{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:57:50Z","timestamp":1785488270979,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T00:00:00Z","timestamp":1765929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,17]]},"DOI":"10.1145\/3774521.3774616","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T07:34:24Z","timestamp":1785483264000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Retrieval Augmented Continuous Person Tracking and Re-Identification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4441-611X","authenticated-orcid":false,"given":"Madan","family":"Sharma","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, Rajiv Gandhi Institute of Petroleum Technology, Jais, Uttar Pradesh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3920-6929","authenticated-orcid":false,"given":"Aditya","family":"Singh","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Rajiv Gandhi Institute of Petroleum Technology, Jais, Uttar Pradesh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2035-8550","authenticated-orcid":false,"given":"Ashank","family":"Kunwar","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Rajiv Gandhi Institute of Petroleum Technology, Jais, Uttar Pradesh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4011-0453","authenticated-orcid":false,"given":"Nirbhay Kumar","family":"Tagore","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Rajiv Gandhi Institute of Petroleum Technology, Jais, Uttar Pradesh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3396-3587","authenticated-orcid":false,"given":"Sachin","family":"Kumar","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Rajiv Gandhi Institute of Petroleum Technology, Jais, Uttar Pradesh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Mohammadjavad Abbaspour and Mohammad\u00a0Ali Masnadi-Shirazi. 2022. Online multi-object tracking with \u03b4 -GLMB filter based on occlusion and identity switch handling. Image and Vision Computing 127 (2022) 104553.","DOI":"10.1016\/j.imavis.2022.104553"},{"key":"e_1_3_3_1_3_2","unstructured":"Favyen Bastani Songtao He and Samuel Madden. 2021. Self-supervised multi-object tracking with cross-input consistency. Advances in Neural Information Processing Systems 34 (2021) 13695\u201313706."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00103"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/246309"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00628"},{"key":"e_1_3_3_1_8_2","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Chen Peng","year":"2023","unstructured":"Peng Chen, Zhenyu Wang, Zilong Guo, Jin Wang, Yuwei Yang, and Yi Yang. 2023. Hybrid CNN-Transformer for Video-based Person Re-Identification. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_3_1_9_2","volume-title":"ECCV","author":"Cheng Yifan","year":"2022","unstructured":"Yifan Cheng, Yan Wang, Jian Lin, and et al.2022. Open-set person re-identification by multi-label learning with orthogonal Graph Neural Network. In ECCV."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Giovanni Ciaparrone Fernando Sanchez Siham Tabik Luigi Troiano Roberto Tagliaferri and Francisco Herrera. 2020. Deep learning in video multi-object tracking: A survey. Neurocomputing 381 (2020) 61\u201388.","DOI":"10.1016\/j.neucom.2019.11.023"},{"key":"e_1_3_3_1_11_2","first-page":"12852","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Dave Achal","year":"2021","unstructured":"Achal Dave, Anna Khoreva, and Deva Ramanan. 2021. TAO: A Large-Scale Benchmark for Tracking Any Object. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 12852\u201312862."},{"key":"e_1_3_3_1_12_2","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2003.09003","author":"Dendorfer Patrick","year":"2020","unstructured":"Patrick Dendorfer, Hamid Rezatofighi, Anton Milan, Jianan Shi, Daniel Cremers, Ian Reid, Stefan Roth, and Laura Leal-Taix\u00e9. 2020. MOT20: A benchmark for multi object tracking in crowded scenes. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2003.09003."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA56598.2022.10034575"},{"key":"e_1_3_3_1_14_2","volume-title":"ICLR","author":"Ge Yixiao","year":"2020","unstructured":"Yixiao Ge and et al.2020. Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification. In ICLR."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"e_1_3_3_1_16_2","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1703.07737","author":"Hermans Alexander","year":"2017","unstructured":"Alexander Hermans, Lucas Beyer, and Bastian Leibe. 2017. In defense of the triplet loss for person re-identification. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1703.07737."