{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:22:33Z","timestamp":1771698153940,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62236010, 62306022"],"award-info":[{"award-number":["62236010, 62306022"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755496","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:47:42Z","timestamp":1761371262000},"page":"4542-4551","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["VicKAM: Visual Conceptual Knowledge Guided Action Map for Weakly Supervised Group Activity Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2230-5716","authenticated-orcid":false,"given":"Zhuming","family":"Wang","sequence":"first","affiliation":[{"name":"Beijing University of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6374-0781","authenticated-orcid":false,"given":"Yihao","family":"Zheng","sequence":"additional","affiliation":[{"name":"China Unicom Research Institute, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9044-7944","authenticated-orcid":false,"given":"Jiarui","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8474-0027","authenticated-orcid":false,"given":"Yaofei","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing University of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8239-7229","authenticated-orcid":false,"given":"Yan","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6100-2788","authenticated-orcid":false,"given":"Zun","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7209-0215","authenticated-orcid":false,"given":"Lifang","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing University of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-8647","authenticated-orcid":false,"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_37"},{"key":"e_1_3_2_1_2_1","volume-title":"Monte Carlo Tree Search for Scheduling Activity Recognition. In International Conference on Computer Vision. 1353-1360","author":"Amer Mohamed R.","year":"2013","unstructured":"Mohamed R. Amer, Sinisa Todorovic, Alan Fern, and Song-Chun Zhu. 2013. Monte Carlo Tree Search for Scheduling Activity Recognition. In International Conference on Computer Vision. 1353-1360."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_14"},{"key":"e_1_3_2_1_4_1","first-page":"7892","article-title":"Convolutional relational machine for group activity recognition","author":"Azar Sina Mokhtarzadeh","year":"2019","unstructured":"Sina Mokhtarzadeh Azar, Mina Ghadimi Atigh, Ahmad Nickabadi, and Alexandre Alahi. 2019. Convolutional relational machine for group activity recognition. In Computer Vision and Pattern Recognition. 7892-7901.","journal-title":"Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_5_1","first-page":"4315","article-title":"Social scene understanding: End-to-end multi-person action localization and collective activity recognition","author":"Bagautdinov Timur","year":"2017","unstructured":"Timur Bagautdinov, Alexandre Alahi, Fran\u00e7ois Fleuret, Pascal Fua, and Silvio Savarese. 2017. Social scene understanding: End-to-end multi-person action localization and collective activity recognition. In Computer Vision and Pattern Recognition. 4315-4324.","journal-title":"Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_6_1","first-page":"4724","article-title":"Quo Vadis, Action Recognition","author":"Carreira Jo\u00e3o","year":"2017","unstructured":"Jo\u00e3o Carreira and Andrew Zisserman. 2017. Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. In Computer Vision and Pattern Recognition. 4724-4733.","journal-title":"A New Model and the Kinetics Dataset. In Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00544"},{"key":"e_1_3_2_1_8_1","volume-title":"Understanding collective activitiesof people from videos","author":"Choi Wongun","year":"2013","unstructured":"Wongun Choi and Silvio Savarese. 2013. Understanding collective activitiesof people from videos. IEEE transactions on pattern analysis and machine intelligence, Vol. 36, 6 (2013), 1242-1257."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.516"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_11"},{"key":"e_1_3_2_1_12_1","volume-title":"Snoek","author":"Gavrilyuk Kirill","year":"2020","unstructured":"Kirill Gavrilyuk, Ryan Sanford, Mehrsan Javan, and Cees G. M. Snoek. 2020. Actor-Transformers for Group Activity Recognition. In Computer Vision and Pattern Recognition. 836-845."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3401608"},{"key":"e_1_3_2_1_14_1","volume-title":"Yali Wang, Rui Yan, Lina Yao, Xiaojun Chang, and Yu Qiao.","author":"Han Mingfei","year":"2022","unstructured":"Mingfei Han, David Junhao Zhang, Yali Wang, Rui Yan, Lina Yao, Xiaojun Chang, and Yu Qiao. 2022. Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition. In Computer Vision and Pattern Recognition. 2990-2999."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00106"},{"key":"e_1_3_2_1_18_1","first-page":"7892","article-title":"MACK: multimodal aligned conceptual knowledge for unpaired image-text matching","volume":"35","author":"Huang Yan","year":"2022","unstructured":"Yan Huang, Yuming Wang, Yunan Zeng, and Liang Wang. 2022. MACK: multimodal aligned conceptual knowledge for unpaired image-text matching. Advances in Neural Information Processing Systems, Vol. 35 (2022), 7892-7904.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_44"},{"key":"e_1_3_2_1_20_1","first-page":"1971","article-title":"A hierarchical deep temporal model for group activity recognition","author":"Ibrahim Mostafa S","year":"2016","unstructured":"Mostafa S Ibrahim, Srikanth Muralidharan, Zhiwei Deng, Arash Vahdat, and Greg Mori. 2016. A hierarchical deep temporal model for group activity recognition. In Computer Vision and Pattern Recognition. 