{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:22:35Z","timestamp":1771698155075,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"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":[[2024,12,8]]},"DOI":"10.1109\/vcip63160.2024.10849921","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:36:57Z","timestamp":1738003017000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Anchoring Vision and Language Knowledge for Weakly Supervised Group Activity Recognition"],"prefix":"10.1109","author":[{"given":"Muhammad Adi","family":"Nugroho","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST)"}]},{"given":"Jinyoung","family":"Park","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST)"}]},{"given":"Donguk","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST)"}]},{"given":"Changick","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST)"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Radford"},{"key":"ref2","first-page":"4904","article-title":"Scaling up visual and Vision-Language representation learning with noisy text supervision","volume-title":"Proceedings of Machine Learning Research","volume":"139","author":"Jia"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01945"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2023.104789"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00544"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3265280"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127135"},{"key":"ref9","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.217"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00092"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00738"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3283282"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00300"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249906"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240572"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01341"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3228731"}],"event":{"name":"2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)","location":"Tokyo, Japan","start":{"date-parts":[[2024,12,8]]},"end":{"date-parts":[[2024,12,11]]}},"container-title":["2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10849624\/10849781\/10849921.pdf?arnumber=10849921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:29:23Z","timestamp":1738045763000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849921\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/vcip63160.2024.10849921","relation":{},"subject":[],"published":{"date-parts":[[2024,12,8]]}}}