Ensemble of exemplar-SVMs for object detection and beyond
Open accessThe DOI matches its Crossref record; 23 of the 25 references it cites were found in a registry or an index.
Abstract
This paper proposes a conceptually simple but surprisingly powerful method which combines the effectiveness of a discriminative object detector with the explicit correspondence offered by a nearest-neighbor approach. The method is based on training a separate linear SVM classifier for every exemplar in the training set. Each of these Exemplar-SVMs is thus defined by a single positive instance and millions of negatives. While each detector is quite specific to its exemplar, we empirically observe that an ensemble of such Exemplar-SVMs offers surprisingly good generalization. Our performance on the PASCAL VOC detection task is on par with the much more complex latent part-based model of Felzenszwalb et al., at only a modest computational cost increase. But the central benefit of our approach is that it creates an explicit association between each detection and a single training exemplar. Because most detections show good alignment to their associated exemplar, it is possible to transfer any available exemplar meta-data (segmentation, geometric structure, 3D model, etc.) directly onto the detections, which can then be used as part of overall scene understanding.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures


![Figure 3 Comparison. Given a bicycle training sample from PASCAL (represented with a HOG weight vector w ), we show the top 6 matches from the PASCAL test-set using three methods. Row 1: naive nearest neighbor (using raw normalized HOG). Row 2: Trained Exemplar-SVM (notice how w focuses on bike-specific edges). Row 3: Learned distance function - an Exemplar-SVM but trained in the 'distance-to-exemplar' vector space, with the exemplar being placed at the origin (loosely corresponding to [10, 14]).](https://figures.cochat.ai/paper-figures/1cc4b956c3534a219577db00fbbb8da4/ensemble-of-exemplar-svms-for-object-detection-and-beyond-figure-3.png)







Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
“In the case of sliding-window object detectors, such as the deformable parts model (DPM) [12], this imbalance may be as extreme as 100,000 background examples to every one object.The recent trend towards object-proposal-based detectors [15,32] mitigates this issue to an extent, but the imbalance ratio may still be high (e.g., 70:1).”
From Training Region-Based Object Detectors with Online Hard Example Mining (2016) · cites this paper as [32]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918 · cited 1×
“Using the procedure above, we train an ensemble of Exemplar-SVM, one for each positive instance in the training set.”
MethodHistograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · cited 2×
“Yet today, a number of methods can do just that with reasonable accuracy.”
BackgroundThe pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599 · cited 2×
“For our experiments, we use a single source of exemplars: the PASCAL VOC 2007 dataset [8] – a popular dataset used to benchmark object detection algorithms.”
BackgroundMethodLibsvm : A library for support vector machines
Ferrari, V. (2008) · Medical Entomology and Zoology · Cited by 10,122
Object Detection with Discriminatively Trained Part-Based Models
Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.167 · Cited by 9,853 · cited 4×
“For this, we present results on a set of tasks including segmentation, qualitative-geometry estimation, 3D model transfer, and related object priming.”
BackgroundMethodInfluentialProbabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods
Platt, J. C. (1999) · Cited by 6,384
Shape matching and object recognition using shape contexts
Belongie, S., Malik, J., & Puzicha, J. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.993558 · Cited by 6,306 · cited 1×
“Because most detections show good alignment to their associated exemplar, it is possible to transfer any available exemplar meta-data (segmentation, geometric structure, 3D model, etc.) directly onto the detections, which can then be used as part of overall scene understanding.”
BackgroundEstimating the Support of a High-Dimensional Distribution
Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., & Williamson, R. C. (2001) · Neural Computation · doi:10.1162/089976601750264965 · Cited by 6,168
SUN database: Large-scale scene recognition from abbey to zoo
Xiao, J., Hays, J., Ehinger, K. A., Oliva, A., & Torralba, A. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539970 · Cited by 3,283 · cited 1×
“Because most detections show good alignment to their associated exemplar, it is possible to transfer any available exemplar meta-data (segmentation, geometric structure, 3D model, etc.) directly onto the detections, which can then be used as part of overall scene understanding.”
Background80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition
Torralba, A., Fergus, R., & Freeman, W. T. (2008) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.128 · Cited by 1,921
Research works printed but not linked: 1
- A. Frome and J. Malik. Image retrieval and recognition using local distance functions. NIPS, 2006. 2, 3, 4
Cited by
Items 801–873 of 873
Latent Hinge-Minimax Risk Minimization for Inference from a Small Number of Training SamplesPreprint
Raviv, D., & Osadchy, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.01293
“suming [18]), it relies heavily on the results of the clustering.”
