{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:31:21Z","timestamp":1781587881830,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["NSFC No. 62272184"],"award-info":[{"award-number":["NSFC No. 62272184"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["GZC20230894, 2024M751012"],"award-info":[{"award-number":["GZC20230894, 2024M751012"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681104","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"2021-2030","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Autogenic Language Embedding for Coherent Point Tracking"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6651-2027","authenticated-orcid":false,"given":"Zikai","family":"Song","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4550-0060","authenticated-orcid":false,"given":"Ying","family":"Tang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2389-4827","authenticated-orcid":false,"given":"Run","family":"Luo","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8471-2014","authenticated-orcid":false,"given":"Lintao","family":"Ma","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7057-0402","authenticated-orcid":false,"given":"Junqing","family":"Yu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4122-3767","authenticated-orcid":false,"given":"Yi-Ping Phoebe","family":"Chen","sequence":"additional","affiliation":[{"name":"La Trobe University, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1189-1254","authenticated-orcid":false,"given":"Wei","family":"Yang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"A framework for the robust estimation of optical flow. In 1993 (4th) International Conference on Computer Vision","author":"Black Michael J","unstructured":"Michael J Black and Padmanabhan Anandan. 1993. A framework for the robust estimation of optical flow. In 1993 (4th) International Conference on Computer Vision. IEEE, 231--236."},{"key":"e_1_3_2_1_2_1","volume-title":"International journal of computer vision","author":"Bruhn Andr\u00e9s","year":"2005","unstructured":"Andr\u00e9s Bruhn, Joachim Weickert, and Christoph Schn\u00f6rr. 2005. Lucas\/Kanade meets Horn\/Schunck: Combining local and global optic flow methods. International journal of computer vision, Vol. 61 (2005), 211--231."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_5_1","volume-title":"Kucas Smaira, Yusuf Aytar, Joao Carreira, Andrew Zisserman, and Yi Yang.","author":"Doersch Carl","year":"2022","unstructured":"Carl Doersch, Ankush Gupta, Larisa Markeeva, Adria Recasens Continente, Kucas Smaira, Yusuf Aytar, Joao Carreira, Andrew Zisserman, and Yi Yang. 2022. TAP-Vid: A Benchmark for Tracking Any Point in a Video. In NeurIPS Datasets Track."},{"key":"e_1_3_2_1_6_1","volume-title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement. ICCV","author":"Doersch Carl","year":"2023","unstructured":"Carl Doersch, Yi Yang, Mel Vecerik, Dilara Gokay, Ankush Gupta, Yusuf Aytar, Joao Carreira, and Andrew Zisserman. 2023. TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement. ICCV (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR (2021)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"e_1_3_2_1_10_1","first-page":"4446","article-title":"Divert more attention to vision-language tracking","volume":"35","author":"Guo Mingzhe","year":"2022","unstructured":"Mingzhe Guo, Zhipeng Zhang, Heng Fan, and Liping Jing. 2022. Divert more attention to vision-language tracking. Advances in Neural Information Processing Systems, Vol. 35 (2022), 4446--4460.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Adam W Harley Zhaoyuan Fang and Katerina Fragkiadaki. 2022. Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories. In ECCV.","DOI":"10.1007\/978-3-031-20047-2_4"},{"key":"e_1_3_2_1_12_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840--6851."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_40"},{"key":"e_1_3_2_1_15_1","volume-title":"CoTracker: It is Better to Track Together. arXiv:2307.07635","author":"Karaev Nikita","year":"2023","unstructured":"Nikita Karaev, Ignacio Rocco, Benjamin Graham, Natalia Neverova, Andrea Vedaldi, and Christian Rupprecht. 2023. CoTracker: It is Better to Track Together. arXiv:2307.07635 (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547771"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the ICLR.","author":"Loshchilov Ilya","year":"2018","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Decoupled weight decay regularization. In Proceedings of the ICLR."},{"key":"e_1_3_2_1_18_1","volume-title":"IJCAI'81: 7th international joint conference on Artificial intelligence","volume":"2","author":"Lucas Bruce D","year":"1981","unstructured":"Bruce D Lucas and Takeo Kanade. 1981. An iterative image registration technique with an application to stereo vision. In IJCAI'81: 7th international joint conference on Artificial intelligence, Vol. 2. 674--679."},{"key":"e_1_3_2_1_19_1","volume-title":"Levine (Eds.)","volume":"36","author":"Luo Grace","year":"2023","unstructured":"Grace Luo, Lisa Dunlap, Dong Huk Park, Aleksander Holynski, and Trevor Darrell. 2023. Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence. In Advances in Neural Information Processing Systems, A. Oh, T. Neumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 47500--47510. