{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:55:22Z","timestamp":1765310122723,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755234","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:38Z","timestamp":1761377198000},"page":"7978-7987","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Bridging Domains in Mental Stress Assessment via Retrieval-Augmented Reasoning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1219-2436","authenticated-orcid":false,"given":"Yi","family":"Dai","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2992-6758","authenticated-orcid":false,"given":"Yang","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8104-9652","authenticated-orcid":false,"given":"Kaisheng","family":"Zeng","sequence":"additional","affiliation":[{"name":"Information Support Force Engineering University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"unstructured":"Anthropic. 2024. Claude 3.5 Sonnet. https:\/\/www.anthropic.com\/news\/claude-3-5-sonnet.","key":"e_1_3_2_1_2_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_3_1","DOI":"10.1109\/ACCESS.2021.3097038"},{"key":"e_1_3_2_1_4_1","volume-title":"Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023a. Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)."},{"unstructured":"Jinze Bai Shuai Bai Shusheng Yang Shijie Wang Sinan Tan Peng Wang Junyang Lin Chang Zhou and Jingren Zhou. 2023b. Qwen-VL: A Versatile Vision-Language Model for Understanding Localization Text Reading and Beyond. arXiv:2308.12966 [cs.CV] https:\/\/arxiv.org\/abs\/2308.12966","key":"e_1_3_2_1_5_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_6_1","DOI":"10.1145\/3432210"},{"key":"e_1_3_2_1_7_1","first-page":"1493","article-title":"Marlin: Masked autoencoder for facial video representation learning","author":"Zhixi Cai","year":"2023","unstructured":"Zhixi Cai et al., 2023. Marlin: Masked autoencoder for facial video representation learning. In CVPR. 1493-1504.","journal-title":"CVPR."},{"key":"e_1_3_2_1_8_1","first-page":"2229","article-title":"Domain generalization by solving jigsaw puzzles","author":"Carlucci Fabio M","year":"2019","unstructured":"Fabio M Carlucci, Antonio D'Innocente, Silvia Bucci, Barbara Caputo, and Tatiana Tommasi. 2019. Domain generalization by solving jigsaw puzzles. In CVPR. 2229-2238.","journal-title":"CVPR."},{"key":"e_1_3_2_1_9_1","volume-title":"Vision-language models can self-improve reasoning via reflection. arXiv preprint arXiv:2411.00855","author":"Cheng Kanzhi","year":"2024","unstructured":"Kanzhi Cheng, Yantao Li, Fangzhi Xu, Jianbing Zhang, Hao Zhou, and Yang Liu. 2024. Vision-language models can self-improve reasoning via reflection. arXiv preprint arXiv:2411.00855 (2024)."},{"key":"e_1_3_2_1_10_1","volume-title":"Observer-based measurement of facial expression with the Facial Action Coding System. The handbook of emotion elicitation and assessment","author":"Cohn Jeffrey F","year":"2007","unstructured":"Jeffrey F Cohn, Zara Ambadar, and Paul Ekman. 2007. Observer-based measurement of facial expression with the Facial Action Coding System. The handbook of emotion elicitation and assessment, Vol. 1, 3 (2007), 203-221."},{"key":"e_1_3_2_1_11_1","volume-title":"Cues to deception. Psychological bulletin","author":"DePaulo Bella M","year":"2003","unstructured":"Bella M DePaulo, James J Lindsay, Brian E Malone, Laura Muhlenbruck, Kelly Charlton, and Harris Cooper. 2003. Cues to deception. Psychological bulletin, Vol. 129, 1 (2003), 74."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_12_1","DOI":"10.1145\/3664647.3680584"},{"volume-title":"What the face reveals: Basic and applied studies of spontaneous expression using the Facial Action Coding System (FACS)","author":"Ekman Paul","unstructured":"Paul Ekman and Erika L Rosenberg. 1997. What the face reveals: Basic and applied studies of spontaneous expression using the Facial Action Coding System (FACS). Oxford University Press, USA.","key":"e_1_3_2_1_13_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_14_1","DOI":"10.18653\/v1\/D19-1222"},{"unstructured":"Chelsea Finn P. Abbeel and S. Levine. 