{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T15:13:32Z","timestamp":1759936412902,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T00:00:00Z","timestamp":1695168000000},"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":[[2023,9,20]]},"DOI":"10.1145\/3617233.3617238","type":"proceedings-article","created":{"date-parts":[[2023,12,30]],"date-time":"2023-12-30T06:05:32Z","timestamp":1703916332000},"page":"61-70","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["TIB: A Dataset for Abstractive Summarization of Long Multimodal Videoconference Records"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6392-8519","authenticated-orcid":false,"given":"Th\u00e9o","family":"Gigant","sequence":"first","affiliation":[{"name":"Laboratoire des Signaux et Syst\u00e8mes, Universit\u00e9 Paris-Saclay, CNRS, CentraleSup\u00e9lec, France and JustAI, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6388-4112","authenticated-orcid":false,"given":"Frederic","family":"Dufaux","sequence":"additional","affiliation":[{"name":"Laboratoire des Signaux et Syst\u00e8mes, Universit\u00e9 Paris-Saclay, CNRS, CentraleSup\u00e9lec, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7249-8715","authenticated-orcid":false,"given":"Camille","family":"Guinaudeau","sequence":"additional","affiliation":[{"name":"Japanese French Laboratory for Informatics, CNRS, Japan and LISN, Universit\u00e9 Paris-Saclay, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9348-7916","authenticated-orcid":false,"given":"Marc","family":"D\u00e9combas","sequence":"additional","affiliation":[{"name":"JustAI, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,12,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3117472"},{"key":"e_1_3_2_1_2_1","volume-title":"Longformer: The Long-Document Transformer","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy, Matthew\u00a0E. Peters, and Arman Cohan. 2020. Longformer: The Long-Document Transformer. http:\/\/arxiv.org\/abs\/2004.05150 arXiv:2004.05150 [cs] version: 2."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-07969-4"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1242\/jcs.249607"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2097"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1269"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/SIU.2004.1338317"},{"key":"e_1_3_2_1_9_1","unstructured":"Dialpad. 2022. State of Video Conferencing 2022. Technical Report."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113679"},{"key":"e_1_3_2_1_11_1","volume-title":"CEUR Workshop Proceedings 1272 (Oct.","author":"Garc\u00eda Jos\u00e9","year":"2014","unstructured":"Jos\u00e9 Garc\u00eda, M. Sabatino, Pasquale Lisena, and Rapha\u00ebl Troncy. 2014. Detecting hot spots in web videos. CEUR Workshop Proceedings 1272 (Oct. 2014), 141\u2013144."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1065"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.112"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.369"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-021-03040-9"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5406"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Wojciech Kry\u015bci\u0144ski Nazneen Rajani Divyansh Agarwal Caiming Xiong and Dragomir Radev. 2022. BookSum: A Collection of Datasets for Long-form Narrative Summarization. http:\/\/arxiv.org\/abs\/2105.08209 arXiv:2105.08209 [cs].","DOI":"10.18653\/v1\/2022.findings-emnlp.488"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2848260"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.752"},{"key":"e_1_3_2_1_22_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain, 74\u201381. https:\/\/aclanthology.org\/W04-1013"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1028"},{"volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","key":"e_1_3_2_1_24_1","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems, Vol.\u00a032. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/bdbca288fee7f92f2bfa9f7012727740-Abstract.html"},{"key":"e_1_3_2_1_25_1","unstructured":"Jason Phang Yao Zhao and Peter\u00a0J. Liu. 2022. Investigating Efficiently Extending Transformers for Long Input Summarization. http:\/\/arxiv.org\/abs\/2208.04347 arXiv:2208.04347 [cs]."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","unstructured":"Alec Radford Jong\u00a0Wook Kim Tao Xu Greg Brockman Christine McLeavey and Ilya Sutskever. 2022. Robust Speech Recognition via Large-Scale Weak Supervision. https:\/\/doi.org\/10.48550\/arXiv.2212.04356 arXiv:2212.04356 [cs eess].","DOI":"10.48550\/arXiv.2212.04356"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the Workshop on Visually Grounded Interaction and Language (ViGIL). https:\/\/hal.science\/hal-02431947","author":"Sanabria Ramon","year":"2018","unstructured":"Ramon Sanabria, Ozan Caglayan, Shruti Palaskar, Desmond Elliott, Lo\u00efc Barrault, Lucia Specia, and Florian Metze. 2018. How2: A Large-scale Dataset for Multimodal Language Understanding. In Proceedings of the Workshop on Visually Grounded Interaction and Language (ViGIL). https:\/\/hal.science\/hal-02431947"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00216-022-03983-y"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1212"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0686-2"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Thomas Wolf Lysandre Debut Victor Sanh Julien Chaumond Clement Delangue Anthony Moi Pierric Cistac Tim Rault R\u00e9mi Louf Morgan Funtowicz Joe Davison Sam Shleifer Patrick von Platen Clara Ma Yacine Jernite Julien Plu Canwen Xu Teven\u00a0Le Scao Sylvain Gugger Mariama Drame Quentin Lhoest and Alexander\u00a0M. Rush. 2020. HuggingFace\u2019s Transformers: State-of-the-art Natural Language Processing. http:\/\/arxiv.org\/abs\/1910.03771 arXiv:1910.03771 [cs].","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning(ICML\u201920)","author":"Zhang Jingqing","year":"2020","unstructured":"Jingqing Zhang, Yao Zhao, Mohammad Saleh, and Peter\u00a0J. Liu. 2020. PEGASUS: pre-training with extracted gap-sentences for abstractive summarization. In Proceedings of the 37th International Conference on Machine Learning(ICML\u201920). JMLR.org, 11328\u201311339."},{"key":"e_1_3_2_1_34_1","unstructured":"Tianyi Zhang Varsha Kishore Felix Wu Kilian\u00a0Q. Weinberger and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. https:\/\/iclr.cc\/virtual_2020\/poster_SkeHuCVFDr.html"}],"event":{"name":"CBMI 2023: 20th International Conference on Content-based Multimedia Indexing","acronym":"CBMI 2023","location":"Orleans France"},"container