Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification
Open accessThe DOI matches its Crossref record; 70 of the 70 references it cites were found in a registry or an index.
Abstract
Video-based person re-identification (re-ID) is an important research topic in computer vision. The key to tackling the challenging task is to exploit both spatial and temporal clues in video sequences. In this work, we propose a novel graph-based framework, namely Multi-Granular Hypergraph (MGH), to pursue better representational capabilities by modeling spatiotemporal dependencies in terms of multiple granularities. Specifically, hypergraphs with different spatial granularities are constructed using various levels of part-based features across the video sequence. In each hypergraph, different temporal granularities are captured by hyperedges that connect a set of graph nodes (i.e., part-based features) across different temporal ranges. Two critical issues (misalignment and occlusion) are explicitly addressed by the proposed hypergraph propagation and feature aggregation schemes. Finally, we further enhance the overall video representation by learning more diversified graph-level representations of multiple granularities based on mutual information minimization. Extensive experiments on three widely-adopted benchmarks clearly demonstrate the effectiveness of the proposed framework. Notably, 90.0% top-1 accuracy on MARS is achieved using MGH, outperforming the state-of-the-arts.
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
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.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“We employ ResNet50 [18] pretrained on ImageNet [11] as the backbone.”
MethodAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“We adopt the Adam [27] optimizer with weight decay 0.”
MethodImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“We employ ResNet50 [18] pretrained on ImageNet [11] as the backbone.”
MethodNeural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213 · cited 1×
“It is therefore necessary to develop a specific attention mechanism [1, 38] to address this.”
BackgroundVeličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., & Bengio, Y. (2017) · arXiv · doi:10.48550/arxiv.1710.10903 · Cited by 12,107
(2017) · Cited by 11,625
Wang, X., Girshick, R., Gupta, A., & He, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00813 · Cited by 11,596
Inductive Representation Learning on Large Graphs
Hamilton, W. L., Ying, R., & Leskovec, J. (2017) · arXiv · doi:10.48550/arxiv.1706.02216 · Cited by 10,639 · cited 1×
“It is worth noting that pooling-based aggregators and LSTM have also been widely utilized for feature aggregation in GNNs [17].”
MethodLearning Spatiotemporal Features with 3D Convolutional Networks
Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.510 · Cited by 9,593 · cited 1×
“3D CNNs [24, 48] have also been applied to address video-based person re-ID [32].”
MethodThe graph neural network model
Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M., & Monfardini, G. (2009) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2008.2005605 · Cited by 9,582 · cited 1×
“Recently, neural networks have been extensively studied for graph learning, leading to the widespread usage of Graph Neural Networks (GNNs) [41, 10, 12, 29, 53].”
BackgroundTwo-Stream Convolutional Networks for Action Recognition in Videos
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1406.2199 · Cited by 6,756 · cited 1×
“Another class of methods [9, 39] resort to using additional information on optical flow, and adopt a two-stream structure [44] for discriminative feature learning.”
Background3D Convolutional Neural Networks for Human Action Recognition
Ji, S., Xu, W., Yang, M., & Yu, K. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.59 · Cited by 6,235
Targeted Branching for the Maximum Independent Set Problem Using Graph Neural Networks
Silva, G., Rodrigues, M., Teixeira, A., & Amorim, M. (2024) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.sea.2024.20 · Cited by 5,183
Advances In Deep Learning On Graphs (Gsp'18 Workshop)
Defferrard, M. (2016) · Figshare · doi:10.5281/zenodo.1286817 · Cited by 4,613
Scalable Person Re-identification: A Benchmark
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., & Tian, Q. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.133 · Cited by 4,506 · cited 1×
“Existing works on person re-ID mainly focus on two sub-tasks, i.e ., image-based [16, 66, 67, 7, 2] and video-based [13, 68] person re-ID.”
BackgroundConvolutional Networks on Graphs for Learning Molecular Fingerprints
Duvenaud, D., Maclaurin, D., Aguilera-Iparraguirre, J., Gómez-Bombarelli, R., Hirzel, T., Aspuru-Guzik, A., & Adams, R. P. (2015) · arXiv · doi:10.48550/arxiv.1509.09292 · Cited by 2,628
Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)
Sun, Y., Zheng, L., Yang, Y., Tian, Q., & Wang, S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01225-0_30 · Cited by 2,522
Learning deep representations by mutual information estimation and maximization
Hjelm, R. D., Fedorov, A., Lavoie-Marchildon, S., Grewal, K., Bachman, P., Trischler, A., & Bengio, Y. (2018) · arXiv · doi:10.48550/arxiv.1808.06670 · Cited by 1,991 · cited 1×
“Following [20], we define the mutual information loss as: where I measures the mutual information between different hypergraph features.”
