{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:14:25Z","timestamp":1765340065381,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20514"],"award-info":[{"award-number":["U21A20514"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Science and Technology Plan Project on the Future Industry Fields of Xiamen City","award":["3502Z20241027"],"award-info":[{"award-number":["3502Z20241027"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755402","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:38:54Z","timestamp":1761377934000},"page":"489-498","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["OV-VOD: Open-Vocabulary Video Object Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4081-5703","authenticated-orcid":false,"given":"Zhihong","family":"Zheng","sequence":"first","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China and Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5723-4381","authenticated-orcid":false,"given":"Yang","family":"Cao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China and Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8734-1021","authenticated-orcid":false,"given":"Junlong","family":"Gao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China and Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6913-9786","authenticated-orcid":false,"given":"Hanzi","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China and Fujian Key Laboratory of Sensing and Computing for Smart City, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00172"},{"key":"e_1_3_2_1_2_1","first-page":"33781","article-title":"Bridging the gap between object and image-level representations for open-vocabulary detection","volume":"35","author":"Bangalath Hanoona","year":"2022","unstructured":"Hanoona Bangalath, Muhammad Maaz, Muhammad Uzair Khattak, Salman H Khan, and Fahad Shahbaz Khan. 2022. Bridging the gap between object and image-level representations for open-vocabulary detection. Advances in Neural Information Processing Systems, Vol. 35 (2022), 33781-33794.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32250"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the European Conference on Computer Vision. 753-771","author":"Damen Dima","year":"2018","unstructured":"Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, and Michael Wray. 2018. Scaling egocentric vision: The dataset. In Proceedings of the European Conference on Computer Vision. 753-771."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_26"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00712"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"e_1_3_2_1_12_1","volume-title":"European Conference on Computer Vision. Springer, 225-241","author":"Fang Hao","year":"2024","unstructured":"Hao Fang, Peng Wu, Yawei Li, Xinxin Zhang, and Xiankai Lu. 2024. Unified embedding alignment for open-vocabulary video instance segmentation. In European Conference on Computer Vision. Springer, 225-241."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_16"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_2_1_15_1","volume-title":"Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921","author":"Gu Xiuye","year":"2021","unstructured":"Xiuye Gu, Tsung-Yi Lin, Weicheng Kuo, and Yin Cui. 2021. Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00401"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413927"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3094533"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01507-2"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3164253"},{"key":"e_1_3_2_1_22_1","volume-title":"Prajit Ramachandran, Mohammad Babaeizadeh, Honghui Shi, Jianan Li, Shuicheng Yan, and Thomas S Huang.","author":"Han Wei","year":"2016","unstructured":"Wei Han, Pooya Khorrami, Tom Le Paine, Prajit Ramachandran, Mohammad Babaeizadeh, Honghui Shi, Jianan Li, Shuicheng Yan, and Thomas S Huang. 2016. Seq-nms for video object detection. arXiv preprint arXiv:1602.08465 (2016)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475285"},{"key":"e_1_3_2_1_26_1","first-page":"31265","article-title":"Minvis: A minimal video instance segmentation framework without video-based training","volume":"35","author":"Huang De-An","year":"2022","unstructured":"De-An Huang, Zhiding Yu, and Anima Anandkumar. 2022. Minvis: A minimal video instance segmentation framework without video-based training. Advances in Neural Information Processing Systems, Vol. 35 (2022), 31265-31277.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the International Conference on Machine Learning. 4904-4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In Proceedings of the International Conference on Machine Learning. 4904-4916."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_2"},{"key":"e_1_3_2_1_29_1","unstructured":"Glenn Jocher Jing Qiu and Ayush Chaurasia. 2023. Ultralytics YOLO . https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2736553"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00539"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413583"},{"volume-title":"Proceedings of the European Conference on Computer Vision. 740-755","author":"Lin Tsung-Yi","key":"e_1_3_2_1_34_1","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common objects in context. In Proceedings of the European Conference on Computer Vision. 740-755."},{"key":"e_1_3_2_1_35_1","first-page":"72983","article-title":"Scaling open-vocabulary object detection","volume":"36","author":"Minderer Matthias","year":"2023","unstructured":"Matthias Minderer, Alexey Gritsenko, and Neil Houlsby. 2023. Scaling open-vocabulary object detection. Advances in Neural Information Processing Systems, Vol. 36 (2023), 72983-73007.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3285136"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3238818"},{"key":"e_1_3_2_1_38_1","first-page":"1","article-title":"IMC-Det: Intra-inter modality contrastive learning for video object detection","volume":"133","author":"Qi Qiang","year":"2024","unstructured":"Qiang Qi, Zhenyu Qiu, Yan Yan, Yang Lu, and Hanzi Wang. 2024. IMC-Det: Intra-inter modality contrastive learning for video object detection. International Journal of Computer Vision, Vol. 133, 2 (2024), 1-20.","journal-title":"International Journal of Computer Vision"},{"key":"e_1_3_2_1_39_1","volume-title":"International Conference on Machine Learning. 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. 8748-8763."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612407"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16365"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02076-w"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00622"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00681"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00931"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612090"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3552694"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223955"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3474698"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.441"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755402","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:09:51Z","timestamp":1765339791000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755402"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":65,"alternative-id":["10.1145\/3746027.3755402","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755402","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}