1971-1980.","journal-title":"Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01945"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3156634"},{"key":"e_1_3_2_1_23_1","first-page":"1354","article-title":"Social roles in hierarchical models for human activity recognition","author":"Lan Tian","year":"2012","unstructured":"Tian Lan, Leonid Sigal, and Greg Mori. 2012. Social roles in hierarchical models for human activity recognition. In Computer Vision and Pattern Recognition. 1354-1361.","journal-title":"Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_24_1","first-page":"1728","article-title":"Nonlocal based deep model for group activity recognition","volume":"24","author":"Li Ding","year":"2019","unstructured":"Ding Li, Jing Ma, Menglin Yang, and Wensheng Zhang. 2019. Nonlocal based deep model for group activity recognition. Journal of Image and Graphics, Vol. 24 (2019), 1728-1737.","journal-title":"Journal of Image and Graphics"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2614228"},{"key":"e_1_3_2_1_26_1","volume-title":"GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer. In International Conference on Computer Vision. 13668-13677","author":"Li Shuaicheng","year":"2021","unstructured":"Shuaicheng Li, Qianggang Cao, Lingbo Liu, Kunlin Yang, Shinan Liu, Jun Hou, and Shuai Yi. 2021a. GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer. In International Conference on Computer Vision. 13668-13677."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.313"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01328"},{"key":"e_1_3_2_1_29_1","volume-title":"Multimodal-Semantic Context-Aware Graph Neural Network for Group Activity Recognition. In 2021 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 1-6.","author":"Liu Tianshan","year":"2021","unstructured":"Tianshan Liu, Rui Zhao, and Kin-Man Lam. 2021. Multimodal-Semantic Context-Aware Graph Neural Network for Group Activity Recognition. In 2021 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 1-6."},{"key":"e_1_3_2_1_30_1","volume-title":"Spatial Formation-Guided Network for Group Activity Recognition. In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 4250-4254","author":"Ning Dunbo","year":"2024","unstructured":"Dunbo Ning, Wenjing Chen, Wei Xie, and Hao Sun. 2024. Spatial Formation-Guided Network for Group Activity Recognition. In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 4250-4254."},{"key":"e_1_3_2_1_31_1","volume-title":"Where do you know what you know? The representation of semantic knowledge in the human brain. Nature reviews neuroscience","author":"Patterson Karalyn","year":"2007","unstructured":"Karalyn Patterson, Peter J Nestor, and Timothy T Rogers. 2007. Where do you know what you know? The representation of semantic knowledge in the human brain. Nature reviews neuroscience, Vol. 8, 12 (2007), 976-987."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_5"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_7"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.453"},{"key":"e_1_3_2_1_35_1","first-page":"4576","article-title":"Joint inference of groups, events and human roles in aerial videos","author":"Shu Tianmin","year":"2015","unstructured":"Tianmin Shu, Dan Xie, Brandon Rothrock, Sinisa Todorovic, and Song Chun Zhu. 2015. Joint inference of groups, events and human roles in aerial videos. In Computer Vision and Pattern Recognition. 4576-4584.","journal-title":"Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2928540"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2914577"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240576"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2973301"},{"key":"e_1_3_2_1_40_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_41_1","first-page":"3048","article-title":"Recurrent modeling of interaction context for collective activity recognition","author":"Wang Minsi","year":"2017","unstructured":"Minsi Wang, Bingbing Ni, and Xiaokang Yang. 2017. Recurrent modeling of interaction context for collective activity recognition. In Computer Vision and Pattern Recognition. 3048-3056.","journal-title":"Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3425856"},{"key":"e_1_3_2_1_43_1","first-page":"9956","article-title":"Learning Actor Relation Graphs for Group Activity Recognition","author":"Wu Jianchao","year":"2019","unstructured":"Jianchao Wu, Limin Wang, Li Wang, Jie Guo, and Gangshan Wu. 2019. Learning Actor Relation Graphs for Group Activity Recognition. In Computer Vision and Pattern Recognition. 9956-9966.","journal-title":"Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3228731"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3349923"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687564"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00643"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240572"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_13"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_13"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"e_1_3_2_1_52_1","first-page":"3261","volume-title":"Learning Visual Context for Group Activity Recognition. In AAAI Conference on Artificial Intelligence","volume":"35","author":"Yuan Hangjie","year":"2021","unstructured":"Hangjie Yuan and Dong Ni. 2021. Learning Visual Context for Group Activity Recognition. In AAAI Conference on Artificial Intelligence, Vol. 35. 3261-3269."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00738"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2918725"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755496","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:18:56Z","timestamp":1765307936000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755496"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":54,"alternative-id":["10.1145\/3746027.3755496","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755496","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}