Dual-branch adaptive attention transformer for occluded person re-identification
•An end-to-end dual-branch vision transformer for occluded person re-identification is proposed.•Adaptive extraction of human local features using self-Attention mechanism is achieved.•Goal Consistency Loss with more consistent convergence goals is designed.•The State-of-the-Art performance were ach...
Saved in:
| Published in | Image and vision computing Vol. 131; p. 104633 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
01.03.2023
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 0262-8856 1872-8138 |
| DOI | 10.1016/j.imavis.2023.104633 |
Cover
| Abstract | •An end-to-end dual-branch vision transformer for occluded person re-identification is proposed.•Adaptive extraction of human local features using self-Attention mechanism is achieved.•Goal Consistency Loss with more consistent convergence goals is designed.•The State-of-the-Art performance were achieved on Occluded-REID dataset.
Occluded person re-identification is still a common and challenging task because people are often occluded by some obstacles (e.g. cars and trees) in the real world. In order to locate the unoccluded parts and extract local fine-grained features of the occluded human body, State-of-the-Art (SOTA) methods usually use a pose estimation model, which usually causes additional bias and this two-stage architecture also complicates the model. To solve this problem, an end-to-end dual-branch Transformer network for occluded person re-identification is designed. Specifically, one of the branches is the transformer-based global branch, which is responsible for extracting global features, while in the other local branch, we design the Selective Token Attention (STA) module. STA can utilize the multi-headed self-attention mechanism to select discriminating tokens for effectively extracting the local features. Further, in order to alleviate the inconsistency between Softmax Loss and Triplet Loss convergence goals, Circle Loss is introduced to design the Goal Consistency Loss (GC Loss) to supervise the network. Experiments on four challenging datasets for Re-ID tasks (including occluded person Re-ID and holistic person Re-ID) illustrate that our method can achieve SOTA performance. |
|---|---|
| AbstractList | •An end-to-end dual-branch vision transformer for occluded person re-identification is proposed.•Adaptive extraction of human local features using self-Attention mechanism is achieved.•Goal Consistency Loss with more consistent convergence goals is designed.•The State-of-the-Art performance were achieved on Occluded-REID dataset.
Occluded person re-identification is still a common and challenging task because people are often occluded by some obstacles (e.g. cars and trees) in the real world. In order to locate the unoccluded parts and extract local fine-grained features of the occluded human body, State-of-the-Art (SOTA) methods usually use a pose estimation model, which usually causes additional bias and this two-stage architecture also complicates the model. To solve this problem, an end-to-end dual-branch Transformer network for occluded person re-identification is designed. Specifically, one of the branches is the transformer-based global branch, which is responsible for extracting global features, while in the other local branch, we design the Selective Token Attention (STA) module. STA can utilize the multi-headed self-attention mechanism to select discriminating tokens for effectively extracting the local features. Further, in order to alleviate the inconsistency between Softmax Loss and Triplet Loss convergence goals, Circle Loss is introduced to design the Goal Consistency Loss (GC Loss) to supervise the network. Experiments on four challenging datasets for Re-ID tasks (including occluded person Re-ID and holistic person Re-ID) illustrate that our method can achieve SOTA performance. |
