{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T14:16:12Z","timestamp":1785939372679,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","funder":[{"name":"Project of the Department of Strategic and Advanced Interdisciplinary Research of Pengcheng Laboratory","award":["2025QYA001"],"award-info":[{"award-number":["2025QYA001"]}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB3105000"],"award-info":[{"award-number":["2022YFB3105000"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Key Lab of Software Defined Networking","award":["ZDSYS20140509172959989"],"award-info":[{"award-number":["ZDSYS20140509172959989"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755185","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:37:21Z","timestamp":1761377841000},"page":"6510-6519","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["HoloTrace: LLM-based Bidirectional Causal Knowledge Graph for Edge-Cloud Video Anomaly Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8463-5211","authenticated-orcid":false,"given":"Hanling","family":"Wang","sequence":"first","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, Guangdong, China and Shenzhen International Graduate School, Tsinghua University, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6071-473X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4166-0566","authenticated-orcid":false,"given":"Li","family":"Chen","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8533-5704","authenticated-orcid":false,"given":"Haidong","family":"Kang","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5388-9125","authenticated-orcid":false,"given":"Fei","family":"Ma","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4260-1395","authenticated-orcid":false,"given":"Yong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, Guangdong, China and Pengcheng Laboratory, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01951"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70825"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3226411"},{"key":"e_1_3_2_1_4_1","volume-title":"Unveiling Context-Related Anomalies: Knowledge Graph Empowered Decoupling of Scene and Action for Human-Related Video Anomaly Detection. ArXiv","author":"Chen Chenglizhao","year":"2024","unstructured":"Chenglizhao Chen, Xinyu Liu, Mengke Song, Luming Li, Xu Yu, and Shanchen Pang. 2024. Unveiling Context-Related Anomalies: Knowledge Graph Empowered Decoupling of Scene and Action for Human-Related Video Anomaly Detection. ArXiv, Vol. abs\/2409.03236 (2024)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.103915"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995434"},{"key":"e_1_3_2_1_7_1","volume-title":"Selection-inference: Exploiting large language models for interpretable logical reasoning. ArXiv","author":"Creswell Antonia","year":"2022","unstructured":"Antonia Creswell, Murray Shanahan, and Irina Higgins. 2022. Selection-inference: Exploiting large language models for interpretable logical reasoning. ArXiv, Vol. abs\/2205.09712 (2022)."},{"key":"e_1_3_2_1_8_1","volume-title":"https:\/\/www.douyin.com\/ Retrieved","year":"2025","unstructured":"Douyin. 2025. Douyin. https:\/\/www.douyin.com\/ Retrieved Apr. 9, 2025 from"},{"key":"e_1_3_2_1_9_1","unstructured":"Fujitsu. 2024. Fujitsu AI White Paper - Causal Knowledge Graph. https:\/\/www.fujitsu.com\/global\/documents\/about\/research\/article\/202410-causal-knowledge-graph\/202410_White-Paper-Casual-Knowledge-Graph_EN.pdf Retrieved Apr. 9 2025 from"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01255"},{"key":"e_1_3_2_1_11_1","volume-title":"Fahad Shahbaz Khan, Marius Popescu, and Mubarak Shah.","author":"Georgescu Mariana Iuliana","year":"2021","unstructured":"Mariana Iuliana Georgescu, Radu Tudor Ionescu, Fahad Shahbaz Khan, Marius Popescu, and Mubarak Shah. 2021b. A background-agnostic framework with adversarial training for abnormal event detection in video. IEEE transactions on pattern analysis and machine intelligence, Vol. 44, 9 (2021), 4505-4523."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"e_1_3_2_1_13_1","volume-title":"https:\/\/www.google.com\/videohp Retrieved","year":"2025","unstructured":"Google. 2025. Google. https:\/\/www.google.com\/videohp Retrieved Apr. 9, 2025 from"},{"key":"e_1_3_2_1_14_1","unstructured":"Wenyi Hong Weihan Wang Ming Ding Wenmeng Yu Qingsong Lv Yan Wang Yean Cheng Shiyu Huang Junhui Ji Zhao Xue et al. 2024. Cogvlm2: Visual language models for image and video understanding. ArXiv Vol. abs\/2408.16500 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290956"},{"key":"e_1_3_2_1_16_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. ArXiv Vol. abs\/2410.21276 (2024)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119079"},{"key":"e_1_3_2_1_18_1","volume-title":"Cees GM Snoek, and Rita Cucchiara","author":"Landi Federico","year":"2019","unstructured":"Federico Landi, Cees GM Snoek, and Rita Cucchiara. 2019. Anomaly locality in video surveillance. ArXiv, Vol. abs\/1901.10364 (2019)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"e_1_3_2_1_20_1","volume-title":"Anomaly detection and localization in crowded scenes","author":"Li Weixin","year":"2013","unstructured":"Weixin Li, Vijay Mahadevan, and Nuno Vasconcelos. 2013. Anomaly detection and localization in crowded scenes. IEEE transactions on pattern analysis and machine intelligence, Vol. 36, 1 (2013), 18-32."