MethodFeng, Y., You, H., Zhang, Z., Ji, R., & Gao, Y. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33013558 · Cited by 1,895
A Spatio-Temporal Descriptor Based on 3D-Gradients
Klaeser, A., Marszalek, M., & Schmid, C. (2008) · Procedings of the British Machine Vision Conference 2008 · doi:10.5244/c.22.99 · Cited by 1,846 · cited 1×
“Early methods tend to employ hand-crafted spatiotemporal features, such as HOG3D [28] and SIFT3D [42].”
MethodA 3-dimensional sift descriptor and its application to action recognition
Scovanner, P., Ali, S., & Shah, M. (2007) · Proceedings of the 15th ACM international conference on Multimedia · doi:10.1145/1291233.1291311 · Cited by 1,596 · cited 1×
“Early methods tend to employ hand-crafted spatiotemporal features, such as HOG3D [28] and SIFT3D [42].”
MethodPerson re-identification by symmetry-driven accumulation of local features
Farenzena, M., Bazzani, L., Perina, A., Murino, V., & Cristani, M. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539926 · Cited by 1,499 · cited 1×
“Existing works on person re-ID mainly focus on two sub-tasks, i.e ., image-based [16, 66, 67, 7, 2] and video-based [13, 68] person re-ID.”
BackgroundLearning with Hypergraphs: Clustering, Classification, and Embedding
Zhou, D., Huang, J., & Schölkopf, B. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0205 · Cited by 1,283 · cited 1×
“To this end, hypergraph [69] was introduced to model higher-order relationships between objects of interest, and has been applied to video segmentation [22] and image retrieval [23].”
MethodMulti-Label Image Recognition With Graph Convolutional Networks
Chen, Z.-M., Wei, X.-S., Wang, P., & Guo, Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00532 · Cited by 1,261 · cited 1×
“Depending on the type of data the nodes represent, graphs have been explored in many computer vision tasks, such as action recognition [55], image classification [8], and person re-ID [6, 43].”
BackgroundLearning Discriminative Features with Multiple Granularities for Person Re-Identification
Wang, G., Yuan, Y., Chen, X., Li, J., & Zhou, X. (2018) · Proceedings of the 26th ACM international conference on Multimedia · doi:10.1145/3240508.3240552 · Cited by 1,203 · cited 2×
“Recent studies [51, 64] have demonstrated that multi-granular spatial features have the advantage of generating more discriminative representations for human bodies.”
BackgroundMARS: A Video Benchmark for Large-Scale Person Re-Identification
Zheng, L., Bie, Z., Sun, Y., Wang, J., Su, C., Wang, S., & Tian, Q. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46466-4_52 · Cited by 965
Person Re-identification by Descriptive and Discriminative Classification
Hirzer, M., Beleznai, C., Roth, P. M., & Bischof, H. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-21227-7_9 · Cited by 961 · cited 2×
“PRID-2011 [19] was collected in an uncrowded outdoor environment with a relatively clean background.”
BackgroundPerson Re-identification in the Wild
Zheng, L., Zhang, H., Sun, S., Chandraker, M., Yang, Y., & Tian, Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.357 · Cited by 830 · cited 1×
“, image-based [16, 66, 67, 7, 2] and video-based [13, 68] person re-ID.”
Hypergraph convolution and hypergraph attention
Bai, S., Zhang, F., & Torr, P. H. S. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2020.107637 · Cited by 809
Liu, Z., & Zhou, J. (2020) · Synthesis Lectures on Artificial Intelligence and Machine Learning · doi:10.1007/978-3-031-01587-8_7 · Cited by 806
Videos as Space-Time Region Graphs
Wang, X., & Gupta, A. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01228-1_25 · Cited by 765
Learning Deep Context-Aware Features over Body and Latent Parts for Person Re-identification
Li, D., Chen, X., Zhang, Z., & Huang, K. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.782 · Cited by 692 · cited 1×
“As the structural information of the human body is beneficial for person identification, part-based models [49, 30, 47] have generally achieved promising performance in person re-ID.”