| ArticleNumber | 104633 |
| Author | Mu, Xinyu Jiang, Mingzi Lu, Yunhua Liu, Zhi |
| Author_xml | – sequence: 1 givenname: Yunhua surname: Lu fullname: Lu, Yunhua email: yhlu@cqut.edu.cn – sequence: 2 givenname: Mingzi surname: Jiang fullname: Jiang, Mingzi email: mingziJ@stu.cqut.edu.cn – sequence: 3 givenname: Zhi surname: Liu fullname: Liu, Zhi email: liuzhi@cqut.edu.cn – sequence: 4 givenname: Xinyu surname: Mu fullname: Mu, Xinyu email: muxy@2020.cqut.edu.cn |
| BookMark | eNqFkE1OwzAQhS1UJNrCDVjkAil2nDgOCyRUfqVKsIC15YzHwlWaVLZbidvjEFYsYDWjmfme3rwFmfVDj4RcMrpilImr7crt9NGFVUELnkal4PyEzJmsi1wyLmdkTguRelmJM7IIYUsprWndzMnr3UF3eet1Dx-ZNnof3REzHSP20Q19FtMm2MHv0GepZANAdzBosj36kPYec2fGW-tAj8Q5ObW6C3jxU5fk_eH-bf2Ub14en9e3mxw4FTEXLWtK0VZQGl1arXlpKa8tiAI0YGOBckNBSF1LY2RdNbVsObXcNIYxVhZ8Sa4nXfBDCB6tAhe_HSTLrlOMqjEbtVVTNmrMRk3ZJLj8Be99OvOf_2E3E4bpsaNDrwI47AGN8whRmcH9LfAFQAKEUw |
| CitedBy_id | crossref_primary_10_1007_s11227_025_07041_z crossref_primary_10_3390_math12223508 crossref_primary_10_1016_j_engappai_2023_107521 crossref_primary_10_1016_j_jvcir_2023_103972 crossref_primary_10_1007_s11042_023_16286_w crossref_primary_10_1016_j_jvcir_2024_104128 crossref_primary_10_1016_j_imavis_2024_104929 crossref_primary_10_1016_j_neunet_2023_09_047 crossref_primary_10_1109_ACCESS_2025_3551672 crossref_primary_10_1109_ACCESS_2023_3317950 crossref_primary_10_1109_TIV_2024_3350669 crossref_primary_10_1016_j_imavis_2023_104740 crossref_primary_10_1016_j_knosys_2023_111155 |
| Cites_doi | 10.1109/CVPR46437.2021.00542 10.1109/CVPR42600.2020.01176 10.1109/TPAMI.2021.3079910 10.1016/j.neucom.2022.03.055 10.1145/3240508.3240552 10.1109/ICCV.2019.00380 10.1109/ICCV48922.2021.01474 10.1609/aaai.v34i07.7000 10.1007/978-3-030-01225-0_30 10.1109/ICCV.2017.349 10.1145/3486678 10.1609/aaai.v35i2.16260 10.1109/CVPR.2019.00048 10.1109/CVPR46437.2021.00292 10.1609/aaai.v36i1.19967 10.1109/CVPR42600.2020.00648 10.1109/CVPR42600.2020.00643 10.1109/ICCV.2015.133 10.1109/ICCV.2019.00063 10.1109/CVPRW.2019.00190 10.1109/CVPR.2018.00129 10.1007/s11042-020-09018-x 10.1109/LSP.2018.2822810 10.1109/TMM.2021.3074239 10.1109/CVPR42600.2020.01058 10.1109/CVPR.2019.00033 10.1109/ICCV.2017.405 10.1109/TPAMI.2021.3054775 |
| ContentType | Journal Article |
| Copyright | 2023 Elsevier B.V. |
| Copyright_xml | – notice: 2023 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.imavis.2023.104633 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Engineering |
| EISSN | 1872-8138 |
| ExternalDocumentID | 10_1016_j_imavis_2023_104633 S0262885623000070 |
| GroupedDBID | --K --M .~1 0R~ 1B1 1~. 1~5 29I 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABFNM ABFRF ABJNI ABMAC ABOCM ABTAH ABXDB ABYKQ ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADTZH AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q G8K GBLVA GBOLZ HLZ HVGLF HZ~ IHE J1W JJJVA KOM LG9 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SBC SDF SDG SDP SES SEW SPC SPCBC SST SSV SSZ T5K TN5 UHS UNMZH VOH WUQ XFK XPP ZMT ZY4 ~G- AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AFXIZ AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SSH |
| ID | FETCH-LOGICAL-c306t-6b1946b5c4da4faa34f037fc62cace9fc03d0c68a78dd875978b30f3d9d111423 |
| IEDL.DBID | AIKHN |
| ISSN | 0262-8856 |
| IngestDate | Thu Apr 24 22:53:43 EDT 2025 Tue Jul 01 00:48:17 EDT 2025 Fri Feb 23 02:39:25 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Transformer Person re-identification Metric learning Multi-headed self-attention |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c306t-6b1946b5c4da4faa34f037fc62cace9fc03d0c68a78dd875978b30f3d9d111423 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_imavis_2023_104633 crossref_primary_10_1016_j_imavis_2023_104633 elsevier_sciencedirect_doi_10_1016_j_imavis_2023_104633 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | March 2023 2023-03-00 |
