{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:46:14Z","timestamp":1765309574223,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754848","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"9395-9403","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["OnlineHOI: Towards Online Human-Object Interaction Generation and Perception"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5033-7530","authenticated-orcid":false,"given":"Yihong","family":"Ji","sequence":"first","affiliation":[{"name":"Shenzhen University, Shenzhen, China and Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3148-8822","authenticated-orcid":false,"given":"Yunze","family":"Liu","sequence":"additional","affiliation":[{"name":"IIIS, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7120-0808","authenticated-orcid":false,"given":"Yiyao","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7449-3093","authenticated-orcid":false,"given":"Weijiang","family":"Yu","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6797-2571","authenticated-orcid":false,"given":"Joshua Zhexue","family":"Huang","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1006-7594","authenticated-orcid":false,"given":"Fei","family":"Yu","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, 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":"Handsonvlm: Vision-language models for hand-object interaction prediction. arXiv preprint arXiv:2412.13187","author":"Bao Chen","year":"2024","unstructured":"Chen Bao, Jiarui Xu, Xiaolong Wang, Abhinav Gupta, and Homanga Bharadhwaj. Handsonvlm: Vision-language models for hand-object interaction prediction. arXiv preprint arXiv:2412.13187, 2024."},{"key":"e_1_3_2_1_2_1","first-page":"8090","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Cai Jiarui","year":"2022","unstructured":"Jiarui Cai, Mingze Xu, Wei Li, Yuanjun Xiong, Wei Xia, Zhuowen Tu, and Stefano Soatto. Memot: Multi-object tracking with memory. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pages 8090--8100, 2022."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00156"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"e_1_3_2_1_6_1","first-page":"18","volume-title":"European Conference on Computer Vision","author":"Dai Sisi","year":"2024","unstructured":"Sisi Dai, Wenhao Li, Haowen Sun, Haibin Huang, Chongyang Ma, Hui Huang, Kai Xu, and Ruizhen Hu. Interfusion: Text-driven generation of 3d human-object interaction. In European Conference on Computer Vision, pages 18--35. Springer, 2024."},{"key":"e_1_3_2_1_7_1","volume-title":"Collage: Collaborative human-agent interaction generation using hierarchical latent diffusion and language models. arXiv preprint arXiv:2409.20502","author":"Daiya Divyanshu","year":"2024","unstructured":"Divyanshu Daiya, Damon Conover, and Aniket Bera. Collage: Collaborative human-agent interaction generation using hierarchical latent diffusion and language models. arXiv preprint arXiv:2409.20502, 2024."},{"key":"e_1_3_2_1_8_1","volume-title":"Diffusion models beat gans on image synthesis. Advances in neural information processing systems, 34:8780--8794","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. Diffusion models beat gans on image synthesis. Advances in neural information processing systems, 34:8780--8794, 2021."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01880"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01398"},{"key":"e_1_3_2_1_11_1","volume-title":"Unisync: A unified framework for audio-visual synchronization. arXiv preprint arXiv:2503.16357","author":"Feng Tao","year":"2025","unstructured":"Tao Feng, Yifan Xie, Xun Guan, Jiyuan Song, Zhou Liu, Fei Ma, and Fei Yu. Unisync: A unified framework for audio-visual synchronization. arXiv preprint arXiv:2503.16357, 2025."},{"key":"e_1_3_2_1_12_1","volume-title":"Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752","author":"Gu Albert","year":"2023","unstructured":"Albert Gu and Tri Dao. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752, 2023."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"e_1_3_2_1_14_1","volume-title":"Syncdiff: Synchronized motion diffusion for multi-body human-object interaction synthesis. arXiv preprint arXiv:2412.20104","author":"He Wenkun","year":"2024","unstructured":"Wenkun He, Yun Liu, Ruitao Liu, and Li Yi. Syncdiff: Synchronized motion diffusion for multi-body human-object interaction synthesis. arXiv preprint arXiv:2412.20104, 2024."},{"key":"e_1_3_2_1_15_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems, 33:6840--6851","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. Denoising diffusion probabilistic models. Advances in neural information processing systems, 33:6840--6851, 2020."