BackgroundAction recognition with prototypes
Yalçınkaya, Ö., & Duygulu, P. (2017) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2017.7960314
An Efficient Word Recognition System Based on Effective Classification Method
Bharat, K. P., & Holambe, A. N. (2017) · International journal of advance research and innovative ideas in education
Visual Self-localization via Inferring View-to-Map Correspondences
Xu, Q., & Liu, X. (2017) · doi:10.1145/3132734.3132740
“As shown in [17], the optimal model parameterφ(hq ) has the following analytic form,”
BackgroundScene Parsing with Deep Features and Per-Exemplar Detectors
Cui, X., Qu, H., Chen, X., Qi, Z., & Dong, L. (2017) · Lecture notes in electrical engineering · doi:10.1007/978-981-10-6445-6_40
Multi-context Deep Convolutional Features and Exemplar-SVMs for Scene Parsing
Cui, X., Qu, H., Wang, S., Dong, L., & Qi, Z. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-7299-4_41
Face recognition in video surveillance from a single reference sample through domain adaptation
Bashbaghi, S. (2017) · Espace ÉTS (ETS)
Learning to focus for object proposals
Chen, Z., You, X., & Li, J. (2017) · International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) · doi:10.1109/spac.2017.8304319
“In order to improve the performance of a detector, numerous research efforts on the features [2], [11], classifiers [4], [12] and other effective schemes [13], [14].”
BackgroundVisual Vehicle Localization System for Smart Parking Application
Lahdili, H., & Ismaili, Z. E. A. A. (2018) · Lecture notes in networks and systems · doi:10.1007/978-3-319-74500-8_34
Week texture objects pose estimation based on 3D model
Chen, Y., Zhang, H., Tian, S., & Gao, C. (2018) · International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR) · doi:10.1117/12.2284972
“took advantage of 3D model to enrich object detection, using the method of the exemplar SVM.(1) Continuous viewpoint images were generated”
MethodInfluentialTask-related Item-Name Discovery Using Text and Image Data from the Internet
Thaipumi, P., & Hasegawa, O. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-78452-6_6
Instance Image Retrieval by Aggregating Sample-based Discriminative Characteristics
Zhang, Z., Wang, L., Wang, Y., Zhou, L., Zhang, J., & Chen, F. (2018) · International Conference on Multimedia Retrieval · doi:10.1145/3206025.3206069
“As verified in [16], each Exemplar-SVM weight vector can be used for similarity measure when the corresponding exemplar is regarded as a query.”
BackgroundMethodInfluentialFusion of Compound Queries with Multiple Modalities for Known Item Video Search
Gialampoukidis, I., Moumtzidou, A., Vrochidis, S., & Kompatsiaris, I. Y. (2018) · Multidimensional Signal Processing Workshop · doi:10.1109/ivmspw.2018.8448876
“A supervised late fusion approach is the Exemplar SVM (MQ-ESVM), which has originated in [5], that trains a separate linear SVM for each positive example and the final score is the maximal score.”
BackgroundNearest-Instance-Centroid-Estimation Linear Discriminant Analysis (Nice Lda)
Singh, R., Li, K., & Príncipe, J. C. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8461584 · Cited by 1
Predictive Ensemble Learning with Application to Scene Text DetectionPreprint
Chen, D., Zhang, X.-Y., Zhang, W., Lu, Y., Li, X., & Mei, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.04641
“[Malisiewicz et al., 2011] applies ensemble of exemplar-SVMs for object detection.”
BackgroundFine-Grained Label Learning via Siamese Network for Cross-modal Information Retrieval
Xu, Y., Yu, J., Guo, J., Hu, Y., & Tan, J. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-22741-8_22
“Hard examples analysis can help classification tasks and retrieval tasks obtain better results [1,3,11,24].”
BackgroundEfficient Media Retrieval from Non-Cooperative QueriesPreprint
Shih, K. J., Wei, D., Jagadeesh, V., & Piramuthu, R. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1411.5307
“While there is little that can be done about the shortcomings of RANSAC, it is likely that replacing the HOG filters with an exemplar detector such as with [9] or [5] could rectify the latter issue.”
BackgroundJoint calibration of Ensemble of Exemplar SVMsPreprint
Modolo, D., Vezhnevets, A. S., Russakovsky, O., & Ferrari, V. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1503.00783
Zunker, R. R., Sinha, A., & Banerji, S. (2019) · International Conference on Computing and Data Engineering (ICCDE) · doi:10.1145/3330530.3330549
Research and Implementation of Anti-occlusion Algorithm for Vehicle Detection in Video Data
Wu, Y., Zhou, Z., Yao, L., Yu, M., & Yan, Y. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30952-7_26
Efficient Deep Representation Learning by Adaptive Latent Space SamplingPreprint
Mo, Y., Wang, S., Dai, C., Zhou, R., Teng, Z., Bai, W., & Guo, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.02757
“The concept of mining hard examples has been employed in different machine learning paradigms for improving training efficiency and performance (Schroff et al., 2015; Huang et al., 2016; Yuan et al., 2017; Malisiewicz et al., 2011; Wang & Gupta, 2015; Zheng et al., 2019; Harwood et al., 2017).”
