{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T01:18:28Z","timestamp":1725585508894},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"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":[[2020,10]]},"DOI":"10.1109\/icip40778.2020.9190820","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T20:45:18Z","timestamp":1601498718000},"page":"1401-1405","source":"Crossref","is-referenced-by-count":0,"title":["Retrieving and Highlighting Action with Spatiotemporal Reference"],"prefix":"10.1109","author":[{"given":"Seito","family":"Kasai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchi","family":"Ishikawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masaki","family":"Hayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshimitsu","family":"Aoki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kensho","family":"Hara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirokatsu","family":"Kataoka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206064"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref12","article-title":"Use what you have: Video retrieval using representations from collaborative experts","author":"liu","year":"2019","journal-title":"Proceedings of the British Machine Vision Conference (BMVC)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref15","first-page":"5288","article-title":"Msrvtt: A large video description dataset for bridging video and language","author":"xu","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref16","article-title":"A short note on the kinetics-700 human action dataset","author":"carreira","year":"2019","journal-title":"arXiv preprint arXiv 1907 09977"},{"key":"ref17","first-page":"618","article-title":"Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization","author":"selvaraju","year":"2016","journal-title":"IEEElCVF International Conference on Computer Vision (ICCV)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref4","first-page":"5814","article-title":"Adversarial representation learning for text-toimage matching","author":"sarafianos","year":"2019","journal-title":"IEEElCVF International Conference on Computer Vision (ICCV)"},{"key":"ref3","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2018","journal-title":"Proceedings of the British Machine Vision Conference (BMVC)"},{"key":"ref6","first-page":"6609","article-title":"Unified visualsemantic embeddings: Bridging vision and language with structured meaning representations","author":"wu","year":"2019","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00419"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00054"},{"key":"ref2","article-title":"Learning visually-grounded semantics from contrastive adversarial samples","author":"shi","year":"2018","journal-title":"Proceedings of the International Conference On Computational Linguistics (COLING)"},{"key":"ref1","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2015","journal-title":"Transactions of the Association for Computational Linguistics (TACL)"},{"key":"ref9","first-page":"19","article-title":"Learning a Text-Video Embedding from Incomplete and Heterogeneous Data","author":"miech","year":"2018","journal-title":"Proc ACM International Conference on Multimedia (ACM MM)"}],"event":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2020,10,25]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2020,10,28]]}},"container-title":["2020 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9184803\/9190635\/09190820.pdf?arnumber=9190820","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:17:35Z","timestamp":1656375455000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9190820\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icip40778.2020.9190820","relation":{},"subject":[],"published":{"date-parts":[[2020,10]]}}}