{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:55:17Z","timestamp":1781538917340,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"funder":[{"name":"The Key Technology R&D Program of Ningbo","award":["2024Z259"],"award-info":[{"award-number":["2024Z259"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810579","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"1166-1173","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["LTA-Gait: In-Network Temporal Activation of Large Vision Models for Gait Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7012-0480","authenticated-orcid":false,"given":"Qichao","family":"Zhang","sequence":"first","affiliation":[{"name":"Dalian Ocean University, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4381-7988","authenticated-orcid":false,"given":"Genlang","family":"Chen","sequence":"additional","affiliation":[{"name":"NingboTech University, Ningbo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9562-5278","authenticated-orcid":false,"given":"Chengcheng","family":"Jia","sequence":"additional","affiliation":[{"name":"NingboTech University, Ningbo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2903-9411","authenticated-orcid":false,"given":"Jiajian","family":"Zhang","sequence":"additional","affiliation":[{"name":"NingboTech University, Ningbo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018126"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Shoufa Chen Chongjian Ge Zhan Tong Jiangliu Wang Yibing Song Jue Wang and Ping Luo. 2022. Adaptformer: Adapting vision transformers for scalable visual recognition. Advances in Neural Information Processing Systems 35 (2022) 16664\u201316678.","DOI":"10.52202\/068431-1212"},{"key":"e_1_3_3_1_4_2","unstructured":"Chao Fan Saihui Hou Yongzhen Huang and Shiqi Yu. 2023. Exploring deep models for practical gait recognition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.03301 (2023)."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00936"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27933"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01423"},{"key":"e_1_3_3_1_8_2","unstructured":"Albert Gu and Tri Dao. 2023. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.00752 (2023)."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00111"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32432"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01152"},{"key":"e_1_3_3_1_12_2","unstructured":"Kunchang Li Xinhao Li Yi Wang Yinan He Yali Wang Limin Wang and Yu Qiao. 2024. VideoMamba: State Space Model for Efficient Video Understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.06977 (2024)."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01328"},{"key":"e_1_3_3_1_14_2","unstructured":"Beibei Lin Shunli Zhang Ming Wang Lincheng Li and Xin Yu. 2022. Gaitgl: Learning discriminative global-local feature representations for gait recognition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.01380 (2022)."},{"key":"e_1_3_3_1_15_2","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby et\u00a0al. 2023. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.07193 (2023)."},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Junting Pan Ziyi Lin Xiatian Zhu Jing Shao and Hongsheng Li. 2022. St-adapter: Parameter-efficient image-to-video transfer learning. Advances in Neural Information Processing Systems 35 (2022) 26462\u201326477.","DOI":"10.52202\/068431-1919"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Yunjie Peng Kang Ma Yang Zhang and Zhiqiang He. 2024. Learning rich features for gait recognition by integrating skeletons and silhouettes. Multimedia Tools and Applications 83 3 (2024) 7273\u20137294.","DOI":"10.1007\/s11042-023-15483-x"},{"key":"e_1_3_3_1_18_2","unstructured":"Jilong Wang Saihui Hou Xianda Guo Yan Huang Yongzhen Huang Tianzhu Zhang and Liang Wang. 2025. Gaitc 3 i: Robust cross-covariate gait recognition via causal intervention. IEEE Transactions on Circuits and Systems for Video Technology (2025)."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCB62174.2024.10744509"},{"key":"e_1_3_3_1_20_2","unstructured":"Dingqiang Ye Chao Fan Zhanbo Huang Chengwen Luo Jianqiang Li Shiqi Yu and Xiaoming Liu. 2025. Biggergait: Unlocking gait recognition with layer-wise representations from large vision models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.18132 (2025)."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00027"},{"key":"e_1_3_3_1_22_2","first-page":"441","volume-title":"18th international conference on pattern recognition (ICPR\u201906)","author":"Yu Shiqi","year":"2006","unstructured":"Shiqi Yu, Daoliang Tan, and Tieniu Tan. 2006. A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. In 18th international conference on pattern recognition (ICPR\u201906) , Vol.\u00a04. IEEE, 441\u2013444."},{"key":"e_1_3_3_1_23_2","volume-title":"International Conference on Machine Learning (ICML)","author":"Zhu Lianghui","year":"2024","unstructured":"Lianghui Zhu, Bencheng Liao, Qian Zhang, Xinwen Wang, Wenyu Liu, and Xinggang Wang. 2024. Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Shinan Zou Chao Fan Jianbo Xiong Chuanfu Shen Shiqi Yu and Jin Tang. 2024. Cross-Covariate Gait Recognition: A Benchmark. Proceedings of the AAAI Conference on Artificial Intelligence 38 7 (Mar. 2024) 7855\u20137863.","DOI":"10.1609\/aaai.v38i7.28621"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:14:11Z","timestamp":1781536451000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810579"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":23,"alternative-id":["10.1145\/3805622.3810579","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810579","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}