{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T02:17:53Z","timestamp":1771294673928,"version":"3.50.1"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031783883","type":"print"},{"value":"9783031783890","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78389-0_16","type":"book-chapter","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T14:14:19Z","timestamp":1733321659000},"page":"233-248","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Latent Behavior Diffusion for Sequential Reaction Generation in Dyadic Setting"],"prefix":"10.1007","author":[{"given":"Minh-Duc","family":"Nguyen","sequence":"first","affiliation":[]},{"given":"Hyung-Jeong","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Soo-Hyung","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Ji-Eun","family":"Shin","sequence":"additional","affiliation":[]},{"given":"Seung-Won","family":"Kim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"16_CR1","unstructured":"Albert Mehrabian and James\u00a0A Russell. An approach to environmental psychology. the MIT Press, 1974"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Xuesong Zhai, Minjuan Wang, and Usman Ghani. The sor (stimulus-organism-response) paradigm in online learning: an empirical study of students\u2019 knowledge hiding perceptions. In Cross Reality (XR) and Immersive Learning Environments (ILEs) in Education, pages 48\u201363. Routledge, 2023","DOI":"10.4324\/9781003457121-5"},{"key":"16_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2019.102674","volume":"65","author":"S Peng","year":"2019","unstructured":"Peng, S., Dong, Y., Wang, W., Jieyi, H., Dong, W.: The affective facial recognition task: The influence of cognitive styles and exposure times. J. Vis. Commun. Image Represent. 65, 102674 (2019)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"16_CR4","unstructured":"German Barquero, Johnny N\u00fanez, Zhen Xu, Sergio Escalera, Wei-Wei Tu, Isabelle Guyon, and Cristina Palmero. Comparison of spatio-temporal models for human motion and pose forecasting in face-to-face interaction scenarios supplementary material. 2022"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Yuchi Huang and Saad\u00a0M Khan. Dyadgan: Generating facial expressions in dyadic interactions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 11\u201318, 2017","DOI":"10.1109\/CVPRW.2017.280"},{"key":"16_CR6","unstructured":"Cristina Palmero, German Barquero, Julio CS\u00a0Jacques Junior, Albert Clap\u00e9s, Johnny N\u00fanez, David Curto, Sorina Smeureanu, Javier Selva, Zejian Zhang, David Saeteros, et\u00a0al. Chalearn lap challenges on self-reported personality recognition and non-verbal behavior forecasting during social dyadic interactions: Dataset, design, and results. In Understanding Social Behavior in Dyadic and Small Group Interactions, pages 4\u201352. PMLR, 2022"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Zilong Shao, Siyang Song, Shashank Jaiswal, Linlin Shen, Michel Valstar, and Hatice Gunes. Personality recognition by modelling person-specific cognitive processes using graph representation. In proceedings of the 29th ACM international conference on multimedia, pages 357\u2013366, 2021","DOI":"10.1145\/3474085.3475460"},{"issue":"4","key":"16_CR8","doi-asserted-by":"publisher","first-page":"3048","DOI":"10.1109\/TAFFC.2022.3230672","volume":"14","author":"S Song","year":"2022","unstructured":"Song, S., Shao, Z., Jaiswal, S., Shen, L., Valstar, M., Gunes, H.: Learning person-specific cognition from facial reactions for automatic personality recognition. IEEE Trans. Affect. Comput. 14(4), 3048\u20133065 (2022)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Mohan Zhou, Yalong Bai, Wei Zhang, Ting Yao, Tiejun Zhao, and Tao Mei. Responsive listening head generation: a benchmark dataset and baseline. In European Conference on Computer Vision, pages 124\u2013142. Springer, 2022","DOI":"10.1007\/978-3-031-19839-7_8"},{"key":"16_CR10","unstructured":"Evonne Ng, Hanbyul Joo, Liwen Hu, Hao Li, Trevor Darrell, Angjoo Kanazawa, and Shiry Ginosar. Learning to listen: Modeling non-deterministic dyadic facial motion. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pages 20395\u201320405, 2022"},{"key":"16_CR11","unstructured":"Siyang Song, Micol Spitale, Yiming Luo, Batuhan Bal, and Hatice Gunes. Multiple appropriate facial reaction generation in dyadic interaction settings: What, why and how? arXiv preprint\u00a0arXiv:2302.06514, 2023"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj\u00f6rn Ommer. