{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T13:13:20Z","timestamp":1787318000646,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":76,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Key Research and Development Program of Chongqing","award":["cstc2021jscx-gksbX0032"],"award-info":[{"award-number":["cstc2021jscx-gksbX0032"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101351"],"award-info":[{"award-number":["62101351"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611803","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"5552-5561","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":44,"title":["All in One: Exploring Unified Vision-Language Tracking with Multi-Modal Alignment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9017-1828","authenticated-orcid":false,"given":"Chunhui","family":"Zhang","sequence":"first","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiaotong University & CloudWalk Technology Co., Ltd, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3092-0583","authenticated-orcid":false,"given":"Xin","family":"Sun","sequence":"additional","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiaotong University & CloudWalk Technology Co., Ltd, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2480-8607","authenticated-orcid":false,"given":"Yiqian","family":"Yang","sequence":"additional","affiliation":[{"name":"Northwest Polytechnical University & Shenzhen Research Institute of Big Data, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4497-0135","authenticated-orcid":false,"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5808-2761","authenticated-orcid":false,"given":"Qiong","family":"Liu","sequence":"additional","affiliation":[{"name":"CloudWalk Technology Co., Ltd, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9943-5482","authenticated-orcid":false,"given":"Xi","family":"Zhou","sequence":"additional","affiliation":[{"name":"CloudWalk Technology Co., Ltd, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3196-2347","authenticated-orcid":false,"given":"Yanfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University & Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"24206","article-title":"Vatt: transformers for multimodal self-supervised learning from raw video, audio and text","volume":"34","author":"Akbari Hassan","year":"2021","unstructured":"Hassan Akbari, Liangzhe Yuan, Rui Qian, Wei-Hong Chuang, Shih-Fu Chang, Yin Cui, and Boqing Gong. 2021. Vatt: transformers for multimodal self-supervised learning from raw video, audio and text. Advances in Neural Information Processing Systems, 34, 24206--24221.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_2_1","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac Jean-Baptiste","year":"2022","unstructured":"Jean-Baptiste Alayrac et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in Neural Information Processing Systems, 35, 23716--23736.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"e_1_3_2_1_4_1","volume-title":"Multi-modal machine learning: a survey and taxonomy","author":"Tadas","unstructured":"Tadas Baltru?aitis, Chaitanya Ahuja, and Louis-Philippe Morency. 2018. Multi-modal machine learning: a survey and taxonomy. IEEE transactions on pattern analysis and machine intelligence, 41, 2, 423--443."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00628"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision, 357--366","author":"Richard Chen Chun-Fu","year":"2021","unstructured":"Chun-Fu Richard Chen, Quanfu Fan, and Rameswar Panda. 2021. Crossvit: cross-attention multi-scale vision transformer for image classification. In Proceedings of the IEEE\/CVF international conference on computer vision, 357--366."},{"key":"e_1_3_2_1_10_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Xi","unstructured":"Xi Chen et al. 2022. Pali: a jointly-scaled multilingual language-image model. The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00479"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Machine Learning, 7480--7512","author":"Mostafa","unstructured":"Mostafa Dehghani et al. 2023. Scaling vision transformers to 22 billion parameters. International Conference on Machine Learning, 7480--7512."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of NAACL-HLT, 4171--4186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL-HLT, 4171--4186."},{"key":"e_1_3_2_1_18_1","volume-title":"International Conference on Learning Representations.","author":"Alexey","unstructured":"Alexey Dosovitskiy et al. 2020. An image is worth 16x16 words: transformers for image recognition at scale. International Conference on Learning Representations."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 5374--5383","author":"Heng","unstructured":"Heng Fan et al. 2019. Lasot: a high-quality benchmark for large-scale single object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 5374--5383."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01387-y"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"e_1_3_2_1_24_1","unstructured":"Mingzhe Guo Zhipeng Zhang Heng Fan and Liping Jing. 2022. Divert more attention to vision-language tracking. arXiv preprint arXiv:2207.01076."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6758"},{"key":"e_1_3_2_1_27_1","volume-title":"Got-10k: a large high-diversity benchmark for generic object tracking in the wild","author":"Huang Lianghua","unstructured":"Lianghua Huang, Xin Zhao, and Kaiqi Huang. 2019. Got-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE transactions on pattern analysis and machine intelligence, 43, 5, 1562--1577."},{"key":"e_1_3_2_1_28_1","volume-title":"International Conference on Machine Learning, 5583--5594","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. Vilt: vision-and-language transformer without convolution or region supervision. In International Conference on Machine Learning, 5583--5594."