2017. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. In ICML.","key":"e_1_3_2_1_15_1"},{"key":"e_1_3_2_1_16_1","first-page":"5961","article-title":"Detecting emotional stress from facial expressions for driving safety. In 2014 IEEE Int'l Conf. on Image Processing (ICIP)","author":"Gao Hua","year":"2014","unstructured":"Hua Gao, Anil Y\u00fcce, and Jean-Philippe Thiran. 2014. Detecting emotional stress from facial expressions for driving safety. In 2014 IEEE Int'l Conf. on Image Processing (ICIP). IEEE, 5961-5965.","journal-title":"IEEE"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_17_1","DOI":"10.1109\/FG47880.2020.00129"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1016\/j.procs.2019.05.022"},{"key":"e_1_3_2_1_19_1","first-page":"325","article-title":"Domain generalization based on transfer component analysis","author":"Grubinger Thomas","year":"2015","unstructured":"Thomas Grubinger, Adriana Birlutiu, Holger Sch\u00f6ner, Thomas Natschl\u00e4ger, and Tom Heskes. 2015. Domain generalization based on transfer component analysis. In ICANN. 325-334.","journal-title":"ICANN."},{"unstructured":"Ishaan Gulrajani and David Lopez-Paz. 2020. In search of lost domain generalization. arXiv preprint arXiv:2007.01434 (2020).","key":"e_1_3_2_1_20_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_21_1","DOI":"10.1109\/CVPR52688.2022.00521"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_22_1","DOI":"10.1007\/978-3-030-58536-5_8"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_23_1","DOI":"10.3390\/s21227498"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_24_1","DOI":"10.1108\/IJMPB-02-2017-0020"},{"key":"e_1_3_2_1_25_1","volume-title":"An academic stress scale: Identification and rated importance of academic stressors. Psychological reports","author":"Kohn James P","year":"1986","unstructured":"James P Kohn and Gregory H Frazer. 1986. An academic stress scale: Identification and rated importance of academic stressors. Psychological reports, Vol. 59, 2 (1986), 415-426."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_26_1","DOI":"10.1561\/9781638283379"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_27_1","DOI":"10.1109\/CVPR52688.2022.01868"},{"key":"e_1_3_2_1_28_1","first-page":"56012","article-title":"Diversifying spatial-temporal perception for video domain generalization","volume":"36","author":"Lin Kun-Yu","year":"2023","unstructured":"Kun-Yu Lin, Jia-Run Du, Yipeng Gao, Jiaming Zhou, and Wei-Shi Zheng. 2023. Diversifying spatial-temporal perception for video domain generalization. Advances in Neural Information Processing Systems, Vol. 36 (2023), 56012-56026.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","first-page":"1353","article-title":"Best sources forward: domain generalization through source-specific nets","author":"Mancini Massimiliano","year":"2018","unstructured":"Massimiliano Mancini, Samuel Rota Bul\u00f2, Barbara Caputo, and Elisa Ricci. 2018. Best sources forward: domain generalization through source-specific nets. In ICIP. 1353-1357.","journal-title":"ICIP."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_30_1","DOI":"10.1109\/CVPRW.2016.182"},{"key":"e_1_3_2_1_31_1","volume-title":"Neurobiological and systemic effects of chronic stress. Chronic stress","author":"McEwen Bruce S","year":"2017","unstructured":"Bruce S McEwen. 2017. Neurobiological and systemic effects of chronic stress. Chronic stress, Vol. 1 (2017), 2470547017692328."},{"key":"e_1_3_2_1_32_1","volume-title":"Clinical depression and regulation of the inflammatory response during acute stress. Psychosomatic medicine","author":"Miller Gregory E","year":"2005","unstructured":"Gregory E Miller, Nicolas Rohleder, Cinnamon Stetler, and Clemens Kirschbaum. 2005. Clinical depression and regulation of the inflammatory response during acute stress. Psychosomatic medicine, Vol. 67, 5 (2005), 679-687."