| PublicationDateYYYYMMDD | 2023-03-01 |
| PublicationDate_xml | – month: 03 year: 2023 text: March 2023 |
| PublicationDecade | 2020 |
| PublicationTitle | Image and vision computing |
| PublicationYear | 2023 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | L. Zheng, Y. Yang, A.G. Hauptmann, Person re-identification: Past, present and future, arXiv preprint arXiv:1610.02984 (2016). C. Song, Y. Huang, W. Ouyang, L. Wang, Mask-guided contrastive attention model for person re-identification, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 1179–1188. Zheng, Zheng, Yang (b0105) 2017; 14 Z. Zhong, L. Zheng, G. Kang, S. Li, Y. Yang, Random erasing data augmentation, in: Proceedings of the AAAI conference on artificial intelligence, vol. 34, 2020, pp. 13001–13008. Y. Sun, L. Zheng, Y. Yang, Q. Tian, S. Wang, Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline), in: Proceedings of the European conference on computer vision (ECCV), 2018, pp. 480–496. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al., An image is worth 16x16 words: Transformers for image recognition at scale, arXiv preprint arXiv:2010.11929 (2020). Z. Zheng, L. Zheng, Y. Yang, Unlabeled samples generated by gan improve the person re-identification baseline in vitro, in: Proceedings of the IEEE international conference on computer vision, 2017, pp. 3754–3762. J. He, J.-N. Chen, S. Liu, A. Kortylewski, C. Yang, Y. Bai, C. Wang, Transfg: A transformer architecture for fine-grained recognition, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, 2022, pp. 852–860. Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin (b0150) 2017; 30 R. Girdhar, J. Carreira, C. Doersch, A. Zisserman, Video action transformer network, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 244–253. Yang, He, Pei, Zhou, Li, Yuan, Zhang (b0020) 2021; 24 Khorramshahi, Peri, Chen, Chellappa (b0040) 2020 Shu, Yuan, Liu, Liu (b0135) 2020; 79 K. Zhou, Y. Yang, A. Cavallaro, T. Xiang, Omni-scale feature learning for person re-identification, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 3702–3712. Jia, Cheng, Lu, Zhang (b0035) 2022 Y. Sun, C. Cheng, Y. Zhang, C. Zhang, L. Zheng, Z. Wang, Y. Wei, Circle loss: A unified perspective of pair similarity optimization, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 6398–6407. Zhu, Guo, Liu, Tang, Wang (b0200) 2020 Raghu, Unterthiner, Kornblith, Zhang, Dosovitskiy (b0075) 2021; 34 S. Gao, J. Wang, H. Lu, Z. Liu, Pose-guided visible part matching for occluded person reid, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11744–11752. Yuan, Shu, Liu, He (b0015) 2022; 491 Carion, Massa, Synnaeve, Usunier, Kirillov, Zagoruyko (b0060) 2020 Wang, Cheng, Liu, Liu (b0165) 2018; 25 Yuan, Chang, Li, He (b0010) 2022; 18 G. Wang, J.-H. Lai, W. Liang, G. Wang, Smoothing adversarial domain attack and p-memory reconsolidation for cross-domain person re-identification, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 10568–10577. H. Luo, Y. Gu, X. Liao, S. Lai, W. Jiang, Bag of tricks and a strong baseline for deep person re-identification, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, 2019, pp. 0–0. Ye, Shen, Lin, Xiang, Shao, Hoi (b0180) 2021; 44 H. Wang, Y. Zhu, H. Adam, A. Yuille, L.