{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:41:50Z","timestamp":1777653710358,"version":"3.51.4"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650814","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":22,"title":["MH-DETR: Video Moment and Highlight Detection with Cross-modal Transformer"],"prefix":"10.1109","author":[{"given":"Yifang","family":"Xu","sequence":"first","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunzhuo","family":"Sun","sequence":"additional","affiliation":[{"name":"Hubei Normal University,School of Physics and Electronics,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benxiang","family":"Zhai","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youyao","family":"Jia","sequence":"additional","affiliation":[{"name":"Gosuncn Chuanglian Technology Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sidan","family":"Du","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3258628"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3117472"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01364"},{"key":"ref5","article-title":"Learning 2d temporal adjacent networks for moment localization with natural language","volume":"34","journal-title":"AAAI"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00787"},{"key":"ref7","first-page":"11 846","article-title":"Detecting Moments and Highlights in Videos via Natural Language Queries","volume":"34","author":"Lei","year":"2021","journal-title":"NeurIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.773"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"},{"key":"ref12","first-page":"28 442","article-title":"End-to-end multi-modal video temporal grounding","volume":"34","author":"Chen","year":"2021","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428446"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-93046-2_39"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/app14051894"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3340103"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3275156"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3451390"},{"key":"ref19","first-page":"4733","article-title":"Learning representations from audio-visual spatial alignment","volume":"33","author":"Morgado","year":"2020","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","first-page":"4171","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"Proceedings of NAACL-HLT","author":"Kenton"},{"key":"ref22","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20133"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref27","first-page":"15 908","article-title":"Transformer in transformer","volume":"34","author":"Han","year":"2021","journal-title":"NeurIPS"},{"key":"ref28","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref29","article-title":"A Survey on Video Moment Localization","author":"Liu","year":"2022","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00802"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00308"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983349"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298994"},{"key":"ref34","article-title":"Temporal localization of moments in video collections with natural language","author":"Escorcia","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00135"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref39","first-page":"5179","article-title":"Tvsum: Summarizing web videos using titles","author":"Song","year":"2015","journal-title":"CVPR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref43","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3113791"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref48","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref49","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00304"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_18"},{"key":"ref53","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650814.pdf?arnumber=10650814","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T06:24:52Z","timestamp":1725949492000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650814\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650814","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}