{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T09:33:24Z","timestamp":1780479204648,"version":"3.54.1"},"reference-count":78,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T00:00:00Z","timestamp":1741305600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2025,3,31]]},"abstract":"<jats:p>\n            This article presents a Temporal Action Detection (TAD) method with Multigranularity (MG) feature aggregation and Cross-level Boundary Modeling (CBM). Compared with other methods, our proposed approach has the following advantages. First, different from most existing works which only consider the local temporal context, a simple and computationally efficient MG module is proposed to comprehensively extract video features in instant, local, and global temporal granularities. Second, unlike the methods that only employ the information from single feature pyramid level for action boundary regression, a CBM strategy that integrates the relative information from both the same and higher level features is designed to improve the accuracy of boundary prediction. At lastfere, benefiting from the MG module and CBM strategy, our method outperforms other state-of-the-art approaches on five challenging TAD datasets: THUMOS14, MultiTHUMOS, EPIC-KITCHENS-100, ActivityNet-1.3, and HACS. We make our code and pre-trained model publicly available at:\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/MGCBM\/TAL-MGCBM\">https:\/\/github.com\/MGCBM\/TAL-MGCBM<\/jats:ext-link>\n          <\/jats:p>","DOI":"10.1145\/3712598","type":"journal-article","created":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T16:33:41Z","timestamp":1737131621000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Multigranularity Feature Aggregation and Cross-level Boundary Modeling for Temporal Action Detection"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4955-8582","authenticated-orcid":false,"given":"Qiang","family":"Li","sequence":"first","affiliation":[{"name":"School of Information Sciences and Technology, Northeast Normal University, Changchun, China and Changchun Humanities and Sciences College, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2556-4135","authenticated-orcid":false,"given":"Di","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Sciences and Technology, Northeast Normal University, Changchun, China and Northeast Electric Power University, Jilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4390-0508","authenticated-orcid":false,"given":"Guang","family":"Zu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2966-2315","authenticated-orcid":false,"given":"Sen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Sciences and Technology, Northeast Normal University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3697-9755","authenticated-orcid":false,"given":"Hui","family":"Sun","sequence":"additional","affiliation":[{"name":"Changchun Humanities and Sciences College, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6867-3282","authenticated-orcid":false,"given":"Jianzhong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Sciences and Technology, Northeast Normal University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,3,7]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00356"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_16"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_8"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.93"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3552458.3556443"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00124"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178173"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475351"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_29"},{"key":"e_1_3_1_13_2","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020 (NeurIPS \u201920)","author":"Lu Chi","year":"2020","unstructured":"Lu Chi, Borui Jiang, and Yadong Mu. 2020. Fast Fourier convolution. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020 (NeurIPS \u201920). Retrieved from https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/2fd5d41ec6cfab47e32164d5624269b1-Abstract.html"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/S11263-021-01531-2"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3567828"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.52"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102850"},{"key":"e_1_3_1_19_2","volume-title":"International Conference on Learning Representations","author":"Guibas John","year":"2021","unstructured":"John Guibas, Morteza Mardani, Zongyi Li, Andrew Tao, Anima Anandkumar, and Bryan Catanzaro. 2021. Efficient token mixing for transformers via adaptive Fourier neural operators. In International Conference on Learning Representations."},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.211"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V34I07.6766"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/SMC53654.2022.9945289"},{"key":"e_1_3_1_24_2","unstructured":"Will Kay Jo\u00e3o Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Apostol Natsev . 2017. The kinetics human action video dataset. arXiv:1705.06950. Retrieved from https:\/\/arxiv.org\/abs\/1705.06950"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2022.NAACL-MAIN.319"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V35I3.16285"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3367599"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V34I07.6815"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00333"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123343"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V34I07.6829"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01938"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3195321"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00043"},{"key":"e_1_3_1_38_2","volume-title":"5th International Conference on Learning Representations (ICLR \u201917)","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. SGDR: Stochastic gradient descent with warm restarts. In 5th International Conference on Learning Representations (ICLR \u201917). Retrieved from https:\/\/openreview.net\/forum?id=Skq89Scxx"},{"key":"e_1_3_1_39_2","volume-title":"7th International Conference on Learning Representations (ICLR \u201919)","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In 7th International Conference on Learning Representations (ICLR \u201919). Retrieved from https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00951"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_37"},{"key":"e_1_3_1_42_2","volume-title":"Discrete-Time Signal Processing","author":"Oppenheim Alan V.","year":"1999","unstructured":"Alan V. Oppenheim. 1999. Discrete-Time Signal Processing. Pearson Education India."},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71249-9_47"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00055"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263824"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_7"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01348"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"e_1_3_1_52_2","unstructured":"Jing Tan Xiaotong Zhao Xintian Shi Bin Kang and Limin Wang. 2022. PointTAD: Multi-label temporal action detection with learnable query points. In NeurIPS. Retrieved from http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/6255539f776ce988a81d3841eadc4cf9-Abstract-Conference.html"},{"key":"e_1_3_1_53_2","unstructured":"Tuan N. Tang Kwonyoung Kim and Kwanghoon Sohn. 2023. TemporalMaxer: Maximize temporal context with only max pooling for temporal action localization. arXiv:2303.09055. Retrieved from https:\/\/arxiv.org\/abs\/2303.09055"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"e_1_3_1_55_2","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems (NeurIPS \u201917)","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems (NeurIPS \u201917), 5998\u20136008. Retrieved from https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"e_1_3_1_58_2","unstructured":"Lining Wang Haosen Yang Wenhao Wu Hongxun Yao and Hujie Huang. 2021. Temporal action proposal generation with transformers. arXiv:2105.12043. Retrieved from https:\/\/arxiv.org\/abs\/2105.12043"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3567827"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3571747"},{"key":"e_1_3_1_61_2","first-page":"9923","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems (NeurIPS \u201821)","author":"Xu Mengmeng","year":"2021","unstructured":"Mengmeng Xu, Juan-Manuel P\u00e9rez-R\u00faa, Xiatian Zhu, Bernard Ghanem, and Brais Mart\u00ednez. 2021. Low-fidelity video encoder optimization for temporal action localization. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems (NeurIPS \u201821), 9923\u20139935. Retrieved from https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/522a9ae9a99880d39e5daec35375e999-Abstract.html"},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3338082"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326692"},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180925"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016486"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1013-y"},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"e_1_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"e_1_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"e_1_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.1016\/J.PATCOG.2020.107312"},{"key":"e_1_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1049\/CIT2.12012"},{"key":"e_1_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01340"},{"key":"e_1_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00876"},{"key":"e_1_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_32"},{"key":"e_1_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"e_1_3_1_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01756"},{"key":"e_1_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V36I3.20277"},{"key":"e_1_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475708"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712598","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:37Z","timestamp":1750295917000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712598"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,7]]},"references-count":78,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3,31]]}},"alternative-id":["10.1145\/3712598"],"URL":"https:\/\/doi.org\/10.1145\/3712598","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,7]]},"assertion":[{"value":"2024-07-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}