MethodDynamic MLML-tree based adaptive object detection using heterogeneous data distribution
Shin, D. K., Ahmed, M. U., Kim, Y. H., & Rhee, P. K. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-08285-7 · Cited by 1
“The intrinsic and nested sub-categories in each object category are dealt with by using the graph shift algorithm [18] with a dense sub-graph.”
MethodCamouflaged Person Identification
Singh, R. K., Nigam, S., Singh, A., & Elhoseny, M. (2020) · Springer eBooks · doi:10.1007/978-3-030-31873-4_7
An End-to-end System for Pests and Diseases Identification
Zhang, N., Ye, Z., & Wang, Y. (2020) · International Conference on Image, Video and Signal Processing (IVSP) · doi:10.1145/3388818.3389155
“For simplicity, we use k-means, but other clustering approaches can also be used, like Power Iteration Clustering (PIC) [11].”
MethodEricsson, L., Gouk, H., & Hospedales, T. M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.12360
Reinforced Sample Re-weighting for Pedestrian Attribute Recognition
Liu, Y., & Lin, Z. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207660
“Methods that emphasise hard examples [24] [25] or easy example [26] have been proposed to improve model’s robustness.”
BackgroundA part-based spatial and temporal aggregation method for dynamic scene recognition
Peng, X., Bouzerdoum, A., & Phung, S. L. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05415-3
“first trained an exemplar-SVM [47] for many part candidates, then selected from them the discriminative ones using the average max precision measure [27].”
MethodSimple Fusion of Object Detectors for Improved Performance and Faster Deployment
Lam, C., Gaspar, J., Ke, W., & Im, S. (2021) · IEEE Access · doi:10.1109/access.2021.3060768
“Experimental results on PASCAL VOC07 and VOC10 datasets reveal that the proposed method outperforms base models by up to 17% (EES [35] on PASCAL VOC07).”
MethodDeep neural networks based visual object detection in videos
Jin, R. (2020) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/144136
INTELLIGENT SYSTEM FOR DETECTION AND ACCOUNTING OF GARBAGE IN THE TERRITORY OF THE MUNICIPALITY
Казаков, О., & Azarenko, N. Y. (2021) · XXI Century Resumes of the Past and Challenges of the Present plus · doi:10.46548/21vek-2021-1054-0011
Object Picking by a Method Combined Cascade Classifier and Deep Reinforcement Learning
Makino, K., Ishida, K., Tanaka, T., & Terada, H. (2021) · Mechanisms and machine science · doi:10.1007/978-3-030-83594-1_23
Edge-guided Adversarial Network Based on Contrastive Learning for Image-to-Image Translation
Zhu, C. G., Lai, R., Bi, L., Wang, X., & Du, J. (2021) · Chinese Control Conference (CCC) · doi:10.23919/ccc52363.2021.9549847
“Some researchers choose different neighboring patches of an image [18], some others select a set of transformed versions of an image [19], or even an image itself [20].”
BackgroundFM-Mnet Real-Time Object Detection Model for Video Feature Fusion Processing
Zhou, T. H., Zhang, Y., Li, Y., & Wang, L. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-8430-2_23
Temporal Ensemble SSDLite: Exploiting Temporal Correlation in Video for Accurate Object Detection
NAKAMURA, L., & Hiromitsu, A. (2022) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.2021eap1068
Learning to Reweight Samples with Offline Loss Sequence
Wei, Y., Li, X., Wei, J., Qian, B., & Li, C. (2021) · Proceedings · doi:10.1109/icdm51629.2021.00083
Adaptable Text Matching via Meta-Weight Regulator
Zhang, B., Zhang, C., Ma, F., & Song, D. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3531932
“Hard example mining downsamples the majority class and utilizes the most difficult examples [22].”
BackgroundReal-Time Ranging of Vehicles and Pedestrians for Mobile Application on Smartphones
Su, Z., & Zhong, Z. (2022) · Journal of Shanghai Jiaotong University (Science) · doi:10.1007/s12204-022-2411-z
“Malisiewicz et al. [5] proposed a support vector machine-based object detection algorithm, which is trained on image datasets, and implemented with sliding window onto the detected images.”
