{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T11:48:43Z","timestamp":1774352923811,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":49,"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":"National Natural Science Foundation of China","award":["61902415"],"award-info":[{"award-number":["61902415"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612097","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"5059-5069","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["HAAN: Human Action Aware Network for Multi-label Temporal Action Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9715-6834","authenticated-orcid":false,"given":"Zikai","family":"Gao","sequence":"first","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6752-7892","authenticated-orcid":false,"given":"Peng","family":"Qiao","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1256-8934","authenticated-orcid":false,"given":"Yong","family":"Dou","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.263"},{"key":"e_1_3_2_1_2_1","unstructured":"Jake Bouvrie. 2006. Notes on convolutional neural networks. (2006)."},{"key":"e_1_3_2_1_3_1","volume-title":"Procedings of the British Machine Vision Conference","author":"Buch Shyamal","year":"2019","unstructured":"Shyamal Buch, Victor Escorcia, Bernard Ghanem, Li Fei-Fei, and Juan Carlos Niebles. 2019. End-to-end, single-stream temporal action detection in untrimmed videos. In Procedings of the British Machine Vision Conference 2017. British Machine Vision Association."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_6_1","unstructured":"Kai Chen Jiaqi Wang Jiangmiao Pang Yuhang Cao Yu Xiong Xiaoxiao Li Shuyang Sun Wansen Feng Ziwei Liu Jiarui Xu et al. 2019. MMDetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)."},{"key":"e_1_3_2_1_7_1","unstructured":"MMPose Contributors. 2020a. OpenMMLab Pose Estimation Toolbox and Benchmark. https:\/\/github.com\/open-mmlab\/mmpose."},{"key":"e_1_3_2_1_8_1","unstructured":"MMAction2 Contributors. 2020b. OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark. https:\/\/github.com\/open-mmlab\/mmaction2."},{"key":"e_1_3_2_1_9_1","unstructured":"MMPreTrain Contributors. 2023. OpenMMLab's Pre-training Toolbox and Benchmark. https:\/\/github.com\/open-mmlab\/mmpretrain."},{"key":"e_1_3_2_1_10_1","volume-title":"CTRN: Class-Temporal Relational Network for Action Detection. arXiv preprint arXiv:2110.13473","author":"Dai Rui","year":"2021","unstructured":"Rui Dai, Srijan Das, and Francois Bremond. 2021a. CTRN: Class-Temporal Relational Network for Action Detection. arXiv preprint arXiv:2110.13473 (2021)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01941"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00301"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02070"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1963405.1963487"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548546"},{"key":"e_1_3_2_1_16_1","volume-title":"Juan Carlos Niebles, and Bernard Ghanem.","author":"Escorcia Victor","year":"2016","unstructured":"Victor Escorcia, Fabian Caba Heilbron, Juan Carlos Niebles, and Bernard Ghanem. 2016. Daps: Deep action proposals for action understanding. In Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III 14. Springer, 768--784."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_5"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.211"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2017.01.010"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00828"},{"key":"e_1_3_2_1_25_1","volume-title":"Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451","author":"Kitaev Nikita","year":"2020","unstructured":"Nikita Kitaev, \u0141ukasz Kaiser, and Anselm Levskaya. 2020. Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451 (2020)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123343"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"e_1_3_2_1_28_1","volume-title":"Activity graph transformer for temporal action localization. arXiv preprint arXiv:2101.08540","author":"Nawhal Megha","year":"2021","unstructured":"Megha Nawhal and Greg Mori. 2021. Activity graph transformer for temporal action localization. arXiv preprint arXiv:2101.08540 (2021)."},{"key":"e_1_3_2_1_29_1","volume-title":"International Conference on Machine learning. PMLR, 5152--5161","author":"Piergiovanni AJ","year":"2019","unstructured":"AJ Piergiovanni and Michael Ryoo. 2019. Temporal gaussian mixture layer for videos. In International Conference on Machine learning. PMLR, 5152--5161."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00556"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00055"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"e_1_3_2_1_33_1","volume-title":"Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems, Vol. 27 (2014)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16363"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"e_1_3_2_1_36_1","volume-title":"High-resolution representations for labeling pixels and regions. arXiv preprint arXiv:1904.04514","author":"Sun Ke","year":"2019","unstructured":"Ke Sun, Yang Zhao, Borui Jiang, Tianheng Cheng, Bin Xiao, Dong Liu, Yadong Mu, Xinggang Wang, Wenyu Liu, and Jingdong Wang. 2019b. High-resolution representations for labeling pixels and regions. arXiv preprint arXiv:1904.04514 (2019)."},{"key":"e_1_3_2_1_37_1","first-page":"15268","article-title":"Pointtad: Multi-label temporal action detection with learnable query points","volume":"35","author":"Tan Jing","year":"2022","unstructured":"Jing Tan, Xiaotong Zhao, Xintian Shi, Bin Kang, and Limin Wang. 2022. Pointtad: Multi-label temporal action detection with learnable query points. Advances in Neural Information Processing Systems, Vol. 35 (2022), 15268--15280.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00151"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3193611"},{"key":"e_1_3_2_1_41_1","volume-title":"Attention is all you need. Advances in neural information processing systems","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_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2986861"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"e_1_3_2_1_45_1","volume-title":"Articulated human detection with flexible mixtures of parts","author":"Yang Yi","year":"2012","unstructured":"Yi Yang and Deva Ramanan. 2012. Articulated human detection with flexible mixtures of parts. IEEE transactions on pattern analysis and machine intelligence, Vol. 35, 12 (2012), 2878--2890."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1013-y"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"e_1_3_2_1_48_1","volume-title":"Recurrent neural network regularization. arXiv preprint arXiv:1409.2329","author":"Zaremba Wojciech","year":"2014","unstructured":"Wojciech Zaremba, Ilya Sutskever, and Oriol Vinyals. 2014. Recurrent neural network regularization. arXiv preprint arXiv:1409.2329 (2014)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"}],"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\/3581783.3612097","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:05:15Z","timestamp":1755821115000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612097"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":49,"alternative-id":["10.1145\/3581783.3612097","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612097","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"}}]}}