-C. Chen, Max-deeplab: End-to-end panoptic segmentation with mask transformers, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 5463–5474. Y. Sun, Q. Xu, Y. Li, C. Zhang, Y. Li, S. Wang, J. Sun, Perceive where to focus: Learning visibility-aware part-level features for partial person re-identification, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 393–402. G. Wang, S. Yang, H. Liu, Z. Wang, Y. Yang, S. Wang, G. Yu, E. Zhou, J. Sun, High-order information matters: Learning relation and topology for occluded person re-identification, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 6449–6458. Y. Li, J. He, T. Zhang, X. Liu, Y. Zhang, F. Wu, Diverse part discovery: Occluded person re-identification with part-aware transformer, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 2898–2907. Wang, Doretto, Sebastian, Rittscher, Tu (b0185) 2007 G. Wang, Y. Yuan, X. Chen, J. Li, X. Zhou, Learning discriminative features with multiple granularities for person re-identification, in: Proceedings of the 26th ACM international conference on Multimedia, 2018, pp. 274–282. L. Zhao, X. Li, Y. Zhuang, J. Wang, Deeply-learned part-aligned representations for person re-identification, in: Proceedings of the IEEE international conference on computer vision, 2017, pp. 3219–3228. Hou, Ma, Chang, Gu, Shan, Chen (b0130) 2021 S. He, H. Luo, P. Wang, F. Wang, H. Li, W. Jiang, Transreid: Transformer-based object re-identification, in: Proceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 15013–15022. M. Jia, X. Cheng, Y. Zhai, S. Lu, S. Ma, Y. Tian, J. Zhang, Matching on sets: Conquer occluded person re-identification without alignment, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, 2021, pp. 1673–1681. P. Sun, J. Cao, Y. Jiang, R. Zhang, E. Xie, Z. Yuan, C. Wang, P. Luo, Transtrack: Multiple object tracking with transformer, arXiv preprint arXiv:2012.15460 (2020). J. Miao, Y. Wu, P. Liu, Y. Ding, Y. Yang, Pose-guided feature alignment for occluded person re-identification, in: Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 542–551. A. Hermans, L. Beyer, B. Leibe, In defense of the triplet loss for person re-identification, arXiv preprint arXiv:1703.07737 (2017). L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, Q. Tian, Scalable person re-identification: A benchmark, in: Proceedings of the IEEE international conference on computer vision, 2015, pp. 1116–1124. 10.1016/j.imavis.2023.104633_b0055 10.1016/j.imavis.2023.104633_b0110 10.1016/j.imavis.2023.104633_b0155 Yuan (10.1016/j.imavis.2023.104633_b0010) 2022; 18 Raghu (10.1016/j.imavis.2023.104633_b0075) 2021; 34 10.1016/j.imavis.2023.104633_b0115 10.1016/j.imavis.2023.104633_b0170 10.1016/j.imavis.2023.104633_b0050 10.1016/j.imavis.2023.104633_b0190 10.1016/j.imavis.2023.104633_b0070 10.1016/j.imavis.2023.104633_b0175 10.1016/j.imavis.2023.104633_b0095 10.1016/j.imavis.2023.104633_b0030 10.1016/j.imavis.2023.104633_b0195 Vaswani (10.1016/j.imavis.2023.104633_b0150) 2017; 30 Hou (10.1016/j.imavis.2023.104633_b0130) 2021 10.1016/j.imavis.2023.104633_b0145 10.1016/j.imavis.2023.104633_b0025 Ye (10.1016/j.imavis.2023.104633_b0180) 2021; 44 10.1016/j.imavis.2023.104633_b0045 10.1016/j.imavis.2023.104633_b0100 Zheng (10.1016/j.imavis.2023.104633_b0105) 2017; 14 10.1016/j.imavis.2023.104633_b0125 10.1016/j.imavis.2023.104633_b0005 10.1016/j.imavis.2023.104633_b0160 10.1016/j.imavis.2023.104633_b0080 Wang (10.1016/j.imavis.2023.104633_b0185) 2007 Zhu (10.1016/j.imavis.2023.104633_b0200) 2020 Khorramshahi (10.1016/j.imavis.2023.104633_b0040) 2020 Jia (10.1016/j.imavis.2023.104633_b0035) 2022 10.1016/j.imavis.2023.104633_b0065 10.1016/j.imavis.2023.104633_b0120 10.1016/j.imavis.2023.104633_b0085 10.1016/j.imavis.2023.104633_b0140 Shu (10.1016/j.imavis.2023.104633_b0135) 2020; 79 10.1016/j.imavis.2023.104633_b0090 Yuan (10.1016/j.imavis.2023.104633_b0015) 2022; 491 Wang (10.1016/j.imavis.2023.104633_b0165) 2018; 25 Carion (10.1016/j.imavis.2023.104633_b0060) 2020 Yang (10.1016/j.imavis.2023.104633_b0020) 2021; 24 |