BackgroundPerson Re-identification by Video Ranking
Wang, T., Gong, S., Zhu, X., & Wang, S. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10593-2_45 · Cited by 642 · cited 5×
“Other methods try to extract more discriminative descriptors[26, 35] or design more effective ranking algorithms [52, 61, 3].”
BackgroundMethodInfluentialRecurrent Convolutional Network for Video-Based Person Re-identification
McLaughlin, N., Martinez del Rincon, J., & Miller, P. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.148 · Cited by 564 · cited 3×
“Another class of methods [9, 39] resort to using additional information on optical flow, and adopt a two-stream structure [44] for discriminative feature learning.”
BackgroundPart-Aligned Bilinear Representations for Person Re-identification
Suh, Y., Wang, J., Tang, S., Mei, T., & Lee, K. M. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01264-9_25 · Cited by 557
Person Reidentification Using Spatiotemporal Appearance
Gheissari, N., Sebastian, T. B., & Hartley, R. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.223 · Cited by 552 · cited 1×
“Existing works on person re-ID mainly focus on two sub-tasks, i.e ., image-based [16, 66, 67, 7, 2] and video-based [13, 68] person re-ID.”
BackgroundA Siamese Long Short-Term Memory Architecture for Human Re-identification
Varior, R. R., Shuai, B., Lu, J., Xu, D., & Wang, G. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46478-7_9 · Cited by 524 · cited 1×
“As the structural information of the human body is beneficial for person identification, part-based models [49, 30, 47] have generally achieved promising performance in person re-ID.”
BackgroundSee More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks
Lu, X., Wang, W., Ma, C., Shen, J., Shao, L., & Porikli, F. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00374 · Cited by 521 · cited 1×
“It is therefore necessary to develop a specific attention mechanism [1, 38] to address this.”
BackgroundSelf-citationPyramidal Person Re-IDentification via Multi-Loss Dynamic Training
Zheng, F., Deng, C., Sun, X., Jiang, X., Guo, X., Yu, Z., Huang, F., & Ji, R. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00871 · Cited by 428 · cited 2×
“Recent studies [51, 64] have demonstrated that multi-granular spatial features have the advantage of generating more discriminative representations for human bodies.”
BackgroundExploit the Unknown Gradually: One-Shot Video-Based Person Re-identification by Stepwise Learning
Wu, Y., Lin, Y., Dong, X., Yan, Y., Ouyang, W., & Yang, Y. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00543 · Cited by 383 · cited 2×
“Specifically, MGH outperforms several recent models ( i.e ., SeeForest [70], ASTPN [58], STAN [34], ETAP-Net [57], Snippet [5] with optical flow inputs, STA [15] and COSAM [45]) in terms of all the evaluation metrics on the two datasets.”
BackgroundMethodSelf-citationDiversity Regularized Spatiotemporal Attention for Video-Based Person Re-identification
Li, S., Bak, S., Carr, P., & Wang, X. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00046 · Cited by 370
Dynamic Hypergraph Neural Networks
Jiang, J., Wei, Y., Feng, Y., Cao, J., & Gao, Y. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/366 · Cited by 369 · cited 2×
“Inspired by the recent success of HGNNs [14, 25], we propose a novel hypergraph neural network for spatiotemporal feature learning.”
MethodJointly Attentive Spatial-Temporal Pooling Networks for Video-Based Person Re-identification
Xu, S., Cheng, Y., Gu, K., Yang, Y., Chang, S., & Zhou, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.507 · Cited by 341 · cited 1×
“Specifically, MGH outperforms several recent models ( i.e ., SeeForest [70], ASTPN [58], STAN [34], ETAP-Net [57], Snippet [5] with optical flow inputs, STA [15] and COSAM [45]) in terms of all the evaluation metrics on the two datasets.”
MethodQuality Aware Network for Set to Set Recognition
Liu, Y., Yan, J., & Ouyang, W. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.499 · Cited by 339 · cited 1×
“Some works [65, 33, 57, 46, 34, 62, 36] leverage the powerful learning capability of Convolutional Neural Networks (CNNs) and perform straightforward spatial/temporal pooling on video sequences to generate global representations.”
