{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T18:58:26Z","timestamp":1767034706778,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T00:00:00Z","timestamp":1696809600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Korean Ministry of Trade, Industry, and Energy","award":["P0017311"],"award-info":[{"award-number":["P0017311"]}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["2020-0-00842"],"award-info":[{"award-number":["2020-0-00842"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,9]]},"DOI":"10.1145\/3577190.3614122","type":"proceedings-article","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T22:30:48Z","timestamp":1696717848000},"page":"314-325","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["HIINT: Historical, Intra- and Inter- personal Dynamics Modeling with Cross-person Memory Transformer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1902-3822","authenticated-orcid":false,"given":"Yubin","family":"Kim","sequence":"first","affiliation":[{"name":"Media Lab, Massachusetts Institute of Technology, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6336-5512","authenticated-orcid":false,"given":"Dong Won","family":"Lee","sequence":"additional","affiliation":[{"name":"Media Lab, Massachusetts Institute of Technology, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7768-3610","authenticated-orcid":false,"given":"Paul Pu","family":"Liang","sequence":"additional","affiliation":[{"name":"Machine Learning Department, Carnegie Mellon University, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9391-0163","authenticated-orcid":false,"given":"Sharifa","family":"Alghowinem","sequence":"additional","affiliation":[{"name":"Media Lab, MIT, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0587-2065","authenticated-orcid":false,"given":"Cynthia","family":"Breazeal","sequence":"additional","affiliation":[{"name":"MIT Media Lab, Massachusetts Institute of Technology, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9638-1722","authenticated-orcid":false,"given":"Hae Won","family":"Park","sequence":"additional","affiliation":[{"name":"MIT Media Lab, Massachusetts Institute of Technology, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,9]]},"reference":[{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"e_1_3_2_1_4_1","volume-title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","author":"Cao Z.","year":"2019","unstructured":"Z. Cao , G. Hidalgo Martinez , T. Simon , S. Wei , and Y.\u00a0 A. Sheikh . 2019. OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields . IEEE Transactions on Pattern Analysis and Machine Intelligence ( 2019 ). Z. Cao, G. Hidalgo Martinez, T. Simon, S. Wei, and Y.\u00a0A. Sheikh. 2019. OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields. IEEE Transactions on Pattern Analysis and Machine Intelligence (2019)."},{"key":"e_1_3_2_1_5_1","volume-title":"Action Recognition? A New Model and the Kinetics Dataset. CoRR abs\/1705.07750","author":"Carreira Jo\u00e3o","year":"2017","unstructured":"Jo\u00e3o Carreira and Andrew Zisserman . 2017. Quo Vadis , Action Recognition? A New Model and the Kinetics Dataset. CoRR abs\/1705.07750 ( 2017 ). arXiv:1705.07750http:\/\/arxiv.org\/abs\/1705.07750 Jo\u00e3o Carreira and Andrew Zisserman. 2017. Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. CoRR abs\/1705.07750 (2017). arXiv:1705.07750http:\/\/arxiv.org\/abs\/1705.07750"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475661"},{"key":"e_1_3_2_1_8_1","volume-title":"Dyadic Affect in Parent-child Multi-modal Interaction: Introducing the DAMI-P2C Dataset and its Preliminary Analysis","author":"Chen Huili","year":"2022","unstructured":"Huili Chen , Sharifa\u00a0Mohammed Alghowinem , Soo\u00a0Jung Jang , Cynthia Breazeal , and Hae\u00a0Won Park . 2022. Dyadic Affect in Parent-child Multi-modal Interaction: Introducing the DAMI-P2C Dataset and its Preliminary Analysis . IEEE Transactions on Affective Computing ( 2022 ), 1\u20131. https:\/\/doi.org\/10.1109\/TAFFC.2022.3178689 10.1109\/TAFFC.2022.3178689 Huili Chen, Sharifa\u00a0Mohammed Alghowinem, Soo\u00a0Jung Jang, Cynthia Breazeal, and Hae\u00a0Won Park. 2022. Dyadic Affect in Parent-child Multi-modal Interaction: Introducing the DAMI-P2C Dataset and its Preliminary Analysis. IEEE Transactions on Affective Computing (2022), 1\u20131. https:\/\/doi.org\/10.1109\/TAFFC.2022.3178689"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418842"},{"key":"e_1_3_2_1_10_1","volume-title":"Dyadformer: A Multi-modal Transformer for Long-Range Modeling of Dyadic Interactions. CoRR abs\/2109.09487","author":"Curto David","year":"2021","unstructured":"David Curto , Albert Clap\u00e9s , Javier Selva , Sorina Smeureanu , J\u00falio C. S.\u00a0 Jacques J\u00fanior , David Gallardo-Pujol , Georgina Guilera , David Leiva , Thomas\u00a0 B. Moeslund , Sergio Escalera , and Cristina Palmero . 2021 . Dyadformer: A Multi-modal Transformer for Long-Range Modeling of Dyadic Interactions. CoRR abs\/2109.09487 (2021). arXiv:2109.09487https:\/\/arxiv.org\/abs\/2109.09487 David Curto, Albert Clap\u00e9s, Javier Selva, Sorina Smeureanu, J\u00falio C. S.\u00a0Jacques J\u00fanior, David Gallardo-Pujol, Georgina Guilera, David Leiva, Thomas\u00a0B. Moeslund, Sergio Escalera, and Cristina Palmero. 2021. Dyadformer: A Multi-modal Transformer for Long-Range Modeling of Dyadic Interactions. CoRR abs\/2109.09487 (2021). arXiv:2109.09487https:\/\/arxiv.org\/abs\/2109.09487"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.00116"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3417973"},{"volume-title":"Applying group communication analysis to educational discourse interactions at scale","author":"Dowell Nia","key":"e_1_3_2_1_13_1","unstructured":"Nia Dowell , Oleksandra Poquet , and Christopher Brooks . 2018. Applying group communication analysis to educational discourse interactions at scale . International Society of the Learning Sciences, Inc.[ISLS]. Nia Dowell, Oleksandra Poquet, and Christopher Brooks. 2018. Applying group communication analysis to educational discourse interactions at scale. International Society of the Learning Sciences, Inc.[ISLS]."},{"key":"e_1_3_2_1_14_1","unstructured":"Jiafei Duan Samson Yu Nicholas Tan Yi\u00a0Ru Wang and Cheston Tan. 2023. Read My Mind: A Multi-Modal Dataset for Human Belief Prediction. arxiv:2304.14501\u00a0[cs.CV]  Jiafei Duan Samson Yu Nicholas Tan Yi\u00a0Ru Wang and Cheston Tan. 2023. Read My Mind: A Multi-Modal Dataset for Human Belief Prediction. arxiv:2304.14501\u00a0[cs.CV]"},{"key":"e_1_3_2_1_15_1","volume-title":"BOSS: A Benchmark for Human Belief Prediction in Object-context Scenarios. arxiv:2206.10665\u00a0[cs.CV]","author":"Duan Jiafei","year":"2022","unstructured":"Jiafei Duan , Samson Yu , Nicholas Tan , Li Yi , and Cheston Tan . 