{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T15:39:30Z","timestamp":1772206770278,"version":"3.50.1"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2017YFC1703503"],"award-info":[{"award-number":["2017YFC1703503"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2021ZD0112100"],"award-info":[{"award-number":["2021ZD0112100"]}]},{"name":"National N S F of China","award":["61972022"],"award-info":[{"award-number":["61972022"]}]},{"name":"National N S F of China","award":["U1936212"],"award-info":[{"award-number":["U1936212"]}]},{"name":"National N S F 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":[[2023]]},"DOI":"10.1109\/tmm.2022.3208742","type":"journal-article","created":{"date-parts":[[2022,9,22]],"date-time":"2022-09-22T22:58:46Z","timestamp":1663887526000},"page":"6446-6457","source":"Crossref","is-referenced-by-count":13,"title":["Heterogeneous Feature Alignment and Fusion in Cross-Modal Augmented Space for Composed Image Retrieval"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4998-4576","authenticated-orcid":false,"given":"Huaxin","family":"Pang","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Advanced Information Science and Network Technology, 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":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1503-4513","authenticated-orcid":false,"given":"Gangjian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2128-0190","authenticated-orcid":false,"given":"Shiyin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Advanced Information Science and Network Technology, 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":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Advanced Information Science and Network Technology, Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00118"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref12","article-title":"Modality-agnostic attention fusion for visual search with text feedback","author":"dodds","year":"2020"},{"key":"ref56","first-page":"361","article-title":"Multimodal residual learning for visual QA","author":"kim","year":"0","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref15","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"37","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref59","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref52","article-title":"Gated multimodal units for information fusion","author":"ovalle","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2922128"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.201"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1065"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074803"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1436"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00365"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093427"},{"key":"ref48","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2017"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.163"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2582379"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.125"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00804"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2876822"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018295"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00226"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00243"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/76.718510"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2957948"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2697824"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.93"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2942480"},{"key":"ref30","first-page":"263","article-title":"Referring expression object segmentation with caption-aware consistency","author":"chen","year":"0","journal-title":"Proc 30th Brit Mach Vis Conf"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_15"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2100463"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.244"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_46"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_19"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298744"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.11"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref68","first-page":"770","article-title":"Deep residual learning for image recognition","author":"kaiming","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref23","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref69","first-page":"4974","article-title":"A simple neural network module for relational reasoning","author":"santoro","year":"0","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref20","first-page":"6077","article-title":"Bottom-up and top-down attention for image captioning and VQA","author":"anderson","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref64","article-title":"The fashion IQ dataset: Retrieving images by combining side information and relative natural language feedback","author":"guo","year":"2019"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.145"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298744"},{"key":"ref21","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"0","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_48"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2441003"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref60","first-page":"104","article-title":"Uniter: Universal image-text representation learning","author":"chen","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref61","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09899752.pdf?arnumber=9899752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T20:00:16Z","timestamp":1701115216000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9899752\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3208742","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}