{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:41:26Z","timestamp":1781797286067,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":79,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680623","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"9340-9349","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Two in One Go: Single-stage Emotion Recognition with Decoupled Subject-context Transformer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4703-7778","authenticated-orcid":false,"given":"Xinpeng","family":"Li","sequence":"first","affiliation":[{"name":"Shenzhen Technology University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2331-3619","authenticated-orcid":false,"given":"Teng","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hongkong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3508-756X","authenticated-orcid":false,"given":"Jian","family":"Zhao","sequence":"additional","affiliation":[{"name":"China Telecom & Northwestern Polytechnical University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4338-687X","authenticated-orcid":false,"given":"Shuyi","family":"Mao","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5916-8965","authenticated-orcid":false,"given":"Jinbao","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1701-9141","authenticated-orcid":false,"given":"Feng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5783-321X","authenticated-orcid":false,"given":"Xiaojiang","family":"Peng","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0019-4197","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"China Telecom & Northwestern Polytechnical University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00924"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_3_1","volume-title":"Group detr: Fast training convergence with decoupled one-to-many label assignment. arXiv preprint arXiv:2207.13085","author":"Chen Qiang","year":"2022","unstructured":"Qiang Chen, Xiaokang Chen, Gang Zeng, and Jingdong Wang. 2022. Group detr: Fast training convergence with decoupled one-to-many label assignment. arXiv preprint arXiv:2207.13085 (2022)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01400"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01471"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547936"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.03.012"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2515606"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"e_1_3_2_1_10_1","volume-title":"The expression of the emotions in man and animals","author":"Darwin Charles","unstructured":"Charles Darwin and Phillip Prodger. 1998. The expression of the emotions in man and animals. Oxford University Press, USA."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3048693"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3091169"},{"key":"e_1_3_2_1_14_1","volume-title":"Istr: End-to-end instance segmentation with transformers. arXiv preprint arXiv:2105.00637","author":"Hu Jie","year":"2021","unstructured":"Jie Hu, Liujuan Cao, Yao Lu, ShengChuan Zhang, Yan Wang, Ke Li, Feiyue Huang, Ling Shao, and Rongrong Ji. 2021. Istr: End-to-end instance segmentation with transformers. arXiv preprint arXiv:2105.00637 (2021)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01897"},{"key":"e_1_3_2_1_17_1","first-page":"2755","article-title":"Context based emotion recognition using emotic dataset","volume":"42","author":"Kosti Ronak","year":"2019","unstructured":"Ronak Kosti, Jose M Alvarez, Adria Recasens, and Agata Lapedriza. 2019. Context based emotion recognition using emotic dataset. TPAMI, Vol. 42, 11 (2019), 2755--2766.","journal-title":"TPAMI"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00603"},{"key":"e_1_3_2_1_19_1","unstructured":"Jiyoung Lee Seungryong Kim Sunok Kim Jungin Park and Kwanghoon Sohn. 2019. Context-aware emotion recognition networks. In CVPR. 10143--10152."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"e_1_3_2_1_22_1","volume-title":"Deep facial expression recognition: A survey","author":"Li Shan","year":"2020","unstructured":"Shan Li and Weihong Deng. 2020. Deep facial expression recognition: A survey. IEEE Transactions on Affective Computing (2020)."},{"key":"e_1_3_2_1_23_1","volume-title":"Human emotion recognition with relational region-level analysis","author":"Li Weixin","year":"2021","unstructured":"Weixin Li, Xuan Dong, and Yunhong Wang. 2021. Human emotion recognition with relational region-level analysis. IEEE Transactions on Affective Computing (2021)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCB52358.2021.9484370"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings, Part V 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part V 13. Springer, 740--755."},{"key":"e_1_3_2_1_27_1","volume-title":"Dab-detr: Dynamic anchor boxes are better queries for detr. arXiv preprint arXiv:2201.12329","author":"Liu Shilong","year":"2022","unstructured":"Shilong Liu, Feng Li, Hao Zhang, Xiao Yang, Xianbiao Qi, Hang Su, Jun Zhu, and Lei Zhang. 2022. Dab-detr: Dynamic anchor boxes are better queries for detr. arXiv preprint arXiv:2201.12329 (2022)."},{"key":"e_1_3_2_1_28_1","volume-title":"End-to-end temporal action detection with transformer. arXiv preprint arXiv:2106.10271","author":"Liu Xiaolong","year":"2021","unstructured":"Xiaolong Liu, Qimeng Wang, Yao Hu, Xu Tang, Song Bai, and Xiang Bai. 2021. End-to-end temporal action detection with transformer. arXiv preprint arXiv:2106.10271 (2021)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_38"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1177\/1754073914534480"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2021.3068387"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Trisha Mittal Pooja Guhan Uttaran Bhattacharya Rohan Chandra Aniket Bera and Dinesh Manocha. 