Image Detection Using Exemplar-SVM with Augmented Features
Sun, S., & Mingyan, J. (2017) · International Conference on Advanced Computer Science Applications and Technologies · doi:10.23977/acsat.2017.1008
“An E-SVM[1] is a large collection of linear SVM classifiers, each trained from one positive example and many negative ones (an E-SVM).”
BackgroundLi, X., Wei, Y. J., Wang, C., Hu, Q., & Liu, C. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03848-y
“Typical methods include the boosting algorithm [49], hard example mining [50], and focal loss [51].”
MethodHarnessing Uncertainty - Multi-label Dysfluency Classification with Uncertain Labels
Jouaiti, M., & Dautenhahn, K. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20980-2_26
Diminishing Empirical Risk Minimization for Unsupervised Anomaly Detection
Wang, S., Liu, Y., Chen, L., & Chengqi Zhang, B. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892076
“Studies have been carried out to devise alternatives to the vanilla ERM in various scenarios, such as classification with imbalanced data [23], [28] and learning in the presence of corrupted data [14], [16].”
Object detection with deep neural networks under constrained scenarios
Zhang, G. (2022) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/164687
Relating images and 3D models with convolutional neural networks
Massa, F. (2017) · theses.fr (ABES) · doi:10.70675/1e407955z4cc1z4976z9a34z4dbb91dbfbb2
“Examples include alignment of IKEA furniture models to images [76], exemplar-based object detection [80] by matching discriminative elements [7, 22], and using”
MethodFaster RCNN-based Refueling Port Detection for the Autonomous Aircraft Ground Refueling System
Kuang, B., Barnes, S. E., Tang, G., & Jenkins, K. W. (2024) · International Conference on Automation and Computing (ICAC) · doi:10.1109/icac61394.2024.10718801
Learning From Mistakes: A Multilevel Optimization Framework
Zhang, L., Garg, B., Sridhara, P., Hosseini, R., & Xie, P. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3534151
“For example, AdaBoost [35] trains subsequent classifiers based on data selected from more difficult training samples, while hard example mining [36] trains Exemplar-support vector machines (SVMs) [37] to exploit challenging training samples and downsample the majority category.”
Brian, Z., Ramazan, B., & Feige, P. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5085936
FMW-Net: a first-order meta-weight-net approach for sample weighting
Zhou, Y., Shu, J., Liu, J., & Meng, D. (2025) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-025-02681-2
“Two dominant paradigms exist: (1) loss-decreasing functions (e.g., self-paced learning [52–55], iterative reweighting [25, 56]) to handle noisy labels, and (2) loss-increasing functions (e.g., AdaBoost [26, 57], hard negative mining [58], focal loss [23]) to emphasize challenging examples.”
Jilani, G., Paul, S., & Sultana, S. (2025) · Cognitive Computation and Systems · doi:10.1049/ccs2.70000
A Novel Method for Using Deep Reinforcement Machine Learning to Identify Objects
Mehta, A. I., & Singh, R. (2025) · International Journal of Latest Technology in Engineering Management & Applied Science · doi:10.51583/ijltemas.2025.1407000037
Boosting Deformable Part Model by Sample Sharing and Outlier Ablation
Liu, F., Huang, Y., Wang, L., & Yang, W. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-42057-3_53
“Our work is also related with [8] which tries to share samples between datasets and [9] which shows the possibility of training an object model with only one positive sample (yet many negative samples).”
BackgroundImproving Deep Learning Training and Inference with Dynamic Hyperparameter Optimization
Jiang, A. (2021) · Figshare · doi:10.1184/r1/14423846
Algorithm Research for Small Targets in Aerial Photography Based on Improved RT-DETR
Zuo, K., Hui, W., Tang, T. A. N. G., Li, C., & Rao, Q. (2025) · International Conference on Robot Systems and Applications (ICRSA) · doi:10.1109/icrsa66467.2025.11383801
“Before the popularity of deep learning methods, object detection relied on manually designed features (HOG, SIFT) and traditional classifiers (SVM) [1].”
Modélisation de contextes pour l'annotation sémantique de vidéos
Ballas, N. (2013) · theses.fr (ABES) · doi:10.70675/d70b424azb321z4223z87bez551fa701bf75 · Cited by 1
“One could add sparsity constraint to ExemplarSVM model [120] applied on several contexts in order to select the most distinctive.”
