{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:16:07Z","timestamp":1765307767941,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20390"],"award-info":[{"award-number":["U21A20390"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Development Project of Jilin Province of China","award":["20240601039RC"],"award-info":[{"award-number":["20240601039RC"]}]},{"name":"Fundamental Research Funds for the Central University, JLU"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755557","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:44:48Z","timestamp":1761371088000},"page":"8537-8546","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Video-Level Multimodal Relation Extraction with Event-Entity Semantic Consistency"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5627-050X","authenticated-orcid":false,"given":"Zefan","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Jilin University, Changchun, China and Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0225-1600","authenticated-orcid":false,"given":"Weiqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University, Changchun, China and Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9411-0110","authenticated-orcid":false,"given":"Kailong","family":"Suo","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University, Changchun, China and Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5270-9814","authenticated-orcid":false,"given":"Yanhui","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University, Changchun, China and Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8060-4725","authenticated-orcid":false,"given":"Tian","family":"Bai","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University, Changchun, China and Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"arXiv preprint arXiv:2502.13923","author":"Bai Shuai","year":"2025","unstructured":"Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, Jiabo Ye, Xi Zhang, Tianbao Xie, Zesen Cheng, Hang Zhang, Zhibo Yang, Haiyang Xu, and Junyang Lin. 2025. Qwen2.5-VL Technical Report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_3_1","volume-title":"Good visual guidance makes a better extractor: Hierarchical visual prefix for multimodal entity and relation extraction. arXiv preprint arXiv:2205.03521","author":"Chen Xiang","year":"2022","unstructured":"Xiang Chen, Ningyu Zhang, Lei Li, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, and Huajun Chen. 2022a. Good visual guidance makes a better extractor: Hierarchical visual prefix for multimodal entity and relation extraction. arXiv preprint arXiv:2205.03521 (2022)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511998"},{"key":"e_1_3_2_1_5_1","unstructured":"Zhe Chen Weiyun Wang Yue Cao Yangzhou Liu Zhangwei Gao Erfei Cui Jinguo Zhu Shenglong Ye Hao Tian Zhaoyang Liu et al. 2024. Expanding Performance Boundaries of Open-Source Multimodal Models with Model Data and Test-Time Scaling. arXiv preprint arXiv:2412.05271 (2024)."},{"key":"e_1_3_2_1_6_1","unstructured":"Yunfei Chu Jin Xu Qian Yang Haojie Wei Xipin Wei Zhifang Guo Yichong Leng Yuanjun Lv Jinzheng He Junyang Lin et al. 2024. Qwen2-audio technical report. arXiv preprint arXiv:2407.10759 (2024)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3345146"},{"key":"e_1_3_2_1_8_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_9_1","first-page":"837","volume-title":"Lrec","volume":"2","author":"Doddington George R","year":"2004","unstructured":"George R Doddington, Alexis Mitchell, Mark A Przybocki, Lance A Ramshaw, Stephanie M Strassel, and Ralph M Weischedel. 2004. The automatic content extraction (ace) program-tasks, data, and evaluation.. In Lrec, Vol. 2. Lisbon, 837-840."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25127"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.26"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120867"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29770"},{"key":"e_1_3_2_1_14_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Kai Han Yunhe Wang Hanting Chen Xinghao Chen Jianyuan Guo Zhenhua Liu Yehui Tang An Xiao Chunjing Xu Yixing Xu et al. 2022. A survey on vision transformer. IEEE transactions on pattern analysis and machine intelligence Vol. 45 1 (2022) 87-110.","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612209"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680995"},{"key":"e_1_3_2_1_18_1","volume-title":"Kushal Lakhotia","author":"Hsu Wei-Ning","year":"2021","unstructured":"Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, and Abdelrahman Mohamed. 2021. Hubert: Self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM transactions on audio, speech, and language processing, Vol. 29 (2021), 3451-3460."