{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T19:29:19Z","timestamp":1769801359850,"version":"3.49.0"},"reference-count":27,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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\/icassp48485.2024.10447444","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"6390-6394","source":"Crossref","is-referenced-by-count":3,"title":["Multi-Level Contrastive Learning For Hybrid Cross-Modal Retrieval"],"prefix":"10.1109","author":[{"given":"Yiming","family":"Zhao","sequence":"first","affiliation":[{"name":"Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China"}]},{"given":"Haoyu","family":"Lu","sequence":"additional","affiliation":[{"name":"Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China"}]},{"given":"Shiqi","family":"Zhao","sequence":"additional","affiliation":[{"name":"China Unicom Research Institute,Beijing,China"}]},{"given":"Haoran","family":"Wu","sequence":"additional","affiliation":[{"name":"China Unicom Research Institute,Beijing,China"}]},{"given":"Zhiwu","family":"Lu","sequence":"additional","affiliation":[{"name":"Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00365"},{"key":"ref3","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413917"},{"key":"ref6","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"ref8","article-title":"Rtic: Residual learning for text and image composition using graph convolutional network","author":"Shin","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"ref11","article-title":"Modality-agnostic attention fusion for visual search with text feedback","author":"Dodds","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00118"},{"key":"ref13","article-title":"Curlingnet: Compositional learning between images and text for fashion iq data","author":"Yu","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00543"},{"key":"ref15","article-title":"Artemis: Attention-based retrieval with text-explicit matching and implicit similarity","volume-title":"ICLR","author":"Delmas"},{"key":"ref16","article-title":"Conditioned image retrieval for fashion using contrastive learning and clip-based features","author":"Baldrati","year":"2022","journal-title":"ACM Multimedia Asia"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref21","article-title":"Dialog-based interactive image retrieval","volume":"31","author":"Guo","year":"2018","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"ref23","article-title":"Image search with text feedback by additive attention compositional learning","author":"Tian","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00067"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref26","article-title":"Multimodal residual learning for visual qa","volume":"29","author":"Kim","year":"2016","journal-title":"NeurIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475619"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"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\/10447444.pdf?arnumber=10447444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:38:37Z","timestamp":1722577117000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447444\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447444","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}