2022 . BOSS: A Benchmark for Human Belief Prediction in Object-context Scenarios. arxiv:2206.10665\u00a0[cs.CV] Jiafei Duan, Samson Yu, Nicholas Tan, Li Yi, and Cheston Tan. 2022. BOSS: A Benchmark for Human Belief Prediction in Object-context Scenarios. arxiv:2206.10665\u00a0[cs.CV]"},{"key":"e_1_3_2_1_16_1","volume-title":"Learning Triadic Belief Dynamics in Nonverbal Communication from Videos. CoRR abs\/2104.02841","author":"Fan Lifeng","year":"2021","unstructured":"Lifeng Fan , Shuwen Qiu , Zilong Zheng , Tao Gao , Song-Chun Zhu , and Yixin Zhu . 2021. Learning Triadic Belief Dynamics in Nonverbal Communication from Videos. CoRR abs\/2104.02841 ( 2021 ). arXiv:2104.02841https:\/\/arxiv.org\/abs\/2104.02841 Lifeng Fan, Shuwen Qiu, Zilong Zheng, Tao Gao, Song-Chun Zhu, and Yixin Zhu. 2021. Learning Triadic Belief Dynamics in Nonverbal Communication from Videos. CoRR abs\/2104.02841 (2021). arXiv:2104.02841https:\/\/arxiv.org\/abs\/2104.02841"},{"key":"e_1_3_2_1_17_1","volume-title":"Dialoguegcn: A graph convolutional neural network for emotion recognition in conversation. arXiv preprint arXiv:1908.11540","author":"Ghosal Deepanway","year":"2019","unstructured":"Deepanway Ghosal , Navonil Majumder , Soujanya Poria , Niyati Chhaya , and Alexander Gelbukh . 2019 . Dialoguegcn: A graph convolutional neural network for emotion recognition in conversation. arXiv preprint arXiv:1908.11540 (2019). Deepanway Ghosal, Navonil Majumder, Soujanya Poria, Niyati Chhaya, and Alexander Gelbukh. 2019. Dialoguegcn: A graph convolutional neural network for emotion recognition in conversation. arXiv preprint arXiv:1908.11540 (2019)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00037"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-psych-010418-103145"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1280"},{"key":"e_1_3_2_1_21_1","volume-title":"CNN Architectures for Large-Scale Audio Classification. CoRR abs\/1609.09430","author":"Hershey Shawn","year":"2016","unstructured":"Shawn Hershey , Sourish Chaudhuri , Daniel P.\u00a0W. Ellis , Jort\u00a0 F. Gemmeke , Aren Jansen , R.\u00a0 Channing Moore , Manoj Plakal , Devin Platt , Rif\u00a0 A. Saurous , Bryan Seybold , Malcolm Slaney , Ron\u00a0 J. Weiss , and Kevin\u00a0 W. Wilson . 2016. CNN Architectures for Large-Scale Audio Classification. CoRR abs\/1609.09430 ( 2016 ). arXiv:1609.09430http:\/\/arxiv.org\/abs\/1609.09430 Shawn Hershey, Sourish Chaudhuri, Daniel P.\u00a0W. Ellis, Jort\u00a0F. Gemmeke, Aren Jansen, R.\u00a0Channing Moore, Manoj Plakal, Devin Platt, Rif\u00a0A. Saurous, Bryan Seybold, Malcolm Slaney, Ron\u00a0J. Weiss, and Kevin\u00a0W. Wilson. 2016. CNN Architectures for Large-Scale Audio Classification. CoRR abs\/1609.09430 (2016). arXiv:1609.09430http:\/\/arxiv.org\/abs\/1609.09430"},{"key":"e_1_3_2_1_22_1","volume-title":"COGMEN: COntextualized GNN based multimodal emotion recognitioN. arXiv preprint arXiv:2205.02455","author":"Joshi Abhinav","year":"2022","unstructured":"Abhinav Joshi , Ashwani Bhat , Ayush Jain , Atin\u00a0Vikram Singh , and Ashutosh Modi . 2022 . COGMEN: COntextualized GNN based multimodal emotion recognitioN. arXiv preprint arXiv:2205.02455 (2022). Abhinav Joshi, Ashwani Bhat, Ayush Jain, Atin\u00a0Vikram Singh, and Ashutosh Modi. 2022. COGMEN: COntextualized GNN based multimodal emotion recognitioN. arXiv preprint arXiv:2205.02455 (2022)."},{"key":"e_1_3_2_1_23_1","unstructured":"Mark\u00a0L Knapp Judith\u00a0A Hall and Terrence\u00a0G Horgan. 2013. Nonverbal communication in human interaction. Cengage Learning.  Mark\u00a0L Knapp Judith\u00a0A Hall and Terrence\u00a0G Horgan. 2013. Nonverbal communication in human interaction. Cengage Learning."