},{"key":"e_1_3_2_1_21_1","volume-title":"Llm-grounded video diffusion models. ArXiv","author":"Lian Long","year":"2023","unstructured":"Long Lian, Baifeng Shi, Adam Yala, Trevor Darrell, and Boyi Li. 2023. Llm-grounded video diffusion models. ArXiv, Vol. abs\/2309.17444 (2023)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737547"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00684"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3511426"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01333"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.338"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.45"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-021-04190-9"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2938527"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/AIKE48582.2020.00018"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00136"},{"key":"e_1_3_2_1_33_1","volume-title":"Jetson Xavier NX. https:\/\/www.nvidia.com\/en-sg\/autonomous-machines\/embedded-systems\/jetson-xavier-nx\/ Retrieved","author":"NVIDIA.","year":"2025","unstructured":"NVIDIA. 2025. Jetson Xavier NX. https:\/\/www.nvidia.com\/en-sg\/autonomous-machines\/embedded-systems\/jetson-xavier-nx\/ Retrieved Apr. 9, 2025 from"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00197"},{"key":"e_1_3_2_1_35_1","first-page":"1","article-title":"Causal knowledge and reasoning by cognitive maps: Pursuing a holistic approach","volume":"35","author":"Alejandro Pe","year":"2008","unstructured":"Alejandro Pe na, Humberto Sossa, and Agust\u00edn Guti\u00e9rrez. 2008. Causal knowledge and reasoning by cognitive maps: Pursuing a holistic approach. Expert Systems with Applications, Vol. 35, 1-2 (2008), 2-18.","journal-title":"Expert Systems with Applications"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-41335-3_34"},{"key":"e_1_3_2_1_37_1","volume-title":"International conference on machine learning. PMLR, Virtual Event, 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, Virtual Event, 8748-8763."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01513"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3417989"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"e_1_3_2_1_41_1","unstructured":"Yunlong Tang Jing Bi Siting Xu Luchuan Song Susan Liang Teng Wang Daoan Zhang Jie An Jingyang Lin Rongyi Zhu et al. 2023. Video understanding with large language models: A survey. ArXiv Vol. abs\/2312.17432 (2023)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.11.024"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3405716"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"e_1_3_2_1_45_1","volume-title":"Llama: Open and efficient foundation language models. ArXiv","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. ArXiv, Vol. abs\/2302.13971 (2023)."},{"key":"e_1_3_2_1_46_1","volume-title":"Video anomaly detection by the duality of normality-granted optical flow. ArXiv","author":"Wang Hongyong","year":"2021","unstructured":"Hongyong Wang, Xinjian Zhang, Su Yang, and Weishan Zhang. 2021b. Video anomaly detection by the duality of normality-granted optical flow. ArXiv, Vol. abs\/2105.04302 (2021)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2010.5655356"},{"key":"e_1_3_2_1_48_1","volume-title":"Cogvlm: Visual expert for pretrained language models. ArXiv","author":"Wang Weihan","year":"2023","unstructured":"Weihan Wang, Qingsong Lv, Wenmeng Yu, Wenyi Hong, Ji Qi, Yan Wang, Junhui Ji, Zhuoyi Yang, Lei Zhao, Xixuan Song, et al., 2023. Cogvlm: Visual expert for pretrained language models. ArXiv, Vol. abs\/2311.03079 (2023)."},{"key":"e_1_3_2_1_49_1","volume-title":"Robust unsupervised video anomaly detection by multipath frame prediction","author":"Wang Xuanzhao","year":"2021","unstructured":"Xuanzhao Wang, Zhengping Che, Bo Jiang, Ning Xiao, Ke Yang, Jian Tang, Jieping Ye, Jingyu Wang, and Qi Qi. 2021a. Robust unsupervised video anomaly detection by multipath frame prediction. IEEE transactions on neural networks and learning systems, Vol. 33, 6 (2021), 2301-2312."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681442"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40555-y"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_18"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2601655"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2023.102057"},{"key":"e_1_3_2_1_55_1","volume-title":"Missiongnn: Hierarchical multimodal gnn-based weakly supervised video anomaly recognition with mission-specific knowledge graph generation. ArXiv","author":"Yun Sanggeon","year":"2024","unstructured":"Sanggeon Yun, Ryozo Masukawa, Minhyoung Na, and Mohsen Imani. 2024. Missiongnn: Hierarchical multimodal gnn-based weakly supervised video anomaly recognition with mission-specific knowledge graph generation. ArXiv, Vol. abs\/2406.18815 (2024)."},{"key":"e_1_3_2_1_56_1","first-page":"18527","volume-title":"Harnessing Large Language Models for Training-free Video Anomaly Detection. In CVPR","author":"Zanella Luca","year":"2024","unstructured":"Luca Zanella, Willi Menapace, Massimiliano Mancini, Yiming Wang, and Elisa Ricci. 2024. Harnessing Large Language Models for Training-free Video Anomaly Detection. In CVPR 2024. IEEE, Seattle, United States, 18527-18536."},{"key":"e_1_3_2_1_57_1","volume-title":"Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM. ArXiv","author":"Zhang Huaxin","year":"2024","unstructured":"Huaxin Zhang, Xiaohao Xu, Xiang Wang, Jialong Zuo, Chuchu Han, Xiaonan Huang, Changxin Gao, Yuehuan Wang, and Nong Sang. 2024. Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM. ArXiv, Vol. abs\/2406.12235 (2024)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2900907"}],"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\/3746027.3755185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:02:30Z","timestamp":1765342950000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755185"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":58,"alternative-id":["10.1145\/3746027.3755185","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755185","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"}}]}}