| References_xml | – reference: H. Wang, Y. Zhu, H. Adam, A. Yuille, L.-C. Chen, Max-deeplab: End-to-end panoptic segmentation with mask transformers, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 5463–5474. – reference: G. Wang, J.-H. Lai, W. Liang, G. Wang, Smoothing adversarial domain attack and p-memory reconsolidation for cross-domain person re-identification, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 10568–10577. – reference: M. Jia, X. Cheng, Y. Zhai, S. Lu, S. Ma, Y. Tian, J. Zhang, Matching on sets: Conquer occluded person re-identification without alignment, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, 2021, pp. 1673–1681. – reference: A. Hermans, L. Beyer, B. Leibe, In defense of the triplet loss for person re-identification, arXiv preprint arXiv:1703.07737 (2017). – reference: C. Song, Y. Huang, W. Ouyang, L. Wang, Mask-guided contrastive attention model for person re-identification, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 1179–1188. – start-page: 346 year: 2020 end-page: 363 ident: b0200 article-title: Identity-guided human semantic parsing for person re-identification publication-title: European Conference on Computer Vision – reference: L. Zheng, Y. Yang, A.G. Hauptmann, Person re-identification: Past, present and future, arXiv preprint arXiv:1610.02984 (2016). – reference: J. Miao, Y. Wu, P. Liu, Y. Ding, Y. Yang, Pose-guided feature alignment for occluded person re-identification, in: Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 542–551. – start-page: 213 year: 2020 end-page: 229 ident: b0060 article-title: End-to-end object detection with transformers publication-title: European conference on computer vision – volume: 30 year: 2017 ident: b0150 article-title: Attention is all you need publication-title: Adv. Neural Inf. Process. Syst. – reference: A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al., An image is worth 16x16 words: Transformers for image recognition at scale, arXiv preprint arXiv:2010.11929 (2020). – reference: Y. Sun, Q. Xu, Y. Li, C. Zhang, Y. Li, S. Wang, J. Sun, Perceive where to focus: Learning visibility-aware part-level features for partial person re-identification, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 393–402. – reference: Y. Li, J. He, T. Zhang, X. Liu, Y. Zhang, F. Wu, Diverse part discovery: Occluded person re-identification with part-aware transformer, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 2898–2907. – volume: 491 start-page: 44 year: 2022 end-page: 56 ident: b0015 article-title: Structural target-aware model for thermal infrared tracking publication-title: Neurocomputing – year: 2021 ident: b0130 article-title: Feature completion for occluded person re-identification publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – reference: H. Luo, Y. Gu, X. Liao, S. Lai, W. Jiang, Bag of tricks and a strong baseline for deep person re-identification, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, 2019, pp. 0–0. – reference: G. Wang, S. Yang, H. Liu, Z. Wang, Y. Yang, S. Wang, G. Yu, E. Zhou, J. Sun, High-order information matters: Learning relation and topology for occluded person re-identification, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 6449–6458. – reference: L. Zhao, X. Li, Y. Zhuang, J. Wang, Deeply-learned part-aligned representations for person re-identification, in: Proceedings of the IEEE international conference on computer vision, 2017, pp. 3219–3228. – reference: S. He, H. Luo, P. Wang, F. Wang, H. Li, W. Jiang, Transreid: Transformer-based object re-identification, in: Proceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 15013–15022. – reference: K. Zhou, Y. Yang, A. Cavallaro, T. Xiang, Omni-scale feature learning for person