2020. EmotiCon: Context-Aware Multimodal Emotion Recognition Using Frege's Principle. In CVPR. 14234--14243.","DOI":"10.1109\/CVPR42600.2020.01424"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00561"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3063612"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00149"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3032037"},{"key":"e_1_3_2_1_37_1","volume-title":"Survey on emotional body gesture recognition","author":"Noroozi Fatemeh","year":"2018","unstructured":"Fatemeh Noroozi, Dorota Kaminska, Ciprian Corneanu, Tomasz Sapinski, Sergio Escalera, and Gholamreza Anbarjafari. 2018. Survey on emotional body gesture recognition. IEEE transactions on affective computing (2018)."},{"key":"e_1_3_2_1_38_1","volume-title":"EMERSK-Explainable Multimodal Emotion Recognition with Situational Knowledge","author":"Palash Mijanur","year":"2023","unstructured":"Mijanur Palash and Bharat Bhargava. 2023. EMERSK-Explainable Multimodal Emotion Recognition with Situational Knowledge. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2005.856076"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10799-012-0138-5"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"e_1_3_2_1_42_1","volume-title":"Deep learning for human affect recognition: Insights and new developments","author":"Rouast Philipp V","year":"2019","unstructured":"Philipp V Rouast, Marc Adam, and Raymond Chiong. 2019. Deep learning for human affect recognition: Insights and new developments. IEEE Transactions on Affective Computing (2019)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413907"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00618"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00248"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00280-0"},{"key":"e_1_3_2_1_48_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00693"},{"key":"e_1_3_2_1_50_1","volume-title":"Rethinking the learning paradigm for facial expression recognition. arXiv preprint arXiv:2209.15402","author":"Wang Weijie","year":"2022","unstructured":"Weijie Wang, Nicu Sebe, and Bruno Lepri. 2022. Rethinking the learning paradigm for facial expression recognition. arXiv preprint arXiv:2209.15402 (2022)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"e_1_3_2_1_53_1","volume-title":"Faces in context: A review and systematization of contextual influences on affective face processing. Frontiers in psychology","author":"Wieser Matthias J","year":"2012","unstructured":"Matthias J Wieser and Tobias Brosch. 2012. Faces in context: A review and systematization of contextual influences on affective face processing. Frontiers in psychology, Vol. 3 (2012), 35406."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612342"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612014"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548183"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.12.003"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01822"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_9"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00422"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611704"},{"key":"e_1_3_2_1_62_1","volume-title":"Wide residual networks. arXiv preprint arXiv:1605.07146","author":"Zagoruyko Sergey","year":"2016","unstructured":"Sergey Zagoruyko and Nikos Komodakis. 2016. Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01965"},{"key":"e_1_3_2_1_64_1","volume-title":"Motr: End-to-end multiple-object tracking with transformer. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27","author":"Zeng Fangao","year":"2022","unstructured":"Fangao Zeng, Bin Dong, Yuang Zhang, Tiancai Wang, Xiangyu Zhang, and Yichen Wei. 2022. Motr: End-to-end multiple-object tracking with transformer. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part XXVII. Springer, 659--675."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02115"},{"key":"e_1_3_2_1_66_1","volume-title":"Semantic-aligned matching for enhanced DETR convergence and multi-scale feature fusion. arXiv preprint arXiv:2207.14172","author":"Zhang Gongjie","year":"2022","unstructured":"Gongjie Zhang, Zhipeng Luo, Yingchen Yu, Jiaxing Huang, Kaiwen Cui, Shijian Lu, and Eric P Xing. 2022. Semantic-aligned matching for enhanced DETR convergence and multi-scale feature fusion. arXiv preprint arXiv:2207.14172 (2022)."},{"key":"e_1_3_2_1_67_1","volume-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605","author":"Zhang Hao","year":"2022","unstructured":"Hao Zhang, Feng Li, Shilong Liu, Lei Zhang, Hang Su, Jun Zhu, Lionel M Ni, and Heung-Yeung Shum. 2022. Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3134167"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3158369"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00034"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01821"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2766843"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00669"},{"key":"e_1_3_2_1_74_1","first-page":"17616","article-title":"Relative uncertainty learning for facial expression recognition","volume":"34","author":"Zhang Yuhang","year":"2021","unstructured":"Yuhang Zhang, Chengrui Wang, and Weihong Deng. 2021. Relative uncertainty learning for facial expression recognition. Advances in Neural Information Processing Systems, Vol. 34 (2021), 17616--17627.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_24"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475292"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3093397"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16465"},{"key":"e_1_3_2_1_79_1","volume-title":"Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159","author":"Zhu Xizhou","year":"2020","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2020. Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680623","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:56Z","timestamp":1750295876000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680623"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":79,"alternative-id":["10.1145\/3664647.3680623","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680623","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}