{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:38Z","timestamp":1786120838632,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["No. 62502049"],"award-info":[{"award-number":["No. 62502049"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817705","type":"proceedings-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:08:33Z","timestamp":1786064913000},"page":"6350-6361","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["VideoExplorer: Advancing Long-Horizon Video Understanding via Hierarchical Orchestration"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6855-6558","authenticated-orcid":false,"given":"Huaying","family":"Yuan","sequence":"first","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7765-8466","authenticated-orcid":false,"given":"Zheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Academy of Artificial Intelligence, Beijing, China and Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5903-2806","authenticated-orcid":false,"given":"Junjie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4011-5673","authenticated-orcid":false,"given":"Hongjin","family":"Qian","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China and Beijing Academy of Artificial Intelligence, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5544-9425","authenticated-orcid":false,"given":"Yan","family":"Shu","sequence":"additional","affiliation":[{"name":"University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6597-7248","authenticated-orcid":false,"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[{"name":"University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9777-9676","authenticated-orcid":false,"given":"Ji-Rong","family":"Wen","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9781-948X","authenticated-orcid":false,"given":"Zhicheng","family":"Dou","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01232"},{"key":"e_1_3_2_1_2_1","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:2502.13923 [cs.CV] https:\/\/arxiv.org\/abs\/2502.13923"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01882"},{"key":"e_1_3_2_1_4_1","volume-title":"LongVILA: Scaling Long-Context Visual Language Models for Long Videos. In The Thirteenth International Conference on Learning Representations, ICLR 2025","author":"Chen Yukang","year":"2025","unstructured":"Yukang Chen, Fuzhao Xue, Dacheng Li, Qinghao Hu, Ligeng Zhu, Xiuyu Li, Yunhao Fang, Haotian Tang, Shang Yang, Zhijian Liu, Yihui He, Hongxu Yin, Pavlo Molchanov, Jan Kautz, Linxi Fan, Yuke Zhu, Yao Lu, and Song Han. 2025a. LongVILA: Scaling Long-Context Visual Language Models for Long Videos. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. https:\/\/openreview.net\/forum?id=wCXAlfvCy6"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Kaituo Feng Kaixiong Gong Bohao Li Zonghao Guo Yibing Wang Tianshuo Peng Junfei Wu Xiaoying Zhang Benyou Wang and Xiangyu Yue. 2025. Video-R1: Reinforcing Video Reasoning in MLLMs. arXiv:2503.21776 [cs.CV] https:\/\/arxiv.org\/abs\/2503.21776","DOI":"10.52202\/085713-3310"},{"key":"e_1_3_2_1_6_1","unstructured":"Noriyuki Kugo Xiang Li Zixin Li Ashish Gupta Arpandeep Khatua Nidhish Jain Chaitanya Patel Yuta Kyuragi Yasunori Ishii Masamoto Tanabiki Kazuki Kozuka and Ehsan Adeli. 2025. VideoMultiAgents: A Multi-Agent Framework for Video Question Answering. arXiv:2504.20091 [cs.CV] https:\/\/arxiv.org\/abs\/2504.20091"},{"key":"e_1_3_2_1_7_1","unstructured":"Rui Li Xiaohan Wang Yuhui Zhang Orr Zohar Zeyu Wang and Serena Yeung-Levy. 2025b. Temporal Preference Optimization for Long-Form Video Understanding. arXiv:2501.13919 [cs.CV] https:\/\/arxiv.org\/abs\/2501.13919"},{"key":"e_1_3_2_1_8_1","unstructured":"Xinhao Li Yi Wang Jiashuo Yu Xiangyu Zeng Yuhan Zhu Haian Huang Jianfei Gao Kunchang Li Yinan He Chenting Wang Yu Qiao Yali Wang and Limin Wang. 2025a. VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling. arXiv:2501.00574 [cs.CV] https:\/\/arxiv.org\/abs\/2501.00574"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Ruotong Liao Max Erler Huiyu Wang Guangyao Zhai Gengyuan Zhang Yunpu Ma and Volker Tresp. 2024. VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs. arXiv:2409.20365 [cs.CV] https:\/\/arxiv.org\/abs\/2409.20365","DOI":"10.18653\/v1\/2024.findings-emnlp.384"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.EMNLP-MAIN.342"},{"key":"e_1_3_2_1_11_1","unstructured":"Jingyang Lin Jialian Wu Ximeng Sun Ze Wang Jiang Liu Yusheng Su Xiaodong Yu Hao Chen Jiebo Luo Zicheng Liu and Emad Barsoum. 2025. Unleashing Hour-Scale Video Training for Long Video-Language Understanding. arXiv:2506.05332 [cs.CV] https:\/\/arxiv.org\/abs\/2506.05332"},{"key":"e_1_3_2_1_12_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li Bo Li Yuanhan Zhang Sheng Shen and Yong Jae Lee. 2024. LLaVA-NeXT: Improved reasoning OCR and world knowledge. https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00390"},{"key":"e_1_3_2_1_14_1","unstructured":"Yongdong Luo Xiawu Zheng Xiao Yang Guilin Li Haojia Lin Jinfa Huang Jiayi Ji Fei Chao Jiebo Luo and Rongrong Ji. 2024. Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension. arXiv:2411.13093 [cs.CV] https:\/\/arxiv.org\/abs\/2411.13093"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01764"},{"key":"e_1_3_2_1_16_1","unstructured":"OpenAI. 2024. GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3439950"},{"key":"e_1_3_2_1_18_1","unstructured":"Minghao Qin Xiangrui Liu Zhengyang Liang Yan Shu Huaying Yuan Juenjie Zhou Shitao Xiao Bo Zhao and Zheng Liu. 2025. Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification. arXiv:2506.19225 [cs.CV] https:\/\/arxiv.org\/abs\/2506.19225"},{"key":"e_1_3_2_1_19_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_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.EMNLP-MAIN.544"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02436"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"e_1_3_2_1_23_1","unstructured":"DeepSeek-AI Team. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv:2501.12948 [cs.CL] https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_2_1_24_1","unstructured":"Gemini Team and etc. 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv:2403.05530 [cs.CL] https:\/\/arxiv.org\/abs\/2403.05530"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Shulin Tian Ruiqi Wang Hongming Guo Penghao Wu Yuhao Dong Xiuying Wang Jingkang Yang Hao Zhang Hongyuan Zhu and Ziwei Liu. 2025. Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning. arXiv:2506.13654 [cs.CV] https:\/\/arxiv.org\/abs\/2506.13654","DOI":"10.1109\/TPAMI.2026.3697367"},{"key":"e_1_3_2_1_26_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024a. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02131"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_4"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00311"},{"key":"e_1_3_2_1_30_1","unstructured":"Kangda Wei Zhengyu Zhou Bingqing Wang Jun Araki Lukas Lange Ruihong Huang and Zhe Feng. 2025. PreMind: Multi-Agent Video Understanding for Advanced Indexing of Presentation-style Videos. arXiv:2503.00162 [cs.CV] https:\/\/arxiv.org\/abs\/2503.00162"},{"key":"e_1_3_2_1_31_1","volume-title":"A survey on robotics with foundation models: toward embodied ai. arXiv preprint arXiv:2402.02385","author":"Xu Zhiyuan","year":"2024","unstructured":"Zhiyuan Xu, Kun Wu, Junjie Wen, Jinming Li, Ning Liu, Zhengping Che, and Jian Tang. 2024. A survey on robotics with foundation models: toward embodied ai. arXiv preprint arXiv:2402.02385 (2024)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01292"},{"key":"e_1_3_2_1_33_1","volume-title":"V2025","author":"Zhang Yuanhan","year":"2025","unstructured":"Yuanhan Zhang, Jinming Wu, Wei Li, Bo Li, Zejun Ma, Ziwei Liu, and Chunyuan Li. 2025a. LLaVA-Video: Video Instruction Tuning With Synthetic Data. Trans. Mach. Learn. Res., V2025 (2025). https:\/\/openreview.net\/forum?id=EElFGvt39K"},{"key":"e_1_3_2_1_34_1","volume-title":"Wenbo Li, Yinchuan Li, Kun Shao, and Kaiwen Zhou.","author":"Zhi Zhuo","year":"2025","unstructured":"Zhuo Zhi, Qiangqiang Wu, Minghe shen, Wenbo Li, Yinchuan Li, Kun Shao, and Kaiwen Zhou. 2025. VideoAgent2: Enhancing the LLM-Based Agent System for Long-Form Video Understanding by Uncertainty-Aware CoT. arXiv:2504.04471 [cs.CV] https:\/\/arxiv.org\/abs\/2504.04471"},{"key":"e_1_3_2_1_35_1","volume-title":"MLVU: A Comprehensive Benchmark for Multi-Task Long Video Understanding. arXiv preprint arXiv:2406.04264","author":"Zhou Junjie","year":"2024","unstructured":"Junjie Zhou, Yan Shu, Bo Zhao, Boya Wu, Shitao Xiao, Xi Yang, Yongping Xiong, Bo Zhang, Tiejun Huang, and Zheng Liu. 2024. MLVU: A Comprehensive Benchmark for Multi-Task Long Video Understanding. arXiv preprint arXiv:2406.04264 (2024)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Yiyang Zhou Yangfan He Yaofeng Su Siwei Han Joel Jang Gedas Bertasius Mohit Bansal and Huaxiu Yao. 2025. ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding. arXiv:2506.01300 [cs.CV] https:\/\/arxiv.org\/abs\/2506.01300","DOI":"10.52202\/085713-5066"},{"key":"e_1_3_2_1_37_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Zhu Bin","year":"2024","unstructured":"Bin Zhu, Bin Lin, Munan Ning, Yang Yan, Jiaxi Cui, Hongfa Wang, Yatian Pang, Wenhao Jiang, Junwu Zhang, Zongwei Li, Caiwan Zhang, Zhifeng Li, Wei Liu, and Li Yuan. 2024. LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=QmZKc7UZCy"},{"key":"e_1_3_2_1_38_1","unstructured":"Jinguo Zhu and etc. 2025. InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models. arXiv:2504.10479 [cs.CV] https:\/\/arxiv.org\/abs\/2504.10479"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:13:35Z","timestamp":1786065215000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817705"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":38,"alternative-id":["10.1145\/3770855.3817705","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817705","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}