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pages 10684\u201310695, 2022","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Siyang Song, Micol Spitale, Cheng Luo, Cristina Palmero, German Barquero, Hengde Zhu, Sergio Escalera, Michel Valstar, Tobias Baur, Fabien Ringeval, et\u00a0al. React 2024: the second multiple appropriate facial reaction generation challenge. arXiv preprint\u00a0arXiv:2401.05166, 2024","DOI":"10.1109\/FG59268.2024.10581935"},{"issue":"5","key":"16_CR14","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1002\/cav.267","volume":"19","author":"M Gillies","year":"2008","unstructured":"Gillies, M., Pan, X., Slater, M., Shawe-Taylor, J.: Responsive listening behavior. Computer animation and virtual worlds 19(5), 579\u2013589 (2008)","journal-title":"Computer animation and virtual worlds"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Chaitanya Ahuja, Shugao Ma, Louis-Philippe Morency, and Yaser Sheikh. To react or not to react: End-to-end visual pose forecasting for personalized avatar during dyadic conversations. In 2019 International conference on multimodal interaction, pages 74\u201384, 2019","DOI":"10.1145\/3340555.3353725"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"David Greenwood, Stephen Laycock, and Iain Matthews. Predicting head pose in dyadic conversation. In Intelligent Virtual Agents: 17th International Conference, IVA 2017, Stockholm, Sweden, August 27-30, 2017, Proceedings 17, pages 160\u2013169. Springer, 2017","DOI":"10.1007\/978-3-319-67401-8_18"},{"key":"16_CR17","unstructured":"Scott Geng, Revant Teotia, Purva Tendulkar, Sachit Menon, and Carl Vondrick. Affective faces for goal-driven dyadic communication. arXiv preprint\u00a0arXiv:2301.10939, 2023"},{"issue":"11","key":"16_CR18","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Bing, X., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"16_CR19","unstructured":"Nguyen Tan\u00a0Viet Tuyen and Oya Celiktutan. Context-aware human behaviour forecasting in dyadic interactions. In Understanding Social Behavior in Dyadic and Small Group Interactions, pages 88\u2013106. PMLR, 2022"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Alex Graves and Alex Graves. Long short-term memory. Supervised sequence labelling with recurrent neural networks, pages 37\u201345, 2012","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"16_CR21","first-page":"157","volume":"2","author":"V Blanz","year":"2023","unstructured":"Blanz, V., Vetter, T.: A morphable model for the synthesis of 3d faces. In Seminal Graphics Papers: Pushing the Boundaries 2, 157\u2013164 (2023)","journal-title":"In Seminal Graphics Papers: Pushing the Boundaries"},{"key":"16_CR22","unstructured":"Aaron Van Den\u00a0Oord, Oriol Vinyals, et\u00a0al. Neural discrete representation learning. Advances in neural information processing systems, 30, 2017"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Luchuan Song, Guojun Yin, Zhenchao Jin, Xiaoyi Dong, and Chenliang Xu. Emotional listener portrait: Neural listener head generation with emotion. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pages 20839\u201320849, 2023","DOI":"10.1109\/ICCV51070.2023.01905"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Siyang Song, Micol Spitale, Cheng Luo, German Barquero, Cristina Palmero, Sergio Escalera, Michel Valstar, Tobias Baur, Fabien Ringeval, Elisabeth Andre, et\u00a0al. React2023: the first multi-modal multiple appropriate facial reaction generation challenge. arXiv preprint\u00a0arXiv:2306.06583, 2023","DOI":"10.1145\/3581783.3612832"},{"key":"16_CR25","unstructured":"Quang\u00a0Tien Dam, Tri Tung\u00a0Nguyen Nguyen, Dinh\u00a0Tuan Tran, and Joo-Ho Lee. Finite scalar quantization as facial tokenizer for dyadic reaction generation"},{"key":"16_CR26","unstructured":"Zhenjie Liu, Cong Liang, Jiahe Wang, Haofan Zhang, Yadong Liu, Caichao Zhang, Jialin Gui, and Shangfei Wang. One-to-many appropriate reaction mapping modeling with discrete latent variable"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Dang-Khanh Nguyen, Prabesh Paudel, Seung-Won Kim, Ji-Eun Shin, Soo-Hyung Kim, and Hyung-Jeong Yang. Multiple facial reaction generation using gaussian mixture of models and multimodal bottleneck transformer. In 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG), pages 1\u20135. IEEE, 2024","DOI":"10.1109\/FG59268.2024.10581901"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Minh-Duc Nguyen, Hyung-Jeong Yang, Ngoc-Huynh Ho, Soo-Hyung Kim, Seungwon Kim, and Ji-Eun