re-identification, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 3702–3712. – volume: 24 start-page: 1956 year: 2021 end-page: 1967 ident: b0020 article-title: Siamcorners: Siamese corner networks for visual tracking publication-title: IEEE Trans. Multimedia – reference: Y. Sun, L. Zheng, Y. Yang, Q. Tian, S. Wang, Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline), in: Proceedings of the European conference on computer vision (ECCV), 2018, pp. 480–496. – reference: Y. Sun, C. Cheng, Y. Zhang, C. Zhang, L. Zheng, Z. Wang, Y. Wei, Circle loss: A unified perspective of pair similarity optimization, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 6398–6407. – start-page: 369 year: 2020 end-page: 386 ident: b0040 article-title: The devil is in the details: Self-supervised attention for vehicle re-identification publication-title: European Conference on Computer Vision – reference: L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, Q. Tian, Scalable person re-identification: A benchmark, in: Proceedings of the IEEE international conference on computer vision, 2015, pp. 1116–1124. – year: 2022 ident: b0035 article-title: Learning disentangled representation implicitly via transformer for occluded person re-identification publication-title: IEEE Trans. Multimedia – volume: 18 start-page: 1 year: 2022 end-page: 18 ident: b0010 article-title: Learning adaptive spatial-temporal context-aware correlation filters for uav tracking publication-title: ACM Trans. Multimed. Comput. Commun. Appl. (TOMM) – volume: 79 start-page: 23617 year: 2020 end-page: 23632 ident: b0135 article-title: Adaptive weight part-based convolutional network for person re-identification publication-title: Multimed. Tools Appl. – reference: S. Gao, J. Wang, H. Lu, Z. Liu, Pose-guided visible part matching for occluded person reid, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11744–11752. – volume: 25 start-page: 926 year: 2018 end-page: 930 ident: b0165 article-title: Additive margin softmax for face verification publication-title: IEEE Signal Process. Lett. – volume: 14 start-page: 1 year: 2017 end-page: 20 ident: b0105 article-title: A discriminatively learned cnn embedding for person reidentification publication-title: ACM Trans. Multimed. Comput. Commun. Appl. (TOMM) – reference: P. Sun, J. Cao, Y. Jiang, R. Zhang, E. Xie, Z. Yuan, C. Wang, P. Luo, Transtrack: Multiple object tracking with transformer, arXiv preprint arXiv:2012.15460 (2020). – reference: G. Wang, Y. Yuan, X. Chen, J. Li, X. Zhou, Learning discriminative features with multiple granularities for person re-identification, in: Proceedings of the 26th ACM international conference on Multimedia, 2018, pp. 274–282. – reference: Z. Zheng, L. Zheng, Y. Yang, Unlabeled samples generated by gan improve the person re-identification baseline in vitro, in: Proceedings of the IEEE international conference on computer vision, 2017, pp. 3754–3762. – start-page: 1 year: 2007 end-page: 8 ident: b0185 article-title: Shape and appearance context modeling publication-title: 2007 ieee 11th international conference on computer vision – reference: Z. Zhong, L. Zheng, G. Kang, S. Li, Y. Yang, Random erasing data augmentation, in: Proceedings of the AAAI conference on artificial intelligence, vol. 34, 2020, pp. 13001–13008. – volume: 34 start-page: 12116 year: 2021 end-page: 12128 ident: b0075 article-title: Do vision transformers see like convolutional neural networks? publication-title: Adv. Neural Inf. Process. Syst. – reference: R. Girdhar, J. Carreira, C. Doersch, A. Zisserman, Video action transformer network, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 244–253. – reference: J. He, J.