{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:52:54Z","timestamp":1740102774545,"version":"3.37.3"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014890","name":"Qilu University of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014890","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014890","name":"Qilu University of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014890","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448127","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"8286-8290","source":"Crossref","is-referenced-by-count":0,"title":["Learning Fine-Grained Information Alignment for Calibrated Cross-Modal Retrieval"],"prefix":"10.1109","author":[{"given":"Jianhua","family":"Dong","sequence":"first","affiliation":[{"name":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengrong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hu","family":"Liang","sequence":"additional","affiliation":[{"name":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"author":"Schuhmann","key":"ref1","article-title":"400m: Open dataset of clip-filtered 400 million image-text pairs. arxiv 2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02226"},{"article-title":"Coca: Contrastive captioners are image-text foundation models","year":"2022","author":"Yu","key":"ref3"},{"article-title":"Mammut: A simple architecture for joint learning for multimodal tasks","year":"2023","author":"Kuo","key":"ref4"},{"key":"ref5","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Adv. NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.43"},{"article-title":"When and why visionlanguage models behave like bags-of-words, and what to do about it?","volume-title":"ICLR","author":"Yuksekgonul","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00294"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00261"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy","key":"ref14"},{"issue":"1","key":"ref15","first-page":"411","article-title":"spacy 2: Natural language understanding with bloom embeddings, convolutional neural networks and incremental parsing","volume":"7","author":"Honnibal","year":"2017"},{"article-title":"Vl-checklist: Evaluating pre-trained vision-language models with objects, attributes and relations","year":"2022","author":"Zhao","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"ref18","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"NeurIPS","volume":"34","author":"Li"},{"article-title":"Ernie-vil 2.0: Multi-view contrastive learning for image-text pre-training","year":"2022","author":"Shan","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448127.pdf?arnumber=10448127","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:49:05Z","timestamp":1722581345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448127\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448127","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}