{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T21:49:30Z","timestamp":1770328170248,"version":"3.49.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2021ZD0112100"],"award-info":[{"award-number":["2021ZD0112100"]}]},{"name":"National NSF of China","award":["61972022"],"award-info":[{"award-number":["61972022"]}]},{"name":"National NSF of China","award":["U1936212"],"award-info":[{"award-number":["U1936212"]}]},{"name":"National NSF of China","award":["62120106009"],"award-info":[{"award-number":["62120106009"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3273466","type":"journal-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:36:03Z","timestamp":1683308163000},"page":"916-928","source":"Crossref","is-referenced-by-count":5,"title":["Enhance Composed Image Retrieval via Multi-Level Collaborative Localization and Semantic Activeness Perception"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1503-4513","authenticated-orcid":false,"given":"Gangjian","family":"Zhang","sequence":"first","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3803-9763","authenticated-orcid":false,"given":"Shikui","family":"Wei","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4998-4576","authenticated-orcid":false,"given":"Huaxin","family":"Pang","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9769-5042","authenticated-orcid":false,"given":"Shuang","family":"Qiu","sequence":"additional","affiliation":[{"name":"College of Data Science, Taiyuan University of Technology, Taiyuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3295822"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"ref4","article-title":"Retrieving similar e-commerce images using deep learning","author":"Sharma","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018295"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00226"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_15"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.374"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00365"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475619"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475483"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00067"},{"key":"ref18","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3469877.3493593"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475659"},{"key":"ref23","article-title":"VSE : Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.47"},{"key":"ref25","first-page":"676","article-title":"Dialog-based interactive image retrieval","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Guo","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/76.718510"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54193-8_8"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.163"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00804"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.93"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_19"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_46"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.125"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093427"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00118"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462967"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01371"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2931352"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2922128"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"ref46","first-page":"30.1","article-title":"Referring expression object segmentation with caption-aware consistency","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Chen","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.2100463"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref51","first-page":"13","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref52","article-title":"Bilingunet: Image segmentation by modulating top-down and bottom-up visual processing with referring expressions","author":"Can"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074803"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref57","first-page":"1857","article-title":"Improved deep metric learning with multi-class N-pair loss objective","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn","year":"2016"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_48"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref60","article-title":"Modality-agnostic attention fusion for visual search with text feedback","author":"Dodds","year":"2020"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10120671.pdf?arnumber=10120671","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:52:33Z","timestamp":1705690353000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10120671\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3273466","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}