},{"key":"e_1_3_2_1_33_1","first-page":"4193","article-title":"Multi-view domain generalization for visual recognition","author":"Niu Li","year":"2015","unstructured":"Li Niu, Wen Li, and Dong Xu. 2015. Multi-view domain generalization for visual recognition. In ICCV. 4193-4201.","journal-title":"ICCV."},{"unstructured":"Openai. 2024. https:\/\/openai.com\/index\/hello-gpt-4o\/.","key":"e_1_3_2_1_34_1"},{"key":"e_1_3_2_1_35_1","first-page":"7249","article-title":"Structured domain randomization: Bridging the reality gap by context-aware synthetic data","author":"Prakash Aayush","year":"2019","unstructured":"Aayush Prakash, Shaad Boochoon, Mark Brophy, David Acuna, Eric Cameracci, Gavriel State, Omer Shapira, and Stan Birchfield. 2019. Structured domain randomization: Bridging the reality gap by context-aware synthetic data. In ICRA. IEEE, 7249-7255.","journal-title":"ICRA. IEEE"},{"key":"e_1_3_2_1_36_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Rafailov Rafael","year":"2024","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2024. Direct preference optimization: Your language model is secretly a reward model. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"Distributionally robust optimization: A review. arXiv preprint arXiv:1908.05659","author":"Rahimian Hamed","year":"2019","unstructured":"Hamed Rahimian and Sanjay Mehrotra. 2019. Distributionally robust optimization: A review. arXiv preprint arXiv:1908.05659 (2019)."},{"key":"e_1_3_2_1_38_1","first-page":"579","article-title":"Multi-component image translation for deep domain generalization","author":"Rahman Mohammad Mahfujur","year":"2019","unstructured":"Mohammad Mahfujur Rahman, Clinton Fookes, Mahsa Baktashmotlagh, and Sridha Sridharan. 2019. Multi-component image translation for deep domain generalization. In WACV. IEEE, 579-588.","journal-title":"WACV. IEEE"},{"key":"e_1_3_2_1_39_1","volume-title":"Batch Normalization Embeddings for Deep Domain Generalization. arXiv preprint arXiv:2011.12672","author":"Seg\u00f9 Mattia","year":"2020","unstructured":"Mattia Seg\u00f9, Alessio Tonioni, and Federico Tombari. 2020. Batch Normalization Embeddings for Deep Domain Generalization. arXiv preprint arXiv:2011.12672 (2020)."},{"unstructured":"Shiv Shankar Vihari Piratla Soumen Chakrabarti Siddhartha Chaudhuri Preethi Jyothi and Sunita Sarawagi. 2018. Generalizing across domains via cross-gradient training. In ICLR.","key":"e_1_3_2_1_40_1"},{"key":"e_1_3_2_1_41_1","volume-title":"Microprocessors and Microsystems","volume":"95","author":"Astha","year":"2022","unstructured":"Astha Singh et al., 2022. Detection of stress, anxiety and depression (SAD) in video surveillance using ResNet-101. Microprocessors and Microsystems, Vol. 95 (2022)."},{"unstructured":"Jake Snell Kevin Swersky and Richard S Zemel. 2017. Prototypical networks for few-shot learning. In NeurIPS.","key":"e_1_3_2_1_42_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_43_1","DOI":"10.1145\/3544793.3563406"},{"key":"e_1_3_2_1_44_1","volume-title":"Ving Ian Lei, et al","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Petko Georgiev, Ving Ian Lei, et al., 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv:2403.05530 [cs.CL] https:\/\/arxiv.org\/abs\/2403.05530"},{"key":"e_1_3_2_1_45_1","first-page":"23","article-title":"Domain randomization for transferring deep neural networks from simulation to the real world","author":"Tobin Josh","year":"2017","unstructured":"Josh Tobin, Rachel Fong, Alex Ray, Jonas Schneider, Wojciech Zaremba, and Pieter Abbeel. 2017. Domain randomization for transferring deep neural networks from simulation to the real world. In IROS. 23-30.","journal-title":"IROS."},{"key":"e_1_3_2_1_46_1","first-page":"1","article-title":"Towards independent stress detection: A dependent model using facial action units. In 2018 Int'l Conf. on content-based multimedia indexing (CBMI)","author":"Viegas Carla","year":"2018","unstructured":"Carla Viegas, Shing-Hon Lau, Roy Maxion, and Alexander Hauptmann. 