{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T04:02:00Z","timestamp":1744344120349,"version":"3.40.4"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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":[[2024,11,21]]},"DOI":"10.1109\/crc63701.2024.10949885","type":"proceedings-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T17:51:01Z","timestamp":1744221061000},"page":"66-70","source":"Crossref","is-referenced-by-count":0,"title":["Implicit Fine-Grained Alignment for Cross-Modal Retrieval"],"prefix":"10.1109","author":[{"given":"Hui","family":"Liu","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Avic Chengdu Aircraft Design and Research Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao-ping","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Hong","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Avic Chengdu Aircraft Design and Research Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Avic Chengdu Aircraft Design and Research Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian-cai","family":"Wan","sequence":"additional","affiliation":[{"name":"Avic Chengdu Aircraft Design and Research Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tai-li","family":"Bai","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2022.3178899"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2021.3135825"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref4","first-page":"2024","author":"Fartash","year":"2017","journal-title":"VSE++: Improving visual-semantic embeddings with hard negatives[J\/OL]"},{"key":"ref5","article-title":"Stacked cross attention for image-text matching[C]","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Kuang-Huei","year":"2018"},{"issue":"2","key":"ref6","first-page":"023022","article-title":"Learning discriminative common alignments for crossmodal retrieval[J]","volume":"33","author":"Hui","year":"2024","journal-title":"Journal of Electronic Imaging"},{"key":"ref7","first-page":"185","article-title":"Consensus-aware visual-semantic embedding for image-text matching[C]","volume-title":"Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXIV 16","author":"Haoran","year":"2020"},{"article-title":"Learning the best pooling strategy for visual semantic embedding[C]","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Jiacheng","key":"ref8"},{"issue":"1","key":"ref9","first-page":"641","article-title":"Image-text embedding learning via visual and textual semantic reasoning[J]","volume":"45","author":"Kunpeng","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"article-title":"Multi-view visual semantic embedding[C]","volume-title":"Proceedings of IJCAI","author":"Zheng","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00957"},{"journal-title":"Use what you have: Video retrieval using representations from collaborative experts[J\/OL]","year":"2019","author":"Yang","key":"ref12"},{"article-title":"Graph structured network for image-text matching[C]","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chunxiao","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3499027"},{"article-title":"Fine-grained video-text retrieval with hierarchical graph reasoning[C]","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Shizhe","key":"ref15"},{"article-title":"Deep evidential learning with noisy correspondence for cross-modal retrieval[C]","volume-title":"Proceedings of the 30th ACM International Conference on Multimedia","author":"Yang","key":"ref16"},{"article-title":"Visual semantic reasoning for image-text matching[C]","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Kunpeng","key":"ref17"},{"article-title":"Fine-grained image-text matching by cross-modal hard aligning network[C]","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhengxin","key":"ref18"},{"article-title":"Negative-aware attention framework for image-text matching[C]","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Kun","key":"ref19"},{"article-title":"Bottom-up and top-down attention for image captioning and visual question answering[C]","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Peter","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3253548"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"article-title":"Microsoft COCO: Common objects in context[C]","volume-title":"Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V","author":"Tsung-Yi","key":"ref23"},{"issue":"7","key":"ref24","first-page":"2866","article-title":"Learning dual semantic relations with graph attention for image-text matching[J]","volume":"31","author":"Keyu","year":"2020","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"article-title":"Learning semantic relationship among instances for image-text matching[C]","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zheren","key":"ref25"}],"event":{"name":"2024 9th International Conference on Control, Robotics and Cybernetics (CRC)","start":{"date-parts":[[2024,11,21]]},"location":"Penang, Malaysia","end":{"date-parts":[[2024,11,23]]}},"container-title":["2024 9th International Conference on Control, Robotics and Cybernetics (CRC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10949866\/10949856\/10949885.pdf?arnumber=10949885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T04:57:02Z","timestamp":1744261022000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10949885\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/crc63701.2024.10949885","relation":{},"subject":[],"published":{"date-parts":[[2024,11,21]]}}}