{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T01:06:06Z","timestamp":1768093566107,"version":"3.49.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683869","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"3970-3974","source":"Crossref","is-referenced-by-count":12,"title":["A Neighbor-aware Approach for Image-text Matching"],"prefix":"10.1109","author":[{"given":"Chunxiao","family":"Liu","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhendong","family":"Mao","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenyu","family":"Zang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref11","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2018","journal-title":"BMVC"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240521"},{"key":"ref14","article-title":"Look, imagine and match: Improving textual-visual cross-modal retrieval with generative models","author":"gu","year":"2017","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref16","article-title":"Deep captioning with multimodal recurrent neural networks","author":"mao","year":"2014","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.142"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref3","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume":"3","author":"karpathy","year":"2014"},{"key":"ref6","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"CoRR"},{"key":"ref5","article-title":"Learning semantic concepts and order for image and sentence matching","author":"huang","year":"2017","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref7","first-page":"iii","article-title":"Deep canonical correlation analysis","author":"andrew","year":"2013","journal-title":"ICML"},{"key":"ref2","first-page":"7254","article-title":"Instance-aware image and sentence matching with selective mul-timodal lstm","author":"huang","year":"2016"},{"key":"ref9","first-page":"1","article-title":"Learning two-branch neural networks for image-text matching tasks","author":"wang","year":"2017","journal-title":"TPAMI"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.208"},{"key":"ref20","first-page":"4188","article-title":"Framing image description as a ranking task: data, models and evaluation metrics","author":"hodosh","year":"2015","journal-title":"AAAI"},{"key":"ref22","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref24","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref23","article-title":"Ten-sorflow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016"},{"key":"ref26","article-title":"Fisher vectors derived from hybrid gaussian-laplacian mixture models for image annotation","author":"klein","year":"2014","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, UK","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683869.pdf?arnumber=8683869","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:18:56Z","timestamp":1755800336000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683869\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683869","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}