{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T22:36:01Z","timestamp":1784673361676,"version":"3.55.0"},"reference-count":143,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62201342"],"award-info":[{"award-number":["62201342"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01165","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12535-12548","source":"Crossref","is-referenced-by-count":2,"title":["Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions"],"prefix":"10.1109","author":[{"given":"Liang","family":"Xu","sequence":"first","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengqun","family":"Yang","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zili","family":"Lin","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Xu","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Liu","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Congsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of AI School of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Qin","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingdong","family":"Sheng","sequence":"additional","affiliation":[{"name":"Lenovo"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunhui","family":"Liu","sequence":"additional","affiliation":[{"name":"Lenovo"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Jin","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichao","family":"Yan","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Easymocap - make human motion capture easier"},{"key":"ref2","volume-title":"Opencv: opencv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00079"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610690"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02032"},{"key":"ref6","article-title":"Introducing hot3d: An egocentric dataset for 3d hand and object tracking","author":"Banerjee","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01260"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_18"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00843"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_22"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref13","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.00047"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.034"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_23"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2018.11.110"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau9757"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00702"},{"key":"ref20","first-page":"1","article-title":"Towards collaborative robots as intelligent co-workers in human-robot joint tasks: what to do and who does it?","volume-title":"ISR 2020; 52th International Symposium on Robotics","author":"Cunha","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.02.016"},{"key":"ref22","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proceedings of the European conference on computer vision (ECCV)","author":"Damen","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01880"},{"key":"ref25","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00054"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-021-00836-z"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01239"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01244"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00054"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_25"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247805"},{"key":"ref33","first-page":"7214","article-title":"Threedimensional reconstruction of human interactions","author":"Fieraru","year":"2020","journal-title":"CVPR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01271"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00072"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01081"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680679"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00237"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01118"},{"key":"ref44","article-title":"Omnih2o: Universal and dexterous human-to-humanoid whole-body teleoperation and learning","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/iros58592.2024.10801984"},{"key":"ref46","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref47","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16788-1_18"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240675"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01352"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_26"},{"key":"ref53","article-title":"Egoposer: Robust real-time ego-body pose estimation in large scenes","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00859"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00171"},{"key":"ref56","article-title":"Harmon: Whole-body motion generation of humanoid robots from language descriptions","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref58","article-title":"Realtime active vision for a humanoid soccer robot using deep reinforcement learning","author":"Khatibi","year":"2020","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Openvla: An open-source vision-language-action model","author":"Jin Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2023.109277"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00998"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01644"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01963"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00687"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02042-6"},{"key":"ref67","article-title":"Motion-x: A largescale 3d expressive whole-body human motion dataset","author":"Lin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01997"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_41"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00328"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02054"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref75","first-page":"25019","article-title":"Dynamics-regulated kinematic policy for egocentric pose estimation","volume":"34","author":"Luo","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_17"},{"key":"ref77","article-title":"Diff-ip2d: Diffusion-based hand-object interaction prediction on egocentric videos","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref78","article-title":"A survey on vision-language-action models for embodied ai","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2572685"},{"key":"ref80","first-page":"651","article-title":"Dexvip: Learning dexterous grasping with human hand pose priors from video","volume-title":"Conference on Robot Learning","author":"Mandikal","year":"2022"},{"key":"ref81","author":"Valls Mascaro","year":"2024","journal-title":"Hoi4abot: Human-object interaction anticipation for human intention reading collaborative robots"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00119"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322961"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00878"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.721"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00991"},{"key":"ref87","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","author":"O\u2019Neill","year":"2023","journal-title":"arXiv preprint"},{"key":"ref88","article-title":"OpenAI","year":"2023","journal-title":"GPT-3.5 turbo fine-tuning and api updates"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw67362.2025.00271"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01080"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids53995.2022.10000239"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3396074"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2898748"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_33"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3011353"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925867"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids57100.2023.10375203"},{"key":"ref101","article-title":"Human motion diffusion as a generative prior","author":"Shafir","year":"2023","journal-title":"arXiv preprint"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657488"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00202"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00855"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"ref106","article-title":"Human motion diffusion model","author":"Tevet","year":"2022","journal-title":"arXiv preprint"},{"key":"ref107","article-title":"Learning robot soccer from egocentric vision with deep reinforcement learning","author":"Tirumala","year":"2024","journal-title":"arXiv preprint"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130396"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00832"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01252"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00080"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01854"},{"key":"ref113","author":"Wang","year":"2024","journal-title":"Quo vadis, motion generation? from large language models to large motion models"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_27"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01548"},{"key":"ref116","article-title":"Hoh: Markerless multimodal human-object-human handover dataset with large object count","volume":"36","author":"Wiederhold","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"ref118","article-title":"Unified human-scene interaction via prompted chain-of-contacts","author":"Xiao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref119","article-title":"Sparsegs: Realtime 360deg sparse view synthesis using gaussian splatting","author":"Xiong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00212"},{"key":"ref121","author":"Xu","year":"2024","journal-title":"Motionbank: A large-scale video motion benchmark with disentangled rule-based annotations"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02101"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00173"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01371"},{"key":"ref125","article-title":"D3d-hoi: Dynamic 3d human-object interactions from videos","author":"Xu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref126","article-title":"Humanvla: Towards vision-language directed object rearrangement by physical humanoid","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00387"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01806"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00663"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01632"},{"key":"ref131","article-title":"Lm-gaussian: Boost sparse-view 3d gaussian splatting with large model priors","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01076"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239234"},{"key":"ref134","article-title":"Core4d: A 4d human-object-human interaction dataset for collaborative object rearrangement","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33070"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-025-00074-1"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00056"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_30"},{"key":"ref139","article-title":"Scenic: Scene-aware semantic navigation with instruction-guided control","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref140","article-title":"3d-vla: A 3d vision-language-action generative world model","author":"Zhen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.511"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_21"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446118.pdf?arnumber=11446118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:40:20Z","timestamp":1777531220000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446118\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":143,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01165","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}