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/942032b61720a3fd64897efe46237c81-Paper-Conference.pdf"},{"key":"e_1_3_2_1_20_1","volume-title":"Deem: Diffusion models serve as the eyes of large language models for image perception. arXiv preprint arXiv:2405.15232","author":"Luo Run","year":"2024","unstructured":"Run Luo, Yunshui Li, Longze Chen, Wanwei He, Ting-En Lin, Ziqiang Liu, Lei Zhang, Zikai Song, Xiaobo Xia, Tongliang Liu, et al. 2024. Deem: Diffusion models serve as the eyes of large language models for image perception. arXiv preprint arXiv:2405.15232 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"DiffusionTrack: Diffusion Model For Multi-Object Tracking. arXiv preprint arXiv:2308.09905","author":"Luo Run","year":"2023","unstructured":"Run Luo, Zikai Song, Lintao Ma, Jinlin Wei, Wei Yang, and Min Yang. 2023. DiffusionTrack: Diffusion Model For Multi-Object Tracking. arXiv preprint arXiv:2308.09905 (2023)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475349"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_21"},{"key":"e_1_3_2_1_24_1","volume-title":"Clipcap: Clip prefix for image captioning. arXiv preprint arXiv:2111.09734","author":"Mokady Ron","year":"2021","unstructured":"Ron Mokady, Amir Hertz, and Amit H Bermano. 2021. Clipcap: Clip prefix for image captioning. arXiv preprint arXiv:2111.09734 (2021)."},{"key":"e_1_3_2_1_25_1","volume-title":"Jon\u00e1vs vSer'ch, and Jivr\u00ed Matas","author":"Neoral Michal","year":"2023","unstructured":"Michal Neoral, Jon\u00e1vs vSer'ch, and Jivr\u00ed Matas. 2023. MFT: Long-Term Tracking of Every Pixel. arXiv preprint arXiv:2305.12998 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Kranthi Kiran GV, et al","author":"Peng Bo","year":"2023","unstructured":"Bo Peng, Eric Alcaide, Quentin Anthony, Alon Albalak, Samuel Arcadinho, Huanqi Cao, Xin Cheng, Michael Chung, Matteo Grella, Kranthi Kiran GV, et al. 2023. Rwkv: Reinventing rnns for the transformer era. arXiv preprint arXiv:2305.13048 (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"The 2017 davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675","author":"Pont-Tuset Jordi","year":"2017","unstructured":"Jordi Pont-Tuset, Federico Perazzi, Sergi Caelles, Pablo Arbel\u00e1ez, Alex Sorkine-Hornung, and Luc Van Gool. 2017. The 2017 davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675 (2017)."},{"key":"e_1_3_2_1_28_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_31_1","volume-title":"Denoising Diffusion Implicit Models. arXiv:2010.02502 (October","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising Diffusion Implicit Models. arXiv:2010.02502 (October 2020). https:\/\/arxiv.org\/abs\/2010.02502"},{"key":"e_1_3_2_1_32_1","volume-title":"Yi-Ping Phoebe Chen, and Wei Yang","author":"Song Zikai","year":"2023","unstructured":"Zikai Song, Run Luo, Junqing Yu, Yi-Ping Phoebe Chen, and Wei Yang. 2023. Compact transformer tracker with correlative masked modeling. arXiv preprint arXiv:2301.10938 (2023)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00859"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"e_1_3_2_1_35_1","volume-title":"Retentive network: A successor to transformer for large language models. arXiv preprint arXiv:2307.08621","author":"Sun Yutao","year":"2023","unstructured":"Yutao Sun, Li Dong, Shaohan Huang, Shuming Ma, Yuqing Xia, Jilong Xue, Jianyong Wang, and Furu Wei. 2023. Retentive network: A successor to transformer for large language models. arXiv preprint arXiv:2307.08621 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=ypOiXjdfnU","author":"Tang Luming","year":"2023","unstructured":"Luming Tang, Menglin Jia, Qianqian Wang, Cheng Perng Phoo, and Bharath Hariharan. 2023. Emergent Correspondence from Image Diffusion. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=ypOiXjdfnU"},{"key":"e_1_3_2_1_37_1","volume-title":"Raft: Recurrent all-pairs field transforms for optical flow. In Proceedings of the","author":"Teed Zachary","year":"2020","unstructured":"Zachary Teed and Jia Deng. 2020. Raft: Recurrent all-pairs field transforms for optical flow. In Proceedings of the ECCV. Springer, 402--419."},{"key":"e_1_3_2_1_38_1","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume":"34","author":"Tsimpoukelli Maria","year":"2021","unstructured":"Maria Tsimpoukelli, Jacob L Menick, Serkan Cabi, SM Eslami, Oriol Vinyals, and Felix Hill. 2021. Multimodal few-shot learning with frozen language models. Advances in Neural Information Processing Systems, Vol. 34 (2021), 200--212.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_39_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In NIPS. 5998--6008."},{"key":"e_1_3_2_1_40_1","volume-title":"Tracking Everything Everywhere All at Once. arXiv preprint arXiv:2306.05422","author":"Wang Qianqian","year":"2023","unstructured":"Qianqian Wang, Yen-Yu Chang, Ruojin Cai, Zhengqi Li, Bharath Hariharan, Aleksander Holynski, and Noah Snavely. 2023. Tracking Everything Everywhere All at Once. arXiv preprint arXiv:2306.05422 (2023)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.615"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547851"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611803"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01707"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01818"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611750"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681104","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:52Z","timestamp":1750294672000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681104"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":48,"alternative-id":["10.1145\/3664647.3681104","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681104","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}