2018. Towards independent stress detection: A dependent model using facial action units. In 2018 Int'l Conf. on content-based multimedia indexing (CBMI). IEEE, 1-6.","journal-title":"IEEE"},{"key":"e_1_3_2_1_47_1","volume-title":"Generalizing to unseen domains: A survey on domain generalization","author":"Wang Jindong","year":"2022","unstructured":"Jindong Wang, Cuiling Lan, Chang Liu, Yidong Ouyang, Tao Qin, Wang Lu, Yiqiang Chen, Wenjun Zeng, and Philip S Yu. 2022. Generalizing to unseen domains: A survey on domain generalization. IEEE transactions on knowledge and data engineering, Vol. 35, 8 (2022), 8052-8072."},{"key":"e_1_3_2_1_48_1","volume-title":"Perspectives on Labour and Income","volume":"15","author":"Williams Cara","year":"2003","unstructured":"Cara Williams. 2003. Sources of workplace stress. Perspectives on Labour and Income, Vol. 15, 3 (2003)."},{"key":"e_1_3_2_1_49_1","volume-title":"An early evaluation of gpt-4v (ision). arXiv preprint arXiv:2310.16534","author":"Wu Yang","year":"2023","unstructured":"Yang Wu, Shilong Wang, Hao Yang, Tian Zheng, Hongbo Zhang, Yanyan Zhao, and Bing Qin. 2023. An early evaluation of gpt-4v (ision). arXiv preprint arXiv:2310.16534 (2023)."},{"key":"e_1_3_2_1_50_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Xue Hongwei","year":"2022","unstructured":"Hongwei Xue, Yuchong Sun, Bei Liu, Jianlong Fu, Ruihua Song, Houqiang Li, and Jiebo Luo. 2022. Clip-vip: Adapting pre-trained image-text model to video-language alignment. In The Eleventh International Conference on Learning Representations."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_51_1","DOI":"10.1371\/journal.pone.0086041"},{"key":"e_1_3_2_1_52_1","volume-title":"The dawn of lmms: Preliminary explorations with gpt-4v (ision). arXiv preprint arXiv:2309.17421","author":"Yang Zhengyuan","year":"2023","unstructured":"Zhengyuan Yang, Linjie Li, Kevin Lin, Jianfeng Wang, Chung-Ching Lin, Zicheng Liu, and Lijuan Wang. 2023. The dawn of lmms: Preliminary explorations with gpt-4v (ision). arXiv preprint arXiv:2309.17421, Vol. 9, 1 (2023), 1."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_53_1","DOI":"10.1145\/3581783.3612153"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_54_1","DOI":"10.3390\/s20195552"},{"key":"e_1_3_2_1_55_1","first-page":"430","article-title":"Detecting negative emotional stress based on facial expression in real time. In 2019 IEEE 4th Int'l Conf. on signal and image processing (ICSIP)","author":"Zhang Jin","year":"2019","unstructured":"Jin Zhang, Xue Mei, Huan Liu, Shenqiang Yuan, and Tiancheng Qian. 2019. Detecting negative emotional stress based on facial expression in real time. In 2019 IEEE 4th Int'l Conf. on signal and image processing (ICSIP). IEEE, 430-434.","journal-title":"IEEE"},{"key":"e_1_3_2_1_56_1","volume-title":"Multimodal chain-of-thought reasoning in language models. arXiv preprint arXiv:2302.00923","author":"Zhang Zhuosheng","year":"2023","unstructured":"Zhuosheng Zhang, Aston Zhang, Mu Li, Hai Zhao, George Karypis, and Alex Smola. 2023. Multimodal chain-of-thought reasoning in language models. arXiv preprint arXiv:2302.00923 (2023)."},{"key":"e_1_3_2_1_57_1","volume-title":"Multi-source domain adaptation in the deep learning era: A systematic survey. arXiv preprint arXiv:2002.12169","author":"Zhao Sicheng","year":"2020","unstructured":"Sicheng Zhao, Bo Li, Pengfei Xu, and Kurt Keutzer. 2020. Multi-source domain adaptation in the deep learning era: A systematic survey. arXiv preprint arXiv:2002.12169 (2020)."},{"doi-asserted-by":"crossref","unstructured":"Kaiyang Zhou Yongxin Yang Timothy M. Hospedales and Tao Xiang. 2020. Learning to Generate Novel Domains for Domain Generalization. In ECCV.","key":"e_1_3_2_1_58_1","DOI":"10.1007\/978-3-030-58517-4_33"}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MM '25","name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:50:28Z","timestamp":1765309828000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755234"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":58,"alternative-id":["10.1145\/3746027.3755234","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755234","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}