{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:17:27Z","timestamp":1740100647976,"version":"3.37.3"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004478","name":"Beijing Union University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004478","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747849","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"1965-1969","source":"Crossref","is-referenced-by-count":4,"title":["Transtl: Spatial-Temporal Localization Transformer for Multi-Label Video Classification"],"prefix":"10.1109","author":[{"given":"Hongjun","family":"Wu","sequence":"first","affiliation":[{"name":"Beijing Union University,Beijing Key Laboratory of Information Service Engineering,Beijing,China"}]},{"given":"Mengzhu","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Union University,Beijing Key Laboratory of Information Service Engineering,Beijing,China"}]},{"given":"Yongcheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}]},{"given":"Hongzhe","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Union University,Beijing Key Laboratory of Information Service Engineering,Beijing,China"}]},{"given":"Cheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Union University,Beijing Key Laboratory of Information Service Engineering,Beijing,China"}]},{"given":"Xuewei","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Union University,Beijing Key Laboratory of Information Service Engineering,Beijing,China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00887"},{"key":"ref12","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"Vidtr: Video transformer without convolutions","year":"2021","author":"li","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"article-title":"Video swin transformer","year":"2021","author":"liu","key":"ref15"},{"key":"ref16","article-title":"Asymmetric loss for multi-label classification","author":"ben-baruch","year":"2021","journal-title":"ICCV"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref18","article-title":"Videograph: Recognizing minutes-long human activities in videos","author":"hussein","year":"2019","journal-title":"ICCV Workshop on Scene Graph Representation and Learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref4","first-page":"649","article-title":"Attention-driven dynamic graph convolutional network for multi-label image recognition","author":"ye","year":"2020","journal-title":"European Conference on Computer Vision"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6964"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.599"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2985708"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref7","first-page":"803","article-title":"Temporal relational reasoning in videos","author":"zhou","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref1","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"ICLRE"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"key":"ref20","first-page":"510","article-title":"Hollywood in homes: Crowdsourcing data collection for activity understanding","author":"sigurdsson","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1013-y"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747849.pdf?arnumber=9747849","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:12:46Z","timestamp":1661199166000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747849\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747849","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}