},{"volume-title":"Affect dynamics","author":"Koval Peter","key":"e_1_3_2_1_24_1","unstructured":"Peter Koval , Patrick\u00a0 T Burnett , and Yixia Zheng . 2021. Emotional inertia: On the conservation of emotional momentum . In Affect dynamics . Springer , 63\u201394. Peter Koval, Patrick\u00a0T Burnett, and Yixia Zheng. 2021. Emotional inertia: On the conservation of emotional momentum. In Affect dynamics. Springer, 63\u201394."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.108112"},{"key":"e_1_3_2_1_26_1","volume-title":"Emotional inertia and psychological maladjustment. Psychological science 21, 7","author":"Kuppens Peter","year":"2010","unstructured":"Peter Kuppens , Nicholas\u00a0 B Allen , and Lisa\u00a0 B Sheeber . 2010. Emotional inertia and psychological maladjustment. Psychological science 21, 7 ( 2010 ), 984\u2013991. Peter Kuppens, Nicholas\u00a0B Allen, and Lisa\u00a0B Sheeber. 2010. Emotional inertia and psychological maladjustment. Psychological science 21, 7 (2010), 984\u2013991."},{"key":"e_1_3_2_1_27_1","unstructured":"Dong\u00a0Won Lee Yubin Kim Rosalind Picard Cynthia Breazeal and Hae\u00a0Won Park. 2023. Multipar-T: Multiparty-Transformer for Capturing Contingent Behaviors in Group Conversations. arxiv:2304.12204\u00a0[cs.CV]  Dong\u00a0Won Lee Yubin Kim Rosalind Picard Cynthia Breazeal and Hae\u00a0Won Park. 2023. Multipar-T: Multiparty-Transformer for Capturing Contingent Behaviors in Group Conversations. arxiv:2304.12204\u00a0[cs.CV]"},{"key":"e_1_3_2_1_28_1","volume-title":"CoMPM: Context Modeling with Speaker\u2019s Pre-trained Memory Tracking for Emotion Recognition in Conversation. arXiv preprint arXiv:2108.11626","author":"Lee Joosung","year":"2021","unstructured":"Joosung Lee and Wooin Lee . 2021. CoMPM: Context Modeling with Speaker\u2019s Pre-trained Memory Tracking for Emotion Recognition in Conversation. arXiv preprint arXiv:2108.11626 ( 2021 ). Joosung Lee and Wooin Lee. 2021. CoMPM: Context Modeling with Speaker\u2019s Pre-trained Memory Tracking for Emotion Recognition in Conversation. arXiv preprint arXiv:2108.11626 (2021)."},{"key":"e_1_3_2_1_29_1","volume-title":"Towards An End-to-End Framework for Flow-Guided Video Inpainting. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Li Zhen","year":"2022","unstructured":"Zhen Li , Cheng-Ze Lu , Jianhua Qin , Chun-Le Guo , and Ming-Ming Cheng . 2022 . Towards An End-to-End Framework for Flow-Guided Video Inpainting. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Zhen Li, Cheng-Ze Lu, Jianhua Qin, Chun-Le Guo, and Ming-Ming Cheng. 2022. Towards An End-to-End Framework for Flow-Guided Video Inpainting. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_30_1","volume-title":"Focal Loss for Dense Object Detection. CoRR abs\/1708.02002","author":"Lin Tsung-Yi","year":"2017","unstructured":"Tsung-Yi Lin , Priya Goyal , Ross\u00a0 B. Girshick , Kaiming He , and Piotr Doll\u00e1r . 2017. Focal Loss for Dense Object Detection. CoRR abs\/1708.02002 ( 2017 ). arXiv:1708.02002http:\/\/arxiv.org\/abs\/1708.02002 Tsung-Yi Lin, Priya Goyal, Ross\u00a0B. Girshick, Kaiming He, and Piotr Doll\u00e1r. 2017. Focal Loss for Dense Object Detection. CoRR abs\/1708.02002 (2017). arXiv:1708.02002http:\/\/arxiv.org\/abs\/1708.02002"},{"key":"e_1_3_2_1_31_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter . 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 ( 2017 ). Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_32_1","volume-title":"deep learning of segment-level feature representation for speech emotion recognition in conversations. arXiv preprint arXiv:2302.02419","author":"Luo Jiachen","year":"2023","unstructured":"Jiachen Luo , Huy Phan , and Joshua Reiss . 