{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:14:16Z","timestamp":1765008856339,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476249"],"award-info":[{"award-number":["62476249"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Key Research and Development Program","award":["2023C01215, 2024C01208"],"award-info":[{"award-number":["2023C01215, 2024C01208"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3743093.3770974","type":"proceedings-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:08:11Z","timestamp":1765008491000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SAAB: Enhancing Action Segmentation via Spatial Attention Pooling and Action-Background Classifier"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1459-8001","authenticated-orcid":false,"given":"Zhenhui","family":"Lou","sequence":"first","affiliation":[{"name":"Zhejiang University of Technology, HangZhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1159-9631","authenticated-orcid":false,"given":"Xia","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology, HangZhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2216-7720","authenticated-orcid":false,"given":"Fengjie","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology, HangZhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6490-7178","authenticated-orcid":false,"given":"Jiangtao","family":"Ye","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology, HangZhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7400-0578","authenticated-orcid":false,"given":"Xiaoping","family":"Jiang","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology, HangZhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2185-7006","authenticated-orcid":false,"given":"Zhenbo","family":"Cheng","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology, HangZhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","unstructured":"Patricia\u00a0S. Abril and Robert Plant. 2007. The patent holder\u2019s dilemma: Buy sell or troll?Commun. ACM 50 1 (Jan. 2007) 36\u201344. 10.1145\/1188913.1188915","DOI":"10.1145\/1188913.1188915"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00950"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_38"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_4"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_3_1_7_2","first-page":"6508","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Ding Li","year":"2018","unstructured":"Li Ding and Chenliang Xu. 2018. Weakly-supervised action segmentation with iterative soft boundary assignment. In Proceedings of the IEEE conference on computer vision and pattern recognition. 6508\u20136516."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01766"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00369"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02253"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Harshala Gammulle David Ahmedt-Aristizabal Simon Denman Lachlan Tychsen-Smith Lars Petersson and Clinton Fookes. 2023. Continuous human action recognition for human-machine interaction: a review. Comput. Surveys 55 13s (2023) 1\u201338.","DOI":"10.1145\/3587931"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01404"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Ho-Joong Kim and Seong-Whan Lee. 2024. Ensuring spatial scalability with temporal-wise spatial attentive pooling for temporal action detection. Neural Networks 176 (2024) 106321.","DOI":"10.1016\/j.neunet.2024.106321"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00930"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01721"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01791"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01266"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126349"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Longshuai Sheng and Ce Li. 2023. Weakly supervised coarse-to-fine learning for human action segmentation in HCI videos. Multimedia Tools and Applications 82 9 (2023) 12977\u201312993.","DOI":"10.1007\/s11042-022-13792-1"},{"key":"e_1_3_3_1_24_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Andrew Viterbi. 2003. Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE transactions on Information Theory 13 2 (2003) 260\u2013269.","DOI":"10.1109\/TIT.1967.1054010"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Jiaming Wang Zhenfeng Shao Xiao Huang Tao Lu Ruiqian Zhang and Xianwei Lv. 2021. Spatial\u2013temporal pooling for action recognition in videos. Neurocomputing 451 (2021) 265\u2013278.","DOI":"10.1016\/j.neucom.2021.04.071"},{"key":"e_1_3_3_1_27_2","unstructured":"Peiyao Wang and Haibin Ling. 2023. DIR-AS: Decoupling individual identification and temporal reasoning for action segmentation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.02110 (2023)."},{"key":"e_1_3_3_1_28_2","unstructured":"Tieqiao Wang and Sinisa Todorovic. 2025. End-to-End Action Segmentation Transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.06316 (2025)."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Huifen Xia and Yongzhao Zhan. 2020. A survey on temporal action localization. IEEE Access 8 (2020) 70477\u201370487.","DOI":"10.1109\/ACCESS.2020.2986861"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Qi Yang Tongwei Lu and Huabing Zhou. 2022. A spatio-temporal motion network for action recognition based on spatial attention. Entropy 24 3 (2022) 368.","DOI":"10.3390\/e24030368"},{"key":"e_1_3_3_1_31_2","unstructured":"Fangqiu Yi Hongyu Wen and Tingting Jiang. 2021. Asformer: Transformer for action segmentation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2110.08568 (2021)."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Yunzuo Zhang Wenxuan Li and Panliang Yang. 2021. Surveillance video motion segmentation based on the progressive spatio-temporal tunnel flow model. Electronics letters 57 13 (2021) 505\u2013507.","DOI":"10.1049\/ell2.12186"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Zhichao Zheng Ying Zhou Yi Chen Junsheng Zhou and Yanhui Gu. 2025. What when and where: Spatial-aware temporal action segmentation. Pattern Recognition (2025) 111833.","DOI":"10.1016\/j.patcog.2025.111833"}],"event":{"name":"MMAsia '25: ACM Multimedia Asia","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743093.3770974","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:10:14Z","timestamp":1765008614000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743093.3770974"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":32,"alternative-id":["10.1145\/3743093.3770974","10.1145\/3743093"],"URL":"https:\/\/doi.org\/10.1145\/3743093.3770974","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}