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611899"},{"key":"e_1_3_2_1_20_1","volume-title":"Multimodal relation extraction with cross-modal retrieval and synthesis. arXiv preprint arXiv:2305.16166","author":"Hu Xuming","year":"2023","unstructured":"Xuming Hu, Zhijiang Guo, Zhiyang Teng, Irwin King, and Philip S Yu. 2023b. Multimodal relation extraction with cross-modal retrieval and synthesis. arXiv preprint arXiv:2305.16166 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"Leveraging the video-level semantic consistency of event for audio-visual event localization","author":"Jiang Yuanyuan","year":"2023","unstructured":"Yuanyuan Jiang, Jianqin Yin, and Yonghao Dang. 2023. Leveraging the video-level semantic consistency of event for audio-visual event localization. IEEE transactions on multimedia, Vol. 26 (2023), 4617-4627."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681115"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i13.26987"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681112"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29828"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645603"},{"key":"e_1_3_2_1_27_1","first-page":"459","volume-title":"ESWC 2019, portoro\u017e, Slovenia, June 2-6, 2019, proceedings 16","author":"Liu Ye","year":"2019","unstructured":"Ye Liu, Hui Li, Alberto Garcia-Duran, Mathias Niepert, Daniel Onoro-Rubio, and David S Rosenblum. 2019a. MMKG: multi-modal knowledge graphs. In The semantic web: 16th international conference, ESWC 2019, portoro\u017e, Slovenia, June 2-6, 2019, proceedings 16. Springer, 459-474."},{"key":"e_1_3_2_1_28_1","volume-title":"GCDT: A global context enhanced deep transition architecture for sequence labeling. arXiv preprint arXiv:1906.02437","author":"Liu Yijin","year":"2019","unstructured":"Yijin Liu, Fandong Meng, Jinchao Zhang, Jinan Xu, Yufeng Chen, and Jie Zhou. 2019b. GCDT: A global context enhanced deep transition architecture for sequence labeling. arXiv preprint arXiv:1906.02437 (2019)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1185"},{"key":"e_1_3_2_1_30_1","volume-title":"Multimodal named entity recognition for short social media posts. arXiv preprint arXiv:1802.07862","author":"Moon Seungwhan","year":"2018","unstructured":"Seungwhan Moon, Leonardo Neves, and Vitor Carvalho. 2018. Multimodal named entity recognition for short social media posts. arXiv preprint arXiv:1802.07862 (2018)."},{"key":"e_1_3_2_1_31_1","volume-title":"HOLMES: Hyper-relational knowledge graphs for multi-hop question answering using LLMs. arXiv preprint arXiv:2406.06027","author":"Panda Pranoy","year":"2024","unstructured":"Pranoy Panda, Ankush Agarwal, Chaitanya Devaguptapu, Manohar Kaul, et al., 2024. HOLMES: Hyper-relational knowledge graphs for multi-hop question answering using LLMs. arXiv preprint arXiv:2406.06027 (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17633"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612449"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548324"},{"key":"e_1_3_2_1_36_1","volume-title":"Mindmap: Knowledge graph prompting sparks graph of thoughts in large language models. arXiv preprint arXiv:2308.09729","author":"Wen Yilin","year":"2023","unstructured":"Yilin Wen, Zifeng Wang, and Jimeng Sun. 2023. Mindmap: Knowledge graph prompting sparks graph of thoughts in large language models. arXiv preprint arXiv:2308.09729 (2023)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681179"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2024.3371530"},{"key":"e_1_3_2_1_39_1","unstructured":"Jin Xu Zhifang Guo Jinzheng He et al. 2025. Qwen2. 5-omni technical report. arXiv preprint arXiv:2503.20215 (2025)."},{"key":"e_1_3_2_1_40_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et al. 2024. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115 (2024)."},{"volume-title":"Improving multimodal named entity recognition via entity span detection with unified multimodal transformer","author":"Yu Jianfei","key":"e_1_3_2_1_41_1","unstructured":"Jianfei Yu, Jing Jiang, Li Yang, and Rui Xia. 2020. Improving multimodal named entity recognition via entity span detection with unified multimodal transformer. Association for Computational Linguistics."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26309"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205212"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17687"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1004"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592272"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681219"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34795"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/734"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.376"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3476968"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3297842"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428274"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:13:35Z","timestamp":1765307615000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755557"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":54,"alternative-id":["10.1145\/3746027.3755557","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755557","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"}}]}}