{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T17:35:23Z","timestamp":1776447323230,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":57,"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":["62206215"],"award-info":[{"award-number":["62206215"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China Postdoctoral Science Foundation","award":["2022M712537"],"award-info":[{"award-number":["2022M712537"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100002858","name":"China National Postdoctoral Program for Innovative Talents","doi-asserted-by":"publisher","award":["BX2021241"],"award-info":[{"award-number":["BX2021241"]}],"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\/3664647.3681513","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"1215-1224","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Rethinking the Architecture Design for Efficient Generic Event Boundary Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4896-3293","authenticated-orcid":false,"given":"Ziwei","family":"Zheng","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1382-9058","authenticated-orcid":false,"given":"Zechuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1363-0234","authenticated-orcid":false,"given":"Yulin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7361-9283","authenticated-orcid":false,"given":"Shiji","family":"Song","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7251-0988","authenticated-orcid":false,"given":"Gao","family":"Huang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8379-4915","authenticated-orcid":false,"given":"Le","family":"Yang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}]}],"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\/CVPR.2019.00129"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_29"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806386"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00508"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_8_1","volume-title":"Scikit-video: Video processing in python. In https:\/\/github.com\/scikit-video\/scikit-video.","author":"Developers S.-V.","year":"2015","unstructured":"S.-V. Developers. 2015. Scikit-video: Video processing in python. In https:\/\/github.com\/scikit-video\/scikit-video."},{"key":"e_1_3_2_1_9_1","volume-title":"IEEE Conf. Comput. Vis. Pattern Recog. 6508--6516","author":"Ding Li","year":"2018","unstructured":"Li Ding and Chenliang Xu. 2018. Weakly-supervised action segmentation with iterative soft boundary assignment. In IEEE Conf. Comput. Vis. Pattern Recog. 6508--6516."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00369"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"e_1_3_2_1_12_1","volume-title":"RefineTAD: Learning Proposal-free Refinement for Temporal Action Detection. In ACM Int. Conf. Multimedia. 135--143","author":"Feng Yue","year":"2023","unstructured":"Yue Feng, Zhengye Zhang, Rong Quan, Limin Wang, and Jie Qin. 2023. RefineTAD: Learning Proposal-free Refinement for Temporal Action Detection. In ACM Int. Conf. Multimedia. 135--143."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01232"},{"key":"e_1_3_2_1_14_1","volume-title":"Exploiting Temporal Motion Cues for Unsupervised Generic Event Boundary Detection. In IEEE Winter Conf. App. Comput. Vis. 6941--6950","author":"Gothe Sourabh Vasant","year":"2024","unstructured":"Sourabh Vasant Gothe, Vibhav Agarwal, Sourav Ghosh, Jayesh Rajkumar Vachhani, Pranay Kashyap, and Barath Raj Kandur Raja. 2024. What's in the Flow? Exploiting Temporal Motion Cues for Unsupervised Generic Event Boundary Detection. In IEEE Winter Conf. App. Comput. Vis. 6941--6950."},{"key":"e_1_3_2_1_15_1","volume-title":"Rishabh Khurana, and Pranay Kashyap.","author":"Gothe Sourabh Vasant","year":"2023","unstructured":"Sourabh Vasant Gothe, Jayesh Rajkumar Vachhani, Rishabh Khurana, and Pranay Kashyap. 2023. Self-Similarity is all You Need for Fast and Light-Weight Generic Event Boundary Detection. In ICASSP. IEEE, 1--5."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2018.8516556"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351056"},{"key":"e_1_3_2_1_19_1","volume-title":"Generic event boundary detection challenge at CVPR 2021 technical report: Cascaded temporal attention network (CASTANET). arXiv preprint arXiv:2107.00239","author":"Hong Dexiang","year":"2021","unstructured":"Dexiang Hong, Congcong Li, Longyin Wen, Xinyao Wang, and Libo Zhang. 2021. Generic event boundary detection challenge at CVPR 2021 technical report: Cascaded temporal attention network (CASTANET). arXiv preprint arXiv:2107.00239 (2021)."},{"key":"e_1_3_2_1_20_1","volume-title":"SC-Transformer: Structured Context Transformer for Generic Event Boundary Detection. arXiv preprint arXiv:2206.12634","author":"Hong Dexiang","year":"2022","unstructured":"Dexiang Hong, Xiaoqi Ma, Xinyao Wang, Congcong Li, Yufei Wang, and Longyin Wen. 2022. SC-Transformer: Structured Context Transformer for Generic Event Boundary Detection. arXiv preprint arXiv:2206.12634 (2022)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_9"},{"key":"e_1_3_2_1_23_1","volume-title":"Generic Event Boundary Detection in Video with Pyramid Features. arXiv preprint arXiv:2301.04288","author":"Huynh Van Thong","year":"2023","unstructured":"Van Thong Huynh, Hyung-Jeong Yang, Guee-Sang Lee, and Soo-Hyung Kim. 2023. Generic Event Boundary Detection in Video with Pyramid Features. arXiv preprint arXiv:2301.04288 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"Int. Conf. Machine Learn. 448--456","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Int. Conf. Machine Learn. 