2023. deep learning of segment-level feature representation for speech emotion recognition in conversations. arXiv preprint arXiv:2302.02419 ( 2023 ). Jiachen Luo, Huy Phan, and Joshua Reiss. 2023. deep learning of segment-level feature representation for speech emotion recognition in conversations. arXiv preprint arXiv:2302.02419 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"How emotions work: The social functions of emotional expression in negotiations. Research in organizational behavior 22","author":"Morris W","year":"2000","unstructured":"Michael\u00a0 W Morris and Dacher Keltner . 2000. How emotions work: The social functions of emotional expression in negotiations. Research in organizational behavior 22 ( 2000 ), 1\u201350. Michael\u00a0W Morris and Dacher Keltner. 2000. How emotions work: The social functions of emotional expression in negotiations. Research in organizational behavior 22 (2000), 1\u201350."},{"key":"e_1_3_2_1_34_1","volume-title":"Proc. ACM International Conference on Intelligent User Interfaces (IUI). 153\u2013164","author":"M\u00fcller Philipp","year":"2018","unstructured":"Philipp M\u00fcller , Michael\u00a0Xuelin Huang , and Andreas Bulling . 2018 . Detecting Low Rapport During Natural Interactions in Small Groups from Non-Verbal Behavior . In Proc. ACM International Conference on Intelligent User Interfaces (IUI). 153\u2013164 . https:\/\/doi.org\/10.1145\/3172944.3172969 10.1145\/3172944.3172969 Philipp M\u00fcller, Michael\u00a0Xuelin Huang, and Andreas Bulling. 2018. Detecting Low Rapport During Natural Interactions in Small Groups from Non-Verbal Behavior. In Proc. ACM International Conference on Intelligent User Interfaces (IUI). 153\u2013164. https:\/\/doi.org\/10.1145\/3172944.3172969"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3204493.3204549"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479219"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC\u201916)","author":"Navarretta Costanza","year":"2016","unstructured":"Costanza Navarretta . 2016 . Mirroring Facial Expressions and Emotions in Dyadic Conversations . In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC\u201916) . European Language Resources Association (ELRA), Portoro\u017e, Slovenia, 469\u2013474. https:\/\/aclanthology.org\/L16-1075 Costanza Navarretta. 2016. Mirroring Facial Expressions and Emotions in Dyadic Conversations. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC\u201916). European Language Resources Association (ELRA), Portoro\u017e, Slovenia, 469\u2013474. https:\/\/aclanthology.org\/L16-1075"},{"key":"e_1_3_2_1_38_1","unstructured":"Evonne Ng Hanbyul Joo Liwen Hu Hao Li Trevor Darrell Angjoo Kanazawa and Shiry Ginosar. 2022. Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion. arxiv:2204.08451\u00a0[cs.CV]  Evonne Ng Hanbyul Joo Liwen Hu Hao Li Trevor Darrell Angjoo Kanazawa and Shiry Ginosar. 2022. Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion. arxiv:2204.08451\u00a0[cs.CV]"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1140.001.0001"},{"key":"e_1_3_2_1_40_1","volume-title":"Deep Learning for Human Affect Recognition: Insights and New Developments. CoRR abs\/1901.02884","author":"Rouast V.","year":"2019","unstructured":"Philipp\u00a0 V. Rouast , Marc T.\u00a0P. Adam , and Raymond Chiong . 