},{"key":"e_1_3_2_1_29_1","unstructured":"Alexander Kirillov et al. 2023. Segment anything. arXiv preprint arXiv:2304.02643."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Anis Koubaa. 2023. Gpt-4 vs. gpt-3.5: a concise showdown.","DOI":"10.36227\/techrxiv.22312330.v2"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna et al. 2017. Visual genome: connecting language and vision using crowdsourced dense image annotations. International journal of computer vision 123 1 32--73.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01435"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00441"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00515"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"e_1_3_2_1_37_1","unstructured":"Junnan Li Ramprasaath Selvaraju Akhilesh Gotmare Shafiq Joty Caiming Xiong and Steven Chu Hong Hoi. 2021. Align before fuse: vision and language representation learning with momentum distillation. Advances in neural information processing systems 34 9694--9705."},{"key":"e_1_3_2_1_38_1","unstructured":"Liunian Harold Li Mark Yatskar Da Yin Cho-Jui Hsieh and Kai-Wei Chang. 2019. Visualbert: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.777"},{"key":"e_1_3_2_1_40_1","first-page":"16743","article-title":"Swin-track: a simple and strong baseline for transformer tracking","volume":"35","author":"Lin Liting","year":"2022","unstructured":"Liting Lin, Heng Fan, Zhipeng Zhang, Yong Xu, and Haibin Ling. 2022. Swin-track: a simple and strong baseline for transformer tracking. Advances in Neural Information Processing Systems, 35, 16743--16754.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_42_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101."},{"key":"e_1_3_2_1_43_1","unstructured":"Jiasen Lu Dhruv Batra Devi Parikh and Stefan Lee. 2019. Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems 32."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475349"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"e_1_3_2_1_46_1","unstructured":"Aaron van den Oord Yazhe Li and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748."},{"key":"e_1_3_2_1_47_1","unstructured":"OpenAI. 2023. Chatgpt. https:\/\/openai.com\/blog\/chatgpt\/. (2023)."},{"key":"e_1_3_2_1_48_1","unstructured":"OpenAI. 2023. Gpt-4. https:\/\/cdn.openai.com\/papers\/gpt-4.pdf. (2023)."},{"key":"e_1_3_2_1_49_1","volume-title":"International Conference on Machine Learning, 8748--8763","author":"Alec","unstructured":"Alec Radford et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning, 8748--8763."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01522"},{"key":"e_1_3_2_1_52_1","volume-title":"Digital video processing","author":"Tekalp A Murat","unstructured":"A Murat Tekalp. 2015. Digital video processing. Prentice Hall Press."},{"key":"e_1_3_2_1_53_1","volume-title":"International conference on machine learning, 10347--10357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In International conference on machine learning, 10347--10357."},{"key":"e_1_3_2_1_54_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00661"},{"key":"e_1_3_2_1_56_1","unstructured":"Alex Jinpeng Wang et al. 2022. All in one: exploring unified video-language pre-training. arXiv preprint arXiv:2203.07303."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"e_1_3_2_1_58_1","volume-title":"International Conference on Machine Learning, 9929--9939","author":"Wang Tongzhou","year":"2020","unstructured":"Tongzhou Wang and Phillip Isola. 2020. Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In International Conference on Machine Learning, 9929--9939."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"crossref","unstructured":"Wenhui Wang et al. 2022. Image as a foreign language: beit pretraining for all vision and vision-language tasks. arXiv preprint arXiv:2208.10442.","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"e_1_3_2_1_63_1","volume-title":"Object tracking benchmark","author":"Wu Yi","year":"1834","unstructured":"Yi Wu, Jongwoo Lim, and Ming-Hsuan Yang. 2015. Object tracking benchmark. IEEE transactions on pattern analysis and machine intelligence, 37, 9, 1834--1848."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"e_1_3_2_1_65_1","unstructured":"Jiange Yang Sheng Guo Gangshan Wu and Limin Wang. 2023. Comae: single model hybrid pre-training on small-scale RGB-D datasets. arXiv preprint arXiv: 2302.06148."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3038720"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413959"},{"key":"e_1_3_2_1_70_1","article-title":"Webuav-3m: a benchmark for unveiling the power of million-scale deep uav tracking","author":"Zhang Chunhui","year":"2022","unstructured":"Chunhui Zhang, Guanjie Huang, Li Liu, Shan Huang, Yinan Yang, Xiang Wan, Shiming Ge, and Dacheng Tao. 2022. Webuav-3m: a benchmark for unveiling the power of million-scale deep uav tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"crossref","unstructured":"Lisai Zhang Hongfa Wu Qingcai Chen Yimeng Deng Joanna Siebert Zhonghua Li Yunpeng Han Dejiang Kong and Zhao Cao. 2022. Vldeformer: vision-language decomposed transformer for fast cross-modal retrieval. Knowledge-Based Systems 109316.","DOI":"10.1016\/j.knosys.2022.109316"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01309"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02217"},{"key":"e_1_3_2_1_76_1","unstructured":"Xueyan Zou Jianwei Yang Hao Zhang Feng Li Linjie Li Jianfeng Gao and Yong Jae Lee. 2023. Segment everything everywhere all at once. arXiv preprint arXiv:2304.06718."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611803","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:11:12Z","timestamp":1755821472000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611803"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":76,"alternative-id":["10.1145\/3581783.3611803","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611803","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}