{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:45:57Z","timestamp":1730231157027,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095598","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Towards Dialogue Modeling Beyond Text"],"prefix":"10.1109","author":[{"given":"Tongzi","family":"Wu","sequence":"first","affiliation":[{"name":"Talka AI,Toronto,ON,Canada"}]},{"given":"Yuhao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Talka AI,Toronto,ON,Canada"}]},{"given":"Wang","family":"Ling","sequence":"additional","affiliation":[{"name":"Talka AI,Toronto,ON,Canada"}]},{"given":"Hojin","family":"Yang","sequence":"additional","affiliation":[{"name":"Talka AI,Toronto,ON,Canada"}]},{"given":"Joana","family":"Veloso","sequence":"additional","affiliation":[{"name":"Talka AI,Toronto,ON,Canada"}]},{"given":"Lin","family":"Sun","sequence":"additional","affiliation":[{"name":"Talka AI,Toronto,ON,Canada"}]},{"given":"Ruixin","family":"Huang","sequence":"additional","affiliation":[{"name":"Talka AI,Toronto,ON,Canada"}]},{"given":"Norberto","family":"Guimaraes","sequence":"additional","affiliation":[{"name":"Talka AI,Toronto,ON,Canada"}]},{"given":"Scott","family":"Sanner","sequence":"additional","affiliation":[{"name":"University of Toronto,Toronto,ON,Canada"}]}],"member":"263","reference":[{"key":"ref13","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"International Conference on Machine Learning"},{"article-title":"Open pre-trained transformer language models","year":"2022","author":"zhang","key":"ref12"},{"year":"2019","author":"radford","key":"ref15"},{"key":"ref14","article-title":"MLPMixer: An all-MLP architecture for vision","author":"tolstikhin","year":"2021","journal-title":"NeurIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref30","first-page":"49","article-title":"Face recognition based on manifold learning and renyi entropy","volume":"2","author":"cao","year":"2010","journal-title":"Journal of Intelligent Learning Systems and Applications"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1929908.1929914"},{"key":"ref10","article-title":"A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"article-title":"A large-scale Chinese personalized and emotional dialogue dataset for conversational AI","year":"2022","author":"chen","key":"ref32"},{"article-title":"Conversational transfer learning for emotion recognition","year":"2020","author":"hazarika","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.131"},{"key":"ref17","article-title":"Momentum contrast for unsupervised visual representation learning","author":"he","year":"2019","journal-title":"CoRR"},{"key":"ref16","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"CoRR"},{"key":"ref19","article-title":"Spatiotemporal contrastive video representation learning","author":"qian","year":"2020","journal-title":"CoRR"},{"key":"ref18","article-title":"Data-efficient image recognition with contrastive predictive coding","author":"h\u00e9naff","year":"2019","journal-title":"CoRR"},{"key":"ref24","article-title":"Audio-visual embodied navigation","author":"chen","year":"2019","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01021"},{"key":"ref26","article-title":"Visual question answering","author":"antol","year":"2015","journal-title":"CoRR"},{"key":"ref25","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","author":"zeng","year":"2021","journal-title":"CoRR"},{"article-title":"AudioLM: a language modeling approach to audio generation","year":"2022","author":"borsos","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref21","article-title":"Multiscale benchmarks for multimodal representation learning","author":"liang","year":"2021","journal-title":"CoRR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01342"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"ref29","first-page":"7425","article-title":"Now you shake me: Towards automatic 4D cinema","author":"zhou","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607997"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054328"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413680"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/10904018.2013.813234"},{"key":"ref3","article-title":"Attention, intentions, and the structure of discourse","author":"grosz","year":"1986","journal-title":"Computational Linguistics"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-368"},{"key":"ref5","article-title":"Prosodic features and the management of interruptions","author":"local","year":"1986","journal-title":"Intonation in Discourse"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095598.pdf?arnumber=10095598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T18:57:16Z","timestamp":1699901836000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095598\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095598","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}