{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:03:53Z","timestamp":1764403433332,"version":"3.33.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10848810","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["GMA: Green Multi-Modal Alignment for Image-Text Retrieval"],"prefix":"10.1109","author":[{"given":"Tsung-Shan","family":"Yang","sequence":"first","affiliation":[{"name":"University of Southern California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun-Cheng","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Southern California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengwei","family":"Wei","sequence":"additional","affiliation":[{"name":"University of Southern California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suya","family":"You","sequence":"additional","affiliation":[{"name":"University of Southern California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.-C. Jay","family":"Kuo","sequence":"additional","affiliation":[{"name":"University of Southern California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00119"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning, PMLR","author":"Radford"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2022.103685"},{"key":"ref13","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning, PMLR","author":"Chen"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3266887"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01095"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/106"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00183"},{"article-title":"Roberta: A robustly optimized bert pretraining approach","year":"2019","author":"Liu","key":"ref25"},{"key":"ref26","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2024,12,3]]},"location":"Macau, Macao","end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10848810.pdf?arnumber=10848810","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:20:04Z","timestamp":1738045204000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10848810\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10848810","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}