{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:52:09Z","timestamp":1782316329700,"version":"3.54.5"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,8]]},"DOI":"10.1109\/icip49359.2023.10222927","type":"proceedings-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T17:58:31Z","timestamp":1694455111000},"page":"1970-1974","source":"Crossref","is-referenced-by-count":1,"title":["Zero-Shot Human-Object Interaction (HOI) Classification by Bridging Generative and Contrastive Image-Language Models"],"prefix":"10.1109","author":[{"given":"Ying","family":"Jin","sequence":"first","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinpeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jenq-Neng","family":"Hwang","sequence":"additional","affiliation":[{"name":"University of Washington"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zicheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.122"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00181"},{"key":"ref3","article-title":"Relvit: Concept-guided vision transformer for visual relational reasoning","author":"Ma","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.129"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_25"},{"key":"ref6","first-page":"33","article-title":"Attentional pooling for action recognition","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Girdhar"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_4"},{"key":"ref8","article-title":"Efficient self-supervised vision transformers for representation learning","author":"Li","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_35"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00056"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00101"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"ref13","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.567"},{"key":"ref16","article-title":"Git: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00528"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01895"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00046"},{"key":"ref23","article-title":"Hake: Human activity knowledge engine","author":"Li","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/169546"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_41"}],"event":{"name":"2023 IEEE International Conference on Image Processing (ICIP)","location":"Kuala Lumpur, Malaysia","start":{"date-parts":[[2023,10,8]]},"end":{"date-parts":[[2023,10,11]]}},"container-title":["2023 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10221937\/10221892\/10222927.pdf?arnumber=10222927","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T20:48:06Z","timestamp":1709326086000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10222927\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,8]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icip49359.2023.10222927","relation":{},"subject":[],"published":{"date-parts":[[2023,10,8]]}}}