Yang, L., Zheng, N., Chen, M., Yang, Y., & Yang, J. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-12307-8_28 · Cited by 4
“In the classical multi-class setting, a group of binary classifiers are trained in either one-vs-all or one-vs-one manner [2, 11 ].”
BackgroundMethodInfluentialLiu, X., Shi, Z., & Shi, Z. (2013) · The Visual Computer · doi:10.1007/s00371-012-0772-2 · Cited by 4
“Several works [10, 14, 18, 22, 23] have shown that a number of well-defined object categories can be learned well.”
BackgroundA novel video dehazing method based on temporal visual coherence
Xiang, X., Cheng, Y. J., & Tang, J. (2015) · International Conference on Internet Multimedia Computing and Service · doi:10.1145/2808492.2808528 · Cited by 4
“…University of Science and Technology Nanjing, 210094, P.R. China 086-25-84315635 ycheng@mail.njust.edu.cn Jinhui Tang School of computer science and engineering, Nanjing University of Science and Technology Nanjing, 210094, P.R. China 086-25-84315635 jhtang@mail.njust.edu.cn ABSTRACT In…”
BackgroundCategory Constrained Learning Model for Scene Classification
Tang, Y., Xu, D., Gu, G., & Liu, C. (2009) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e92.d.357 · Cited by 4
“Pioneering work [2]–[5] used it to match particular scene.”
BackgroundMeta-classifiers for multimodal document classification
Chen, S. D., Monga, V., & Moulin, P. (2009) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2009.5293343 · Cited by 5
“To remove them, two main techniques are used.”
BackgroundMethodCombining Visual and Textual Systems within the Context of User Feedback
Kaliciak, L., Song, D., Wiratunga, N., & Pan, J. Z. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-35725-1_41 · Cited by 4
Selective features for RGB-D saliency
Zhu, L., Cao, Z., Fang, Z., Xiao, Y., Wu, J., Deng, H., & Liu, J. (2015) · Chinese Automation Congress · doi:10.1109/cac.2015.7382554 · Cited by 4
Clothing Color and Pattern Recognition for Impaired people
Mrs. Anuradha., S. G., & Ashwini, T. (2016) · International Journal Of Engineering And Computer Science · doi:10.18535/ijecs/v5i4.51 · Cited by 4
Performance Comparison of Image Classifier using Discrete Cosine Transform and Walsh Transform
Sarode, T., & Ugale, M. (2011) · Cited by 4
Roy, A., Banerjee, B., & Murino, V. (2017) · International Conference on Pattern Recognition Applications and Methods · doi:10.5220/0006200205190526 · Cited by 5
“Effective sampling strategies for the BoW model is the focus of discussion in (Nowak et al., 2006) where several aspects including the codebook size, clustering techniques adopted etc.”
BackgroundSpatio-Temporal Scale Coded Bag-of-Words
Govender, D., & Tapamo, J. (2020) · Sensors · doi:10.3390/s20216380 · Cited by 4
“Scovanner et al. [17] extended Scale-Invariant Feature Transforms (SIFT) [18,19] to form the 3D-SIFT descriptor for classification of video data represented by the BoW approach.”
MethodInfluentialImage classification based on support vector machine and the fusion of complementary featuresPreprint
Gao, H., Chen, W., & Dou, L. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.01706 · Cited by 4
Imaging and Classification Techniques for Seagrass Mapping and Monitoring: A Comprehensive Survey.Preprint
Moniruzzaman, M., Islam, S. M. S., Lavery, P. S., Bennamoun, M., & Lam, C. P. (2019) · arXiv (Cornell University) · Cited by 4
Salience based hierarchical fuzzy representation for object recognition
Yang, L., Hu, Q., Zhao, L., & Li, Y. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351733 · Cited by 3
“We show that our approach outperforms the traditional BOVW and weighted BOVW.”
BackgroundInfluentialScalable Face Retrieval by Simple Classifiers and Voting Scheme
Utsumi, Y., Sakano, Y., Maekawa, K., Iwamura, M., & Kise, K. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-13737-7_9 · Cited by 3
“In object retrieval, some scalable methods based on the Bag-of-Features (BoF) model have already proposed [3,14,20].”
MethodOn the Spatial Extents of SIFT Descriptors for Visual Concept Detection
Mühling, M., Ewerth, R., & Freisleben, B. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23968-7_8 · Cited by 3
Weighted Symbols-Based Edit Distance for String-Structured Image Classification
Barat, C., Ducottet, C., Fromont, É., Legrand, A.-C., & Sebban, M. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15880-3_11 · Cited by 3
“Each word can be weighted either according to its frequency in the image, or using more sophisticated techniques such as mutual-information-based binarization (9) or TF-IDF-based weighting (Term Frequency-Inverse Document Frequency) (10; 11).”
BackgroundMethodRobust Tracking Based on Pixel-Wise Spatial Pyramid and Biased Fusion
Lu, H., Lu, S., & Chen, Y. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19282-1_14 · Cited by 3
“Bag of words (bag of features) [15, 16 ] representations have become popular for content based image classification and object localization owing to their simplicity and good performance.”
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.