Shin. Vector quantized diffusion models for multiple appropriate reactions generation. In 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG), pages 1\u20135. IEEE, 2024","DOI":"10.1109\/FG59268.2024.10581978"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Konpat Preechakul, Nattanat Chatthee, Suttisak Wizadwongsa, and Supasorn Suwajanakorn. Diffusion autoencoders: Toward a meaningful and decodable representation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pages 10619\u201310629, 2022","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"16_CR30","unstructured":"Luping Liu, Yi\u00a0Ren, Zhijie Lin, and Zhou Zhao. Pseudo numerical methods for diffusion models on manifolds. arXiv preprint\u00a0arXiv:2202.09778, 2022"},{"key":"16_CR31","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Angelo Cafaro, Johannes Wagner, Tobias Baur, Soumia Dermouche, Mercedes Torres\u00a0Torres, Catherine Pelachaud, Elisabeth Andr\u00e9, and Michel Valstar. The noxi database: multimodal recordings of mediated novice-expert interactions. In Proceedings of the 19th ACM International Conference on Multimodal Interaction, pages 350\u2013359, 2017","DOI":"10.1145\/3136755.3136780"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Fabien Ringeval, Andreas Sonderegger, Juergen Sauer, and Denis Lalanne. Introducing the recola multimodal corpus of remote collaborative and affective interactions. In 2013 10th IEEE international conference and workshops on automatic face and gesture recognition (FG), pages 1\u20138. IEEE, 2013","DOI":"10.1109\/FG.2013.6553805"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Cheng Luo, Siyang Song, Weicheng Xie, Linlin Shen, and Hatice Gunes. Learning multi-dimensional edge feature-based au relation graph for facial action unit recognition. arXiv preprint\u00a0arXiv:2205.01782, 2022","DOI":"10.24963\/ijcai.2022\/173"},{"key":"16_CR35","unstructured":"Siyang Song, Yuxin Song, Cheng Luo, Zhiyuan Song, Selim Kuzucu, Xi\u00a0Jia, Zhijiang Guo, Weicheng Xie, Linlin Shen, and Hatice Gunes. Gratis: Deep learning graph representation with task-specific topology and multi-dimensional edge features. arXiv preprint\u00a0arXiv:2211.12482, 2022"},{"issue":"1","key":"16_CR36","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1038\/s42256-020-00280-0","volume":"3","author":"A Toisoul","year":"2021","unstructured":"Toisoul, A., Kossaifi, J., Bulat, A., Tzimiropoulos, G., Pantic, M.: Estimation of continuous valence and arousal levels from faces in naturalistic conditions. Nature Machine Intelligence 3(1), 42\u201350 (2021)","journal-title":"Nature Machine Intelligence"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Nikos Athanasiou, Mathis Petrovich, Michael\u00a0J Black, and G\u00fcl Varol. Teach: Temporal action composition for 3d humans. In 2022 International Conference on 3D Vision (3DV), pages 414\u2013423. IEEE, 2022","DOI":"10.1109\/3DV57658.2022.00053"},{"key":"16_CR38","doi-asserted-by":"crossref","unstructured":"German Barquero, Sergio Escalera, and Cristina Palmero. Belfusion: Latent diffusion for behavior-driven human motion prediction. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023","DOI":"10.1109\/ICCV51070.2023.00220"},{"key":"16_CR39","unstructured":"Fabian Mentzer, David Minnen, Eirikur Agustsson, and Michael Tschannen. Finite scalar quantization: Vq-vae made simple. arXiv preprint\u00a0arXiv:2309.15505, 2023"},{"key":"16_CR40","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et\u00a0al. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 2019"},{"key":"16_CR41","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017"},{"key":"16_CR42","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, 30, 2017"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Yurui Ren, Ge\u00a0Li, Yuanqi Chen, Thomas\u00a0H Li, and Shan Liu. Pirenderer: Controllable portrait image generation via semantic neural rendering. In Proceedings of the IEEE\/CVF international conference on computer vision, pages 13759\u201313768, 2021","DOI":"10.1109\/ICCV48922.2021.01350"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78389-0_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T15:07:40Z","timestamp":1733324860000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78389-0_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"ISBN":["9783031783883","9783031783890"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78389-0_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"5 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}