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01607"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00171"},{"key":"e_1_3_2_1_18_1","first-page":"54","volume-title":"European Conference on Computer Vision","author":"Li Jiaman","year":"2024","unstructured":"Jiaman Li, Alexander Clegg, Roozbeh Mottaghi, Jiajun Wu, Xavier Puig, and C Karen Liu. Controllable human-object interaction synthesis. In European Conference on Computer Vision, pages 54--72. Springer, 2024."},{"key":"e_1_3_2_1_19_1","volume-title":"Object motion guided human motion synthesis. ACM Transactions on Graphics (TOG), 42(6):1--11","author":"Li Jiaman","year":"2023","unstructured":"Jiaman Li, Jiajun Wu, and C Karen Liu. Object motion guided human motion synthesis. ACM Transactions on Graphics (TOG), 42(6):1--11, 2023."},{"key":"e_1_3_2_1_20_1","volume-title":"Core4d: A 4d human-object-human interaction dataset for collaborative object rearrangement. arXiv preprint arXiv:2406.19353","author":"Liu Yun","year":"2024","unstructured":"Yun Liu, Chengwen Zhang, Ruofan Xing, Bingda Tang, Bowen Yang, and Li Yi. Core4d: A 4d human-object-human interaction dataset for collaborative object rearrangement. arXiv preprint arXiv:2406.19353, 2024."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"e_1_3_2_1_22_1","first-page":"300","volume-title":"European Conference on Computer Vision","author":"Lv Xintao","year":"2024","unstructured":"Xintao Lv, Liang Xu, Yichao Yan, Xin Jin, Congsheng Xu, Shuwen Wu, Yifan Liu, Lincheng Li, Mengxiao Bi, Wenjun Zeng, et al. Himo: A new benchmark for full-body human interacting with multiple objects. In European Conference on Computer Vision, pages 300--318. Springer, 2024."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1076-4"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2025.3573878"},{"key":"e_1_3_2_1_25_1","volume-title":"Hoi-diff: Text-driven synthesis of 3d human-object interactions using diffusion models. arXiv preprint arXiv:2312.06553","author":"Peng Xiaogang","year":"2023","unstructured":"Xiaogang Peng, Yiming Xie, Zizhao Wu, Varun Jampani, Deqing Sun, and Huaizu Jiang. Hoi-diff: Text-driven synthesis of 3d human-object interactions using diffusion models. arXiv preprint arXiv:2312.06553, 2023."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"e_1_3_2_1_27_1","volume-title":"Pointnet: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, 30","author":"Qi Charles Ruizhongtai","year":"2017","unstructured":"Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J Guibas. Pointnet: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, 30, 2017."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01265"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"e_1_3_2_1_31_1","volume-title":"Human motion diffusion model. arXiv preprint arXiv:2209.14916","author":"Tevet Guy","year":"2022","unstructured":"Guy Tevet, Sigal Raab, Brian Gordon, Yonatan Shafir, Daniel Cohen-Or, and Amit H Bermano. Human motion diffusion model. arXiv preprint arXiv:2209.14916, 2022."},{"key":"e_1_3_2_1_32_1","volume-title":"Attention is all you need. Advances in neural information processing systems, 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01271"},{"key":"e_1_3_2_1_34_1","first-page":"14959","article-title":"Language-conditioned human motion generation in 3d scenes","volume":"35","author":"Wang Zan","year":"2022","unstructured":"Zan Wang, Yixin Chen, Tengyu Liu, Yixin Zhu, Wei Liang, and Siyuan Huang. Humanise: Language-conditioned human motion generation in 3d scenes. Advances in Neural Information Processing Systems, 35:14959--14971, 2022.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_2"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32946"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02035"},{"key":"e_1_3_2_1_38_1","unstructured":"Haiwei Xue Xiangyang Luo Zhanghao Hu Xin Zhang Xunzhi Xiang Yuqin Dai Jianzhuang Liu Zhensong Zhang Minglei Li Jian Yang et al. Human motion video generation: A survey. Authorea Preprints."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02028"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_30"},{"key":"e_1_3_2_1_42_1","first-page":"265","volume-title":"European Conference on Computer Vision","author":"Zhang Zeyu","year":"2024","unstructured":"Zeyu Zhang, Akide Liu, Ian Reid, Richard Hartley, Bohan Zhuang, and Hao Tang. Motion mamba: Efficient and long sequence motion generation. In European Conference on Computer Vision, pages 265--282. Springer, 2024."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-96530-3"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3272319"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00545"}],"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\/3746027.3754848","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:42:36Z","timestamp":1765309356000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754848"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":45,"alternative-id":["10.1145\/3746027.3754848","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754848","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"}}]}}