{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T19:01:09Z","timestamp":1758394869444,"version":"3.37.3"},"reference-count":22,"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"}]},{"DOI":"10.13039\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","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\/icassp48485.2024.10445903","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"3260-3264","source":"Crossref","is-referenced-by-count":5,"title":["Self-Distilled Dynamic Fusion Network for Language-Based Fashion Retrieval"],"prefix":"10.1109","author":[{"given":"Yiming","family":"Wu","sequence":"first","affiliation":[{"name":"Zhejiang University of Technology,School of Computer Science and Technology,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hangfei","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology,School of Computer Science and Technology,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangfang","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang Laboratory,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yilong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology,School of Computer Science and Technology,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ronghua","family":"Liang","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology,School of Computer Science and Technology,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01371"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612088"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3133897"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_48"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"article-title":"ARTEMIS: attention-based retrieval with text-explicit matching and implicit similarity","volume-title":"Proc. ICLR","author":"Delmas","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462967"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"journal-title":"Modality-agnostic attention fusion for visual search with text feedback","year":"2020","author":"Dodds","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475619"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475659"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00067"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3204213"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3584703"},{"journal-title":"Relieving triplet ambiguity: Consensus network for language-guided image retrieval","year":"2023","author":"Zhang","key":"ref19"},{"key":"ref20","first-page":"361","article-title":"Multimodal residual learning for visual QA","volume-title":"Proc. NeurIPS","author":"Kim"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3346434"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3235495"}],"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\/10445903.pdf?arnumber=10445903","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:58:27Z","timestamp":1722574707000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445903\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445903","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}