BackgroundPerson Re-identification with Deep Similarity-Guided Graph Neural Network
Shen, Y., Li, H., Yi, S., Chen, D., & Wang, X. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01267-0_30 · Cited by 324
Zhou, Z., Huang, Y., Wang, W., Wang, L., & Tan, T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.717 · Cited by 323 · cited 2×
“Specifically, MGH outperforms several recent models ( i.e ., SeeForest [70], ASTPN [58], STAN [34], ETAP-Net [57], Snippet [5] with optical flow inputs, STA [15] and COSAM [45]) in terms of all the evaluation metrics on the two datasets.”
BackgroundMethodScalable Person Re-identification on Supervised Smoothed Manifold
Bai, S., Bai, X., & Tian, Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.358 · Cited by 320 · cited 1×
“Existing works on person re-ID mainly focus on two sub-tasks, i.e ., image-based [16, 66, 67, 7, 2] and video-based [13, 68] person re-ID.”
BackgroundZero-Shot Video Object Segmentation via Attentive Graph Neural Networks
Wang, W., Lu, X., Shen, J., Crandall, D., & Shao, L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00933 · Cited by 303 · cited 1×
“Recently, neural networks have been extensively studied for graph learning, leading to the widespread usage of Graph Neural Networks (GNNs) [41, 10, 12, 29, 53].”
BackgroundSelf-citationImage retrieval via probabilistic hypergraph ranking
Huang, Y., Liu, Q., Zhang, S., & Metaxas, D. N. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5540012 · Cited by 293 · cited 1×
“To this end, hypergraph [69] was introduced to model higher-order relationships between objects of interest, and has been applied to video segmentation [22] and image retrieval [23].”
MethodA Two Stream Siamese Convolutional Neural Network for Person Re-identification
Chung, D., Tahboub, K., & Delp, E. J. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.218 · Cited by 286 · cited 2×
“Another class of methods [9, 39] resort to using additional information on optical flow, and adopt a two-stream structure [44] for discriminative feature learning.”
BackgroundUnsupervised Person Re-identification by Deep Learning Tracklet Association
Li, M., Zhu, X., & Gong, S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01225-0_45 · Cited by 272
Global-Local Temporal Representations for Video Person Re-Identification
Li, J., Zhang, S., Wang, J., Gao, W., & Tian, Q. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00406 · Cited by 256
Group Consistent Similarity Learning via Deep CRF for Person Re-identification
Chen, D., Xu, D., Li, H., Sebe, N., & Wang, X. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00902 · Cited by 241 · cited 1×
“Depending on the type of data the nodes represent, graphs have been explored in many computer vision tasks, such as action recognition [55], image classification [8], and person re-ID [6, 43].”
BackgroundVRSTC: Occlusion-Free Video Person Re-Identification
Hou, R., Ma, B., Chang, H., Gu, X., Shan, S., & Chen, X. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00735 · Cited by 234 · cited 2×
“It is worth noting that VRSTC [21] also achieves promising results on MARS; however, it is a two-stage model, i.e ., VRSTC first locates the occluded regions and completes the regions with a generative model, and then utilizes the non-occluded frames for re-ID.”
MethodPerson Re-identification via Recurrent Feature Aggregation
Yan, Y., Ni, B., Song, Z., Ma, C., Yan, Y., & Yang, X. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46466-4_42 · Cited by 233 · cited 1×
“Other meth-ods [39, 60, 70, 37, 5] adopt RNNs and attention mechanisms for more robust temporal feature fusion.”
BackgroundSelf-citationChen, D., Li, H., Xiao, T., Yi, S., & Wang, X. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00128 · Cited by 219 · cited 2×
“Specifically, MGH outperforms several recent models ( i.e ., SeeForest [70], ASTPN [58], STAN [34], ETAP-Net [57], Snippet [5] with optical flow inputs, STA [15] and COSAM [45]) in terms of all the evaluation metrics on the two datasets.”
BackgroundMethodPerson Re-Identification with Discriminatively Trained Viewpoint Invariant Dictionaries
Karanam, S., Li, Y., & Radke, R. J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.513 · Cited by 211 · cited 1×
“Other methods try to extract more discriminative descriptors[26, 35] or design more effective ranking algorithms [52, 61, 3].”
