{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T10:05:10Z","timestamp":1766484310954,"version":"3.27.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,8]]},"DOI":"10.1109\/icarm62033.2024.10715789","type":"proceedings-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T17:27:32Z","timestamp":1729272452000},"page":"70-75","source":"Crossref","is-referenced-by-count":3,"title":["Context-aware Emotion Recognition Based on Vision-Language Pre-trained Model"],"prefix":"10.1109","volume":"37","author":[{"given":"XingLin","family":"Li","sequence":"first","affiliation":[{"name":"Southeast University,School of Automation,Nanjing,China,210008"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinde","family":"Li","sequence":"additional","affiliation":[{"name":"Southeast University,School of Automation,Nanjing,China,210008"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanfei","family":"Hu","sequence":"additional","affiliation":[{"name":"Southeast University,School of Automation,Nanjing,China,210008"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaping","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100000"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01722"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095448"},{"issue":"1","key":"ref3","article-title":"\u2019Intensity-aware loss for dynamic facial expression recognition in the wild","volume-title":"Proc. AAAI Conf. Artif. Intell. (AAAI)","volume":"37","author":"Hanting"},{"issue":"2020","key":"ref4","first-page":"1195","article-title":"\u2019Deep facial expression recognition: A survey","volume":"13","author":"Shan","journal-title":"IEEE Trans. Affect. Comput. (T-AFFC)"},{"key":"ref5","article-title":"\u2019Facial emotion recognition: State of the art performance on FER2013","author":"Khaireddin","year":"2021","journal-title":"arXiv preprint arXiv:2105.03588"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref10","article-title":"Improving clip training with language rewrites","volume":"36","author":"Fan","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/773"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3036075"},{"key":"ref13","article-title":"Prompting visual-language models for dynamic facial expression recognition","author":"Zhao","year":"2023","journal-title":"arXiv preprint arXiv:2308.13382"},{"article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Int. Conf. Mach. Learn. (ICML) PMLR","author":"Jia","key":"ref14"},{"key":"ref15","article-title":"Simvlm: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021","journal-title":"arXiv preprint arXiv:2108.10904"},{"issue":"1","key":"ref16","first-page":"5","article-title":"Real-Time Emotion Recognition Using Deep Learning Methods: Systematic Review","volume":"2","author":"Muthana","journal-title":"Intelligent Methods in Engineering Sciences"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_20"},{"key":"ref18","article-title":"Videoclip: Contrastive pre-training for zero-shot video-text understanding","author":"Hu","year":"2021","journal-title":"arXiv preprint arXiv:2109.14084"},{"article-title":"Scaling language-image pre-training via masking","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Yanghao","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/e21070646"},{"article-title":"Continuous emotion recognition in videos by fusing facial expression, head pose and eye gaze","volume-title":"2019 Int. Conf. Multimodal Interact. (ICMI)","author":"Suowei","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803460"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACII59096.2023.10388075"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01822"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00217"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3182780"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746047"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2021.3079495"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2976812"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2694399"}],"event":{"name":"2024 International Conference on Advanced Robotics and Mechatronics (ICARM)","start":{"date-parts":[[2024,7,8]]},"location":"Tokyo, Japan","end":{"date-parts":[[2024,7,10]]}},"container-title":["2024 International Conference on Advanced Robotics and Mechatronics (ICARM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10715684\/10715739\/10715789.pdf?arnumber=10715789","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T04:53:50Z","timestamp":1729313630000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10715789\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,8]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icarm62033.2024.10715789","relation":{},"subject":[],"published":{"date-parts":[[2024,7,8]]}}}