-N. Chen, S. Liu, A. Kortylewski, C. Yang, Y. Bai, C. Wang, Transfg: A transformer architecture for fine-grained recognition, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, 2022, pp. 852–860. – volume: 44 start-page: 2872 year: 2021 end-page: 2893 ident: b0180 article-title: Deep learning for person re-identification: A survey and outlook publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – ident: 10.1016/j.imavis.2023.104633_b0065 doi: 10.1109/CVPR46437.2021.00542 – ident: 10.1016/j.imavis.2023.104633_b0090 doi: 10.1109/CVPR42600.2020.01176 – year: 2021 ident: 10.1016/j.imavis.2023.104633_b0130 article-title: Feature completion for occluded person re-identification publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2021.3079910 – volume: 491 start-page: 44 year: 2022 ident: 10.1016/j.imavis.2023.104633_b0015 article-title: Structural target-aware model for thermal infrared tracking publication-title: Neurocomputing doi: 10.1016/j.neucom.2022.03.055 – ident: 10.1016/j.imavis.2023.104633_b0045 doi: 10.1145/3240508.3240552 – ident: 10.1016/j.imavis.2023.104633_b0025 doi: 10.1109/ICCV.2019.00380 – ident: 10.1016/j.imavis.2023.104633_b0070 doi: 10.1109/ICCV48922.2021.01474 – ident: 10.1016/j.imavis.2023.104633_b0190 doi: 10.1609/aaai.v34i07.7000 – ident: 10.1016/j.imavis.2023.104633_b0080 doi: 10.1007/978-3-030-01225-0_30 – ident: 10.1016/j.imavis.2023.104633_b0195 doi: 10.1109/ICCV.2017.349 – volume: 18 start-page: 1 issue: 3 year: 2022 ident: 10.1016/j.imavis.2023.104633_b0010 article-title: Learning adaptive spatial-temporal context-aware correlation filters for uav tracking publication-title: ACM Trans. Multimed. Comput. Commun. Appl. (TOMM) doi: 10.1145/3486678 – ident: 10.1016/j.imavis.2023.104633_b0140 doi: 10.1609/aaai.v35i2.16260 – volume: 34 start-page: 12116 year: 2021 ident: 10.1016/j.imavis.2023.104633_b0075 article-title: Do vision transformers see like convolutional neural networks? publication-title: Adv. Neural Inf. Process. Syst. – ident: 10.1016/j.imavis.2023.104633_b0085 doi: 10.1109/CVPR.2019.00048 – ident: 10.1016/j.imavis.2023.104633_b0145 doi: 10.1109/CVPR46437.2021.00292 – ident: 10.1016/j.imavis.2023.104633_b0160 – start-page: 346 year: 2020 ident: 10.1016/j.imavis.2023.104633_b0200 article-title: Identity-guided human semantic parsing for person re-identification – volume: 14 start-page: 1 issue: 1 year: 2017 ident: 10.1016/j.imavis.2023.104633_b0105 article-title: A discriminatively learned cnn embedding for person reidentification publication-title: ACM Trans. Multimed. Comput. Commun. Appl. (TOMM) – ident: 10.1016/j.imavis.2023.104633_b0005 – ident: 10.1016/j.imavis.2023.104633_b0100 doi: 10.1609/aaai.v36i1.19967 – ident: 10.1016/j.imavis.2023.104633_b0095 doi: 10.1109/CVPR42600.2020.00648 – ident: 10.1016/j.imavis.2023.104633_b0120 doi: 10.1109/CVPR42600.2020.00643 – ident: 10.1016/j.imavis.2023.104633_b0110 – ident: 10.1016/j.imavis.2023.104633_b0170 doi: 10.1109/ICCV.2015.133 – ident: 10.1016/j.imavis.2023.104633_b0030 doi: 10.1109/ICCV.2019.00063 – ident: 10.1016/j.imavis.2023.104633_b0115 doi: 10.1109/CVPRW.2019.00190 – ident: 10.1016/j.imavis.2023.104633_b0055 – ident: 10.1016/j.imavis.2023.104633_b0125 doi: 10.1109/CVPR.2018.00129 – volume: 79 start-page: 23617 issue: 31 year: 2020 ident: 10.1016/j.imavis.2023.104633_b0135 article-title: Adaptive weight part-based convolutional network for person re-identification publication-title: Multimed. Tools Appl. doi: 10.1007/s11042-020-09018-x – volume: 25 start-page: 926 issue: 7 year: 2018 ident: 10.1016/j.imavis.2023.104633_b0165 article-title: Additive margin softmax for face verification publication-title: IEEE Signal Process. Lett. doi: 10.1109/LSP.2018.2822810 – start-page: 369 year: 2020 ident: 10.1016/j.imavis.2023.104633_b0040 article-title: The devil is in the details: Self-supervised attention