Method]Video object segmentation by hypergraph cut
Huang, Y., Liu, Q., & Metaxas, D. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206795 · Cited by 209 · cited 1×
“To this end, hypergraph [69] was introduced to model higher-order relationships between objects of interest, and has been applied to video segmentation [22] and image retrieval [23].”
MethodA Spatio-Temporal Appearance Representation for Video-Based Pedestrian Re-Identification
Liu, K., Ma, B., Zhang, W., & Huang, R. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.434 · Cited by 208 · cited 1×
“Other methods try to extract more discriminative descriptors[26, 35] or design more effective ranking algorithms [52, 61, 3].”
MethodMulti-Scale 3D Convolution Network for Video Based Person Re-Identification
Li, J., Zhang, S., & Huang, T. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018618 · Cited by 183
Ktena, S. I., Parisot, S., Ferrante, E., Rajchl, M., Lee, M., Glocker, B., & Rueckert, D. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-66182-7_54 · Cited by 175 · cited 1×
“Recently, neural networks have been extensively studied for graph learning, leading to the widespread usage of Graph Neural Networks (GNNs) [41, 10, 12, 29, 53].”
BackgroundAttribute-Driven Feature Disentangling and Temporal Aggregation for Video Person Re-Identification
Zhao, Y., Shen, X., Jin, Z., Lu, H., & Hua, X.-S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00505 · Cited by 172 · cited 1×
“We note that ADFD [63] obtains strong performance on iLIDS-VID and PRID-2011.”
BackgroundSTA: Spatial-Temporal Attention for Large-Scale Video-Based Person Re-Identification
Fu, Y., Wang, X., Wei, Y., & Huang, T. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018287 · Cited by 170 · cited 1×
“Specifically, MGH outperforms several recent models ( i.e ., SeeForest [70], ASTPN [58], STAN [34], ETAP-Net [57], Snippet [5] with optical flow inputs, STA [15] and COSAM [45]) in terms of all the evaluation metrics on the two datasets.”
MethodSpatial and Temporal Mutual Promotion for Video-Based Person Re-Identification
Liu, Y., Yuan, Z., Zhou, W., & Li, H. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018786 · Cited by 151
Co-Segmentation Inspired Attention Networks for Video-Based Person Re-Identification
Subramaniam, A., Nambiar, A., & Mittal, A. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00065 · Cited by 134 · cited 1×
“Specifically, MGH outperforms several recent models ( i.e ., SeeForest [70], ASTPN [58], STAN [34], ETAP-Net [57], Snippet [5] with optical flow inputs, STA [15] and COSAM [45]) in terms of all the evaluation metrics on the two datasets.”
MethodRe-Ranking via Metric Fusion for Object Retrieval and Person Re-Identification
Bai, S., Tang, P., Torr, P. H. S., & Latecki, L. J. (2019) · 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.2019.00083 · Cited by 119 · cited 1×
“Other methods try to extract more discriminative descriptors[26, 35] or design more effective ranking algorithms [52, 61, 3].”
MethodFast Person Re-identification via Cross-Camera Semantic Binary Transformation
Chen, J., Wang, Y., Qin, J., Liu, L., & Shao, L. (2017) · 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.2017.566 · Cited by 85 · cited 1×
“Existing works on person re-ID mainly focus on two sub-tasks, i.e ., image-based [16, 66, 67, 7, 2] and video-based [13, 68] person re-ID.”
BackgroundSelf-citationTransfer re-identification: From person to set-based verification
Zheng, W., Gong, S., & Xiang, T. (2012) · 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.2012.6247985 · Cited by 84 · cited 1×
“, image-based [16, 66, 67, 7, 2] and video-based [13, 68] person re-ID.”
Multi-shot Pedestrian Re-identification via Sequential Decision Making
Zhang, J., Wang, N., & Zhang, L. (2018) · 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.2018.00709 · Cited by 77
HyperGCN: Hypergraph Convolutional Networks for Semi-Supervised Classification.Preprint
Yadati, N., Nimishakavi, M., Yadav, P., Louis, A., & Talukdar, P. P. (2018) · arXiv (Cornell University) · Cited by 22
Metadata
- Authors
- Yan, Y., Qin, J., Chen, J., Liu, L., Zhu, F., Tai, Y., & Shao, L.
- Venue
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 2896-2905
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3035486808
- Cited by
- 159
- References
- 70
- FWCI
- 7.95
- Type
- conference paper
- Language
- en
- Open access
- green
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.