2019. Deep Learning for Human Affect Recognition: Insights and New Developments. CoRR abs\/1901.02884 ( 2019 ). arXiv:1901.02884http:\/\/arxiv.org\/abs\/1901.02884 Philipp\u00a0V. Rouast, Marc T.\u00a0P. Adam, and Raymond Chiong. 2019. Deep Learning for Human Affect Recognition: Insights and New Developments. CoRR abs\/1901.02884 (2019). arXiv:1901.02884http:\/\/arxiv.org\/abs\/1901.02884"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413909"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17625"},{"key":"e_1_3_2_1_43_1","volume-title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition. CoRR abs\/1711.11248","author":"Tran Du","year":"2017","unstructured":"Du Tran , Heng Wang , Lorenzo Torresani , Jamie Ray , Yann LeCun , and Manohar Paluri . 2017. A Closer Look at Spatiotemporal Convolutions for Action Recognition. CoRR abs\/1711.11248 ( 2017 ). arXiv:1711.11248http:\/\/arxiv.org\/abs\/1711.11248 Du Tran, Heng Wang, Lorenzo Torresani, Jamie Ray, Yann LeCun, and Manohar Paluri. 2017. A Closer Look at Spatiotemporal Convolutions for Action Recognition. CoRR abs\/1711.11248 (2017). arXiv:1711.11248http:\/\/arxiv.org\/abs\/1711.11248"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"e_1_3_2_1_45_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan\u00a0 N Gomez , \u0141ukasz Kaiser , and Illia Polosukhin . 2017. Attention is all you need. Advances in neural information processing systems 30 ( 2017 ). Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_46_1","first-page":"308","article-title":"Memformer: A Memory-Augmented Transformer for Sequence Modeling","volume":"2022","author":"Wu Qingyang","year":"2022","unstructured":"Qingyang Wu , Zhenzhong Lan , Kun Qian , Jing Gu , Alborz Geramifard , and Zhou Yu . 2022 . Memformer: A Memory-Augmented Transformer for Sequence Modeling . In Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022. 308 \u2013 318 . Qingyang Wu, Zhenzhong Lan, Kun Qian, Jing Gu, Alborz Geramifard, and Zhou Yu. 2022. Memformer: A Memory-Augmented Transformer for Sequence Modeling. In Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022. 308\u2013318.","journal-title":"Findings of the Association for Computational Linguistics: AACL-IJCNLP"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301371"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Dong Zhang Liangqing Wu Changlong Sun Shoushan Li Qiaoming Zhu and Guodong Zhou. 2019. Modeling both Context-and Speaker-Sensitive Dependence for Emotion Detection in Multi-speaker Conversations.. In IJCAI. 5415\u20135421.  Dong Zhang Liangqing Wu Changlong Sun Shoushan Li Qiaoming Zhu and Guodong Zhou. 2019. Modeling both Context-and Speaker-Sensitive Dependence for Emotion Detection in Multi-speaker Conversations.. In IJCAI. 5415\u20135421.","DOI":"10.24963\/ijcai.2019\/752"}],"event":{"name":"ICMI '23: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"],"location":"Paris France","acronym":"ICMI '23"},"container-title":["INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577190.3614122","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3577190.3614122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:01Z","timestamp":1750178221000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577190.3614122"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,9]]},"references-count":47,"alternative-id":["10.1145\/3577190.3614122","10.1145\/3577190"],"URL":"https:\/\/doi.org\/10.1145\/3577190.3614122","relation":{},"subject":[],"published":{"date-parts":[[2023,10,9]]},"assertion":[{"value":"2023-10-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}