for vehicle re-identification – start-page: 1 year: 2007 ident: 10.1016/j.imavis.2023.104633_b0185 article-title: Shape and appearance context modeling – volume: 24 start-page: 1956 year: 2021 ident: 10.1016/j.imavis.2023.104633_b0020 article-title: Siamcorners: Siamese corner networks for visual tracking publication-title: IEEE Trans. Multimedia doi: 10.1109/TMM.2021.3074239 – volume: 30 year: 2017 ident: 10.1016/j.imavis.2023.104633_b0150 article-title: Attention is all you need publication-title: Adv. Neural Inf. Process. Syst. – ident: 10.1016/j.imavis.2023.104633_b0050 doi: 10.1109/CVPR42600.2020.01058 – start-page: 213 year: 2020 ident: 10.1016/j.imavis.2023.104633_b0060 article-title: End-to-end object detection with transformers – ident: 10.1016/j.imavis.2023.104633_b0155 doi: 10.1109/CVPR.2019.00033 – year: 2022 ident: 10.1016/j.imavis.2023.104633_b0035 article-title: Learning disentangled representation implicitly via transformer for occluded person re-identification publication-title: IEEE Trans. Multimedia – ident: 10.1016/j.imavis.2023.104633_b0175 doi: 10.1109/ICCV.2017.405 – volume: 44 start-page: 2872 issue: 6 year: 2021 ident: 10.1016/j.imavis.2023.104633_b0180 article-title: Deep learning for person re-identification: A survey and outlook publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2021.3054775 |
| SSID | ssj0007079 |
| Score | 2.465342 |
| Snippet | •An end-to-end dual-branch vision transformer for occluded person re-identification is proposed.•Adaptive extraction of human local features using... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 104633 |
| SubjectTerms | Metric learning Multi-headed self-attention Person re-identification Transformer |
| Title | Dual-branch adaptive attention transformer for occluded person re-identification |
| URI | https://dx.doi.org/10.1016/j.imavis.2023.104633 |
| Volume | 131 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NS8MwFH_M7aIHP6bi_Bg5eM2WNWnXHsd0TMUh6GC3kq9iZW5ldlf_dpM2HRNEwVNp6SvlJXnv90veB8A1jUQSKC_CtnQ6ZpJEWPiUYSlDi2iFZtwmJz9OgvGU3c_8WQ2GVS6MDat0tr-06YW1dk-6TpvdLE27z4Y9eGFo_XdxHmd4e8OjUeDXoTG4exhPNgbZFoErt1rM4jcCVQZdEeaVvtts_o7tIl6cd1L6s4fa8jqjQ9h3cBENyj86gppeNOHAQUfkFuZHE_a26goew9PNms-xsD0zXhFXPLM2DdlKmkVsI8ortKpXyFzQUsr5WpkPZgX-RiuNU-XCiIqRO4Hp6PZlOMaudQKWhgPkOBC9iAXCl0xxlnBOWUJoP5GBJ7nUUSIJVUQGIe-HShnKYrikoCShKlI9m11LT6G-WC70GaDEcCKitEE6nDCmDR8JieG1kSCKqoTyFtBKXbF0dcVte4t5XAWQvcWlkmOr5LhUcgvwRior62r88X6_Gon42_yIjen_VfL835IXsGvvyoizS6jnq7W-MhAkF23Y6Xz22m6ifQFgCNuF |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LTwIxEG4IHtSDD9SIzx68Fgrtvo4GJahATISE26bPuAaB4HL1t9t2u4qJ0cTTJrvtZjNtp9-3_WYGgCuScB3KdoJs6nREBU4QDwhFQsQW0XJFmQ1OHgzD3pjeT4JJBXTKWBgrq_S-v_Dpzlv7O01vzeYiy5pPhj2049ju3-48zvD2DRqQyOr6Gu9fOg-bAq740WKWvmlexs85kVf2amP5G7aGuDvtJOTn_Wltz-nugR0PFuF18T37oKJmNbDrgSP0y_KtBrbXsgoegMebFZsibitmPEMm2cJ6NGjzaDplI8xLrKqW0FzgXIjpSpoXLhz6hkuFMulFRG7cDsG4ezvq9JAvnICEYQA5CnkroSEPBJWMasYI1ZhEWoRtwYRKtMBEYhHGLIqlNITFMElOsCYykS0bW0uOQHU2n6ljALVhRFgqg3MYplQZNhJjw2oTjiWRmrA6IKW5UuGzitviFtO0lI-9pIWRU2vktDByHaDPXosiq8Yf7aNyJNJvsyM1jv_Xnif_7nkJNnujQT_t3w0fTsGWfVJoz85ANV-u1LkBIzm_cJPtAzme3FA |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Dual-branch+adaptive+attention+transformer+for+occluded+person+re-identification&rft.jtitle=Image+and+vision+computing&rft.au=Lu%2C+Yunhua&rft.au=Jiang%2C+Mingzi&rft.au=Liu%2C+Zhi&rft.au=Mu%2C+Xinyu&rft.date=2023-03-01&rft.issn=0262-8856&rft.volume=131&rft.spage=104633&rft_id=info:doi/10.1016%2Fj.imavis.2023.104633&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_imavis_2023_104633 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0262-8856&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0262-8856&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0262-8856&client=summon |