{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:26:09Z","timestamp":1773156369022,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":51,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612096","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"5281-5291","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8714-4151","authenticated-orcid":false,"given":"Yu","family":"Zhao","sequence":"first","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3026-6347","authenticated-orcid":false,"given":"Hao","family":"Fei","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7157-6961","authenticated-orcid":false,"given":"Yixin","family":"Cao","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0513-5540","authenticated-orcid":false,"given":"Bobo","family":"Li","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, Chile"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6335-1340","authenticated-orcid":false,"given":"Meishan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8964-9759","authenticated-orcid":false,"given":"Jianguo","family":"Wei","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, Chile"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4659-1822","authenticated-orcid":false,"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"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":"10.1145\/3503161.3548420"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413841"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00998"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547943"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19922"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-171"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01904"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01606"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01710"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17514"},{"key":"e_1_3_2_1_11_1","first-page":"549","article-title":"Better Combine Them Together! Integrating Syntactic Constituency and Dependency Representations for Semantic Role Labeling","volume":"2021","author":"Fei Hao","year":"2021","unstructured":"Hao Fei, Shengqiong Wu, Yafeng Ren, Fei Li, and Donghong Ji. 2021. Better Combine Them Together! Integrating Syntactic Constituency and Dependency Representations for Semantic Role Labeling. In Findings of the Association for Computational Linguistics: ACL\/IJCNLP 2021. 549--559.","journal-title":"Findings of the Association for Computational Linguistics: ACL\/IJCNLP"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17515"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of ICCV","author":"Feichtenhofer Christoph","year":"2019","unstructured":"Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, and Kaiming He. 2019. Slow-Fast Networks for Video Recognition. In Proceedings of ICCV 2019. 6201--6210."},{"key":"e_1_3_2_1_14_1","volume-title":"Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs. CoRR abs\/2112.09828","author":"Feng Shengyu","year":"2021","unstructured":"Shengyu Feng, Subarna Tripathi, Hesham Mostafa, Marcel Nassar, and Somdeb Majumdar. 2021. Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs. CoRR abs\/2112.09828 (2021). arXiv:2112.09828"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16231"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01692"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.3115\/1075218.1075283"},{"key":"e_1_3_2_1_18_1","volume-title":"CoRR abs\/1505.04474","author":"Gupta Saurabh","year":"2015","unstructured":"Saurabh Gupta and Jitendra Malik. 2015. CoRR abs\/1505.04474 (2015). arXiv:1505.04474"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33676-9_30"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3183434"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-021-00842-1"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of NeurIPS","author":"Khan Zeeshan","year":"2022","unstructured":"Zeeshan Khan, C. V. Jawahar, and Makarand Tapaswi. 2022. Grounded Video Situation Recognition. In Proceedings of NeurIPS 2022."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of ICLR","author":"Li Yujia","year":"2016","unstructured":"Yujia Li, Daniel Tarlow, Marc Brockschmidt, and Richard S. Zemel. 2016. Gated Graph Sequence Neural Networks. In Proceedings of ICLR 2016."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01350"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-022-01012-7"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1060"},{"key":"e_1_3_2_1_30_1","volume-title":"Roy-Chowdhury","author":"Nag Sayak","year":"2023","unstructured":"Sayak Nag, Kyle Min, Subarna Tripathi, and Amit K. Roy-Chowdhury. 2023. Unbiased Scene Graph Generation in Videos. CoRR abs\/2304.00733 (2023). arXiv:2304.00733"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548180"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00554"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983349"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"e_1_3_2_1_35_1","volume-title":"Graph Attention Networks. CoRR abs\/1710.10903","author":"Veli\u010dkovi\u0107 Petar","year":"2017","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2017. Graph Attention Networks. CoRR abs\/1710.10903 (2017)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528668"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2023.3269620"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2023.3291718"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3225187","article-title":"Recognition in Label and Discrimination in Feature: A Hierarchically Designed Lightweight Method for Limited Data in SAR ATR","volume":"60","author":"Wang Chenwei","year":"2022","unstructured":"Chenwei Wang, Jifang Pei, Jianyu Yang, Xiaoyu Liu, Yulin Huang, and Deqing Mao. 2022. Recognition in Label and Discrimination in Feature: A Hierarchically Designed Lightweight Method for Limited Data in SAR ATR. IEEE Transactions on Geoscience and Remote Sensing 60 (2022), 1--13.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25350"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.2737\/FPL-GTR-290"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20167"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3587578"},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of NeurIPS 2020","volume":"33","author":"Wu Tailin","year":"2020","unstructured":"Tailin Wu, Hongyu Ren, Pan Li, and Jure Leskovec. 2020. Graph information bottleneck. In Proceedings of NeurIPS 2020, Vol. 33. 20437--20448."},{"key":"e_1_3_2_1_45_1","first-page":"5381","article-title":"A Syntax-aware Multi-task Learning Framework for Chinese Semantic Role Labeling","volume":"2019","author":"Xia Qingrong","year":"2019","unstructured":"Qingrong Xia, Zhenghua Li, and Min Zhang. 2019. A Syntax-aware Multi-task Learning Framework for Chinese Semantic Role Labeling. In Proceedings of EMNLP-IJCNLP 2019. 5381--5391.","journal-title":"Proceedings of EMNLP-IJCNLP"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"e_1_3_2_1_47_1","volume-title":"Proceedings of AAAI","author":"Yang Guang","year":"2022","unstructured":"Guang Yang, Manling Li, Jiajie Zhang, Xudong Lin, Shih-Fu Chang, and Heng Ji. 2022. Video Event Extraction via Tracking Visual States of Arguments. In Proceedings of AAAI 2020."},{"key":"e_1_3_2_1_48_1","first-page":"2313","article-title":"Auto-Encoding and Distilling Scene Graphs for Image Captioning","volume":"44","author":"Yang Xu","year":"2022","unstructured":"Xu Yang, Hanwang Zhang, and Jianfei Cai. 2022. Auto-Encoding and Distilling Scene Graphs for Image Captioning. IEEE Trans. Pattern Anal. Mach. Intell. 44, 5 (2022), 2313--2327.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5391"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.597"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123294"}],"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\/3581783.3612096","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:05:35Z","timestamp":1755821135000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612096"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":51,"alternative-id":["10.1145\/3581783.3612096","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612096","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"}}]}}