MethodTransfert de connaissance pour la compréhension des images
Kulkarni, P. (2017) · theses.fr (ABES) · doi:10.70675/22f42a83zd8cfz486cz994aza66d0b21be88
Towards robust visual object tracking : proposal selection and occlusion reasoning
Hua, Y. (2016) · theses.fr (ABES) · doi:10.70675/6198605ez66dfz4543zae20zb11f2812387e
“This idea of maintaining multiple detectors for an object category is similar in spirit to exemplar SVMs [Malisiewicz et al., 2011].”
MethodApprentissage statistique de classes sémantiques pour l'interprétation d'images aériennes
Randrianarivo, H. (2016) · theses.fr (ABES) · doi:10.70675/577f7fc0zf41dz4f13z827az0b63447b7485
Efficient multi-class objet detection with a hierarchy of classes
Fard, S. H. O. (2015) · theses.fr (ABES) · doi:10.70675/e92c2d99z5bb7z4b31z923fzdb46ad615bfb · Cited by 2
Représentations à base de parties pour la vision 3D de haut niveau
Kinauer, S. (2018) · theses.fr (ABES) · doi:10.70675/656d581ezce02z4326z9b0ezc7952eb7fd8e
New methods for image classification, image retrieval and semantic correspondence
de Rezende, R. S. (2017) · theses.fr (ABES) · doi:10.70675/0bd94776z371ez41e3z9afeze9c993ed9ab8
Multi-object detection and tracking in video sequences
Mhalla, A. (2018) · theses.fr (ABES) · doi:10.70675/6d64f9c8ze926z44d0zb444z11cb37d67638
du Terrail, J. O. (2018) · theses.fr (ABES) · doi:10.70675/083d206az0a4ez4480z866ez53e9de431d15 · Cited by 1
Gonthier, N. (2021) · theses.fr (ABES) · doi:10.70675/9abc66b4zca61z423bz85dcz07b849b15209 · Cited by 1
Self-supervised learning of deep visual representations
Caron, M. (2021) · theses.fr (ABES) · doi:10.70675/40d50cc9zaa9bz46aez992bz262e84a1f57d · Cited by 5
Biau, J. (2022) · theses.fr (ABES) · doi:10.70675/d1550a5bz5690z4a6bzaef7z490e096412d2 · Cited by 1
Petitjean, T. (2024) · theses.fr (ABES) · doi:10.70675/4c8bc911zb57az48a4z9d62z2cdab29f2277
Xu-Darme, R. (2023) · theses.fr (ABES) · doi:10.70675/1c468aadz651fz460czb151za8c972f432a2 · Cited by 1
Liu, Y., Lin, H., Chen, H., Chen, S., Gui, L., & Tao, M. (2025) · International Conference on Big Data, Artificial Intelligence and Risk Management (ICBAR) · doi:10.1145/3800227.3800378
ACVM: An Adaptive Combination Validation Mechanism for Long-Tailed Image Recognition
Sun, T., He, W., Shao, C., Zheng, S., & Yu, H. (2026) · Information · doi:10.3390/info17050455
ICDAR 2026 Competition on Writer Identification and Pen Classification from Hand-Drawn Circles
Gorges, T., van der Loop, J., Hüttner, L., Schneider, L.-S., Wu, F., Seuret, M., & Christlein, V. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36042-7_25
Discovering Multi-relational Latent Attributes by Visual Similarity Networks
Yancheshmeh, F. S., Kämäräinen, J., & Chen, K. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16634-6_1
“In recent works, Aghazadeh et al. [1] and Dong et al. [4] establish their similarity measures using classification scores of the exemplar SVM [17] which forms own classifier for each sample.”
Multi-Task Multi-Sample Learning
Aytar, Y., & Zisserman, A. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16199-0_6
Metadata
- Authors
- Malisiewicz, T., Gupta, A., & Efros, A. A.
- Affiliations
- Carnegie Mellon University (US)
- Venue
- 2011 International Conference on Computer Vision
- Publisher
- IEEE
- Published
- 2011-11
- Pages
- 89-96
- OpenAlex
- W1989684337
- Cited by
- 865
- References
- 25
- Citations by year
- 2026: 4 · 2025: 18 · 2024: 16 · 2023: 29 · 2022: 54 · 2021: 52 · 2020: 49 · 2019: 45 · 2018: 65 · 2017: 78 · 2016: 105 · 2015: 148 · 2014: 97 · 2013: 65 · 2012: 36
- FWCI
- 48.23
- Type
- conference paper
- Language
- en
- Open access
- green
- figshare.com
- Licence
- cc-by
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- Figshare (submittedVersion, cc-by)
- KiltHub Repository (submittedVersion)
- KiltHub Repository
- Funders
- National Science Foundation (0905402)
- Multidisciplinary University Research Initiative
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- object detection, linear SVM classifier, Pascal VOC, scene understanding, part-based models, generalization
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.