448--456."},{"key":"e_1_3_2_1_25_1","volume-title":"Winning the CVPR'2021 Kinetics-GEBD Challenge: Contrastive Learning Approach. arXiv preprint arXiv:2106","author":"Kang Hyolim","year":"2021","unstructured":"Hyolim Kang, Jinwoo Kim, Kyungmin Kim, Taehyun Kim, and Seon Joo Kim. 2021. Winning the CVPR'2021 Kinetics-GEBD Challenge: Contrastive Learning Approach. arXiv preprint arXiv:2106.11549 (2021)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01944"},{"key":"e_1_3_2_1_27_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_3"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00705"},{"key":"e_1_3_2_1_30_1","volume-title":"Structured context transformer for generic event boundary detection. arXiv preprint arXiv:2206.02985","author":"Li Congcong","year":"2022","unstructured":"Congcong Li, Xinyao Wang, Dexiang Hong, Yufei Wang, Libo Zhang, Tiejian Luo, and Longyin Wen. 2022. Structured context transformer for generic event boundary detection. arXiv preprint arXiv:2206.02985 (2022)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01358"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00858"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_36_1","volume-title":"Margin MCC: Chance-Robust Metric for Video Boundary Detection with Allowed Margin. In ACM Int. Conf. Multimedia. 2694--2703","author":"Mizufune Kosuke","year":"2023","unstructured":"Kosuke Mizufune, Shunsuke Tanaka, Toshihide Yukitake, and Tatsushi Matsubayashi. 2023. Margin MCC: Chance-Robust Metric for Video Boundary Detection with Allowed Margin. In ACM Int. Conf. Multimedia. 2694--2703."},{"key":"e_1_3_2_1_37_1","volume-title":"Post-Processing Temporal Action Detection. In IEEE Conf. Comput. Vis. Pattern Recog. 18837--18845","author":"Nag Sauradip","year":"2023","unstructured":"Sauradip Nag, Xiatian Zhu, Yi-Zhe Song, and Tao Xiang. 2023. Post-Processing Temporal Action Detection. In IEEE Conf. Comput. Vis. Pattern Recog. 18837--18845."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1002\/wcs.133"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00275"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00081"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"e_1_3_2_1_42_1","unstructured":"Mike Zheng Shou Stan LEI Linchao Zhu Xiaohan Wang et al. 2021. . https:\/\/sites.google.com\/view\/loveucvpr21\/track-1"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00797"},{"key":"e_1_3_2_1_44_1","unstructured":"Mike Zheng Shou Linchao Zhu Lorenzo Torresani Kristen Grauman Matt Feiszli et al. 2022. . https:\/\/sites.google.com\/view\/loveucvpr22\/track-1"},{"key":"e_1_3_2_1_45_1","unstructured":"Mike Zheng Shou Linchao Zhu Lorenzo Torresani Kristen Grauman Matt Feiszli et al. 2023. . https:\/\/sites.google.com\/view\/loveucvpr23\/track1"},{"key":"e_1_3_2_1_46_1","volume-title":"Transnet: A deep network for fast detection of common shot transitions. arXiv preprint arXiv:1906.03363","author":"Souvcek Tom\u00e1vs","year":"2019","unstructured":"Tom\u00e1vs Souvcek, Jaroslav Moravec, and Jakub Lokovc. 2019. Transnet: A deep network for fast detection of common shot transitions. arXiv preprint arXiv:1906.03363 (2019)."},{"key":"e_1_3_2_1_47_1","volume-title":"MAE-GEBD: Winning the CVPR'2023 LOVEU-GEBD Challenge. arXiv preprint arXiv:2306","author":"Sun Yuanxi","year":"2023","unstructured":"Yuanxi Sun, Rui He, Youzeng Li, Zuwei Huang, Feng Hu, Xu Cheng, and Jie Tang. 2023. MAE-GEBD: Winning the CVPR'2023 LOVEU-GEBD Challenge. arXiv preprint arXiv:2306.15704 (2023)."},{"key":"e_1_3_2_1_48_1","volume-title":"Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection","author":"Tan Jing","year":"2023","unstructured":"Jing Tan, Yuhong Wang, Gangshan Wu, and Limin Wang. 2023. Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection. IEEE Trans. Pattern Anal. Mach. Intell. (2023)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00335"},{"key":"e_1_3_2_1_50_1","volume-title":"Asian Conference on Computer Vision. Springer, 577--592","author":"Tang Shitao","year":"2018","unstructured":"Shitao Tang, Litong Feng, Zhanghui Kuang, Yimin Chen, and Wei Zhang. 2018. Fast video shot transition localization with deep structured models. In Asian Conference on Computer Vision. Springer, 577--592."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00631"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"e_1_3_2_1_54_1","volume-title":"Int. J. Comput. Vis.","author":"Zhang Libo","year":"2023","unstructured":"Libo Zhang, Xin Gu, Congcong Li, Tiejian Luo, and Heng Fan. 2023. Local Compressed Video Stream Learning for Generic Event Boundary Detection. Int. J. Comput. Vis. (2023), 1--18."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356080"},{"key":"e_1_3_2_1_56_1","volume-title":"Fine-grained Dynamic Network for Generic Event Boundary Detection. In Eur. Conf. Comput. Vis.","author":"Zheng Ziwei","year":"2024","unstructured":"Ziwei Zheng, Lijun He, Le Yang, and Fan Li. 2024. Fine-grained Dynamic Network for Generic Event Boundary Detection. In Eur. Conf. Comput. Vis."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3287201"}],"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\/3664647.3681513","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681513","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:48Z","timestamp":1750294668000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681513"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":57,"alternative-id":["10.1145\/3664647.3681513","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681513","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"}}]}}