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21227-7_9"},{"key":"e_1_3_3_1_18_2","volume-title":"ECCV","author":"Hou Qiang","year":"2021","unstructured":"Qiang Hou and et al.2021. Enabling Unsupervised Person Re-Identification with OSNet-AIN. In ECCV."},{"key":"e_1_3_3_1_19_2","unstructured":"Glenn Jocher et\u00a0al. 2023. YOLO by Ultralytics (v8). https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Jeff Johnson Matthijs Douze and Herv\u00e9 J\u00e9gou. 2021. Billion-scale similarity search with GPUs. IEEE Transactions on Big Data 7 3 (2021) 535\u2013547.","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_3_1_21_2","unstructured":"Arne\u00a0Hoffhues Jonathon\u00a0Luiten. 2020. TrackEval. https:\/\/github.com\/JonathonLuiten\/TrackEval."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00117"},{"key":"e_1_3_3_1_23_2","volume-title":"Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW)","author":"Karami Amirhossein","year":"2024","unstructured":"Amirhossein Karami, Hassan Ghaemmaghami, and Ali Diba. 2024. Video Person Re-Identification via a Multi-Level Deep Network. In Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW)."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00406"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.782"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.27"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/74"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01375-2"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Jonathon Luiten Aljosa Osep Patrick Dendorfer Philip Torr Andreas Geiger Laura Leal-Taix\u00e9 and Bastian Leibe. 2020. HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking. International Journal of Computer Vision (2020) 1\u201331.","DOI":"10.1007\/s11263-020-01375-2"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Wenhan Luo Jinjun Xing Anton Milan Xiaowei Zhang Wei Liu and Tae-Kyun Kim. 2021. Multiple Object Tracking: A Literature Review. Artificial Intelligence 293 (2021) 103448.","DOI":"10.1016\/j.artint.2020.103448"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Cong Ma Fan Yang Yuan Li Huizhu Jia Xiaodong Xie and Wen Gao. 2021. Deep trajectory post-processing and position projection for single & multiple camera multiple object tracking. International Journal of Computer Vision 129 (2021) 3255\u20133278.","DOI":"10.1007\/s11263-021-01527-y"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.148"},{"key":"e_1_3_3_1_34_2","volume-title":"arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1603.00831","author":"Milan Anton","year":"2016","unstructured":"Anton Milan, Laura Leal-Taix\u00e9, Ian Reid, Stefan Roth, and Konrad Schindler. 2016. MOT16: A Benchmark for Multi-Object Tracking. In arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1603.00831."},{"key":"e_1_3_3_1_35_2","unstructured":"Ioannis Papakis Abhijit Sarkar and Anuj Karpatne. 2020. Gcnnmatch: Graph convolutional neural networks for multi-object tracking via sinkhorn normalization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.00067 (2020)."},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Jinlong Peng Tao Wang Weiyao Lin Jian Wang John See Shilei Wen and Erui Ding. 2020. TPM: Multiple object tracking with tracklet-plane matching. Pattern Recognition 107 (2020) 107480.","DOI":"10.1016\/j.patcog.2020.107480"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Athena Psalta Vasileios Tsironis and Konstantinos Karantzalos. 2024. Transformer-based assignment decision network for multiple object tracking. Computer Vision and Image Understanding 241 (2024) 103957.","DOI":"10.1016\/j.cviu.2024.103957"},{"key":"e_1_3_3_1_38_2","unstructured":"Facebook\u00a0AI Research. 2017. FAISS: A library for efficient similarity search. https:\/\/github.com\/facebookresearch\/faiss."},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00632"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_30"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00166"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.410"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Nirbhay\u00a0Kumar Tagore and Pratik Chattopadhyay. 2022. A bi-network architecture for occlusion handling in Person re-identification. Signal Image and Video Processing 16 4 (2022) 1071\u20131079.","DOI":"10.1007\/s11760-021-02056-4"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Nirbhay\u00a0Kumar Tagore Pratik Chattopadhyay and Lipo Wang. 2020. T-MAN: a neural ensemble approach for person re-identification using spatio-temporal information. Multimedia Tools and Applications 79 37 (2020) 28393\u201328409.","DOI":"10.1007\/s11042-020-09398-0"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"crossref","unstructured":"Nirbhay\u00a0Kumar Tagore Prathistith\u00a0Raj Medi and Pratik Chattopadhyay. 