{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:16:24Z","timestamp":1777655784325,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":49,"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":[{"name":"Guangdong Provincial Natural Science Foundation for Outstanding Youth Team Project","award":["2024B1515040010"],"award-info":[{"award-number":["2024B1515040010"]}]},{"name":"China National Key R&D Program","award":["2023YFE0202700"],"award-info":[{"award-number":["2023YFE0202700"]}]},{"name":"Key-Area Research and Development Program of Guangzhou City","award":["2023B01J0022"],"award-info":[{"award-number":["2023B01J0022"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302170"],"award-info":[{"award-number":["62302170"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/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":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680833","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"1437-1446","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["VrdONE: One-stage Video Visual Relation Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9207-9070","authenticated-orcid":false,"given":"Xinjie","family":"Jiang","sequence":"first","affiliation":[{"name":"South China University of Technology, Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0344-2439","authenticated-orcid":false,"given":"Chenxi","family":"Zheng","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8006-3663","authenticated-orcid":false,"given":"Xuemiao","family":"Xu","sequence":"additional","affiliation":[{"name":"South China University of Technology & Guangdong Engineering Center for Large Model and GenAI Technology, Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6621-0594","authenticated-orcid":false,"given":"Bangzhen","family":"Liu","sequence":"additional","affiliation":[{"name":"South China University of Technology & State Key Laboratory of Subtropical Building and Urban Science, Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8196-1051","authenticated-orcid":false,"given":"Weiying","family":"Zheng","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7662-9831","authenticated-orcid":false,"given":"Huaidong","family":"Zhang","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3802-4644","authenticated-orcid":false,"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_2_1_2_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01323"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"e_1_3_2_1_7_1","volume-title":"Per-pixel classification is not all you need for semantic segmentation. Advances in Neural Information Processing Systems","author":"Cheng Bowen","year":"2021","unstructured":"Bowen Cheng, Alex Schwing, and Alexander Kirillov. 2021. Per-pixel classification is not all you need for semantic segmentation. Advances in Neural Information Processing Systems (2021), 17864--17875."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"e_1_3_2_1_9_1","unstructured":"Krzysztof Choromanski Valerii Likhosherstov David Dohan Xingyou Song Andreea Gane Tamas Sarlos Peter Hawkins Jared Davis Afroz Mohiuddin Lukasz Kaiser et al. 2020. Rethinking attention with performers. arXiv preprint arXiv:2009.14794 (2020)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.65"},{"key":"e_1_3_2_1_11_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01889"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.40"},{"key":"e_1_3_2_1_16_1","volume-title":"Stereo object proposals","author":"Huang Shao","year":"2016","unstructured":"Shao Huang, Weiqiang Wang, Shengfeng He, and Rynson WH Lau. 2016. Stereo object proposals. IEEE Transactions on Image Processing (2016), 671--683."},{"key":"e_1_3_2_1_17_1","volume-title":"Egocentric temporal action proposals","author":"Huang Shao","year":"2017","unstructured":"Shao Huang, Weiqiang Wang, Shengfeng He, and Rynson WH Lau. 2017. Egocentric temporal action proposals. IEEE Transactions on Image Processing (2017), 764--777."},{"key":"e_1_3_2_1_18_1","volume-title":"Fractalnet: Ultra-deep neural networks without residuals. arXiv preprint arXiv:1605.07648","author":"Larsson Gustav","year":"2016","unstructured":"Gustav Larsson, Michael Maire, and Gregory Shakhnarovich. 2016. Fractalnet: Ultra-deep neural networks without residuals. arXiv preprint arXiv:1605.07648 (2016)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475540"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01085"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2902784"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_27_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"e_1_3_2_1_29_1","volume-title":"Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351058"},{"key":"e_1_3_2_1_32_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_33_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems (2015)."},{"key":"e_1_3_2_1_34_1","volume-title":"The watershed transform: Definitions, algorithms and parallelization strategies. Fundamenta Informaticae","author":"Roerdink Jos BTM","year":"2000","unstructured":"Jos BTM Roerdink and Arnold Meijster. 2000. The watershed transform: Definitions, algorithms and parallelization strategies. Fundamenta Informaticae (2000), 187--228."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325056"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475263"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123380"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413764"},{"key":"e_1_3_2_1_39_1","volume-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. Advances in Neural Information Processing Systems","author":"Tong Zhan","year":"2022","unstructured":"Zhan Tong, Yibing Song, Jue Wang, and Limin Wang. 2022. Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. Advances in Neural Information Processing Systems (2022), 10078--10093."},{"key":"e_1_3_2_1_40_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani Ashish","year":"2017","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, Vol. 30 (2017)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"e_1_3_2_1_42_1","volume-title":"Actionclip: A new paradigm for video action recognition. arXiv preprint arXiv:2109.08472","author":"Wang Mengmeng","year":"2021","unstructured":"Mengmeng Wang, Jiazheng Xing, and Yong Liu. 2021. Actionclip: A new paradigm for video action recognition. arXiv preprint arXiv:2109.08472 (2021)."},{"key":"e_1_3_2_1_43_1","unstructured":"Meng Wei Long Chen Wei Ji Xiaoyu Yue and Roger Zimmermann. 2023. In Defense of Clip-based Video Relation Detection. arXiv preprint arXiv:2307.08984 (2023)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"e_1_3_2_1_45_1","volume-title":"What and when to look?: Temporal span proposal network for video relation detection. arXiv preprint arXiv:2107.07154","author":"Woo Sangmin","year":"2021","unstructured":"Sangmin Woo, Junhyug Noh, and Kangil Kim. 2021. What and when to look?: Temporal span proposal network for video relation detection. arXiv preprint arXiv:2107.07154 (2021)."},{"key":"e_1_3_2_1_46_1","volume-title":"Transductive zero-shot action recognition via visually connected graph convolutional networks","author":"Xu Yangyang","year":"2020","unstructured":"Yangyang Xu, Chu Han, Jing Qin, Xuemiao Xu, Guoqiang Han, and Shengfeng He. 2020. Transductive zero-shot action recognition via visually connected graph convolutional networks. IEEE Transactions on Neural Networks and Learning Systems (2020), 3761--3769."},{"key":"e_1_3_2_1_47_1","volume-title":"VideoCoCa: Video-text modeling with zero-shot transfer from contrastive captioners. arXiv preprint arXiv:2212.04979","author":"Yan Shen","year":"2022","unstructured":"Shen Yan, Tao Zhu, Zirui Wang, Yuan Cao, Mi Zhang, Soham Ghosh, Yonghui Wu, and Jiahui Yu. 2022. VideoCoCa: Video-text modeling with zero-shot transfer from contrastive captioners. arXiv preprint arXiv:2212.04979 (2022)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01827"}],"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\/3664647.3680833","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:08Z","timestamp":1750295888000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680833"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":49,"alternative-id":["10.1145\/3664647.3680833","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680833","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"}}]}}