2024. Deep pixel regeneration for occlusion reconstruction in person re-identification. Multimedia Tools and Applications 83 2 (2024) 4443\u20134463.","DOI":"10.1007\/s11042-023-15322-z"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"crossref","unstructured":"Nirbhay\u00a0Kumar Tagore Ayushman Singh Sumanth Manche and Pratik Chattopadhyay. 2021. Person re-identification from appearance cues and deep Siamese features. Journal of Visual Communication and Image Representation 75 (2021) 103029.","DOI":"10.1016\/j.jvcir.2021.103029"},{"key":"e_1_3_3_1_49_2","unstructured":"Longhui Wang Shuangjie Gong Xiatian Zhang and Tao Xiang. 2021. Strong Baselines and a Data Augmentation Strategy for Video-based Person Re-Identification. Pattern Recognition 98 (2021) 107069."},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_45"},{"key":"e_1_3_3_1_51_2","volume-title":"ECCV","author":"Wang Zhi","year":"2022","unstructured":"Zhi Wang, Xin Jin, Wen Gao, and Yajie Ding. 2022. Open-set person re-identification via multi-distribution matching. In ECCV."},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00471"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123279"},{"key":"e_1_3_3_1_54_2","unstructured":"Xinshuo Weng and Kris\u00a0M. Kitani. 2023. Track One Thing Every Frame. International Journal of Computer Vision 131 (2023) 2345\u20132365."},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"e_1_3_3_1_56_2","volume-title":"ACM MM","author":"Wu Yifan","year":"2022","unstructured":"Yifan Wu and et al.2022. Open-world person re-identification with prototype-based incremental learning. In ACM MM."},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00543"},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3001693"},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00682"},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"crossref","unstructured":"Qin Yang Peizhi Wang Zihan Fang and Qiyong Lu. 2020. Focus on the visible regions: Semantic-guided alignment model for occluded person re-identification. Sensors 20 16 (2020) 4431.","DOI":"10.3390\/s20164431"},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"crossref","unstructured":"Yang Zhang Hao Sheng Yubin Wu Shuai Wang Weifeng Lyu Wei Ke and Zhang Xiong. 2020. Long-term tracking with deep tracklet association. IEEE Transactions on Image Processing 29 (2020) 6694\u20136706.","DOI":"10.1109\/TIP.2020.2993073"},{"key":"e_1_3_3_1_62_2","volume-title":"European Conference on Computer Vision (ECCV)","author":"Zhang Yifu","year":"2021","unstructured":"Yifu Zhang, Peize Sun, Yi Jiang, Dongdong Yu, Feng Weng, Zhenbo Yuan, Ping Luo, Wenyu Liu, and Xiangyu Wang. 2021. ByteTrack: Multi-Object Tracking by Associating Every Detection Box. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_3_1_63_2","doi-asserted-by":"crossref","unstructured":"Liang Zheng Yujia Huang Huchuan Lu and Yi Yang. 2019. Pose-invariant embedding for deep person re-identification. IEEE transactions on image processing 28 9 (2019) 4500\u20134509.","DOI":"10.1109\/TIP.2019.2910414"},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"e_1_3_3_1_65_2","unstructured":"Liang Zheng Yi Yang and Alexander\u00a0G Hauptmann. 2016. Person Re-identification: Past Present and Future. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1610.02984 (2016)."},{"key":"e_1_3_3_1_66_2","first-page":"923","volume-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence","author":"Zhou Kaiyang","year":"2021","unstructured":"Kaiyang Zhou, Yongxin Yang, Andrea Cavallaro, and Timothy\u00a0M. Hospedales. 2021. Learning Generalisable Omni-Scale Representations for Person Re-Identification. In IEEE Transactions on Pattern Analysis and Machine Intelligence , Vol.\u00a043. 923\u2013938."},{"key":"e_1_3_3_1_67_2","volume-title":"CVPR","author":"Zhu Fuxun","year":"2021","unstructured":"Fuxun Zhu, Xiaoliang Chen, Wenkai Ding, Qinghua Liu, Wangmeng Zuo, and Ling Shao. 2021. Open-world person re-identification via adaptive knowledge accumulation. In CVPR."}],"event":{"name":"ICVGIP 2025: Indian Conference on Computer Vision, Graphics, and Image Processing","location":"Mandi Himachal Pradesh India","acronym":"ICVGIP 2025"},"container-title":["Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774521.3774616","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:04:22Z","timestamp":1785485062000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774521.3774616"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":66,"alternative-id":["10.1145\/3774521.3774616","10.1145\/3774521"],"URL":"https:\/\/doi.org\/10.1145\/3774521.3774616","relation":{},"subject":[],"published":{"date-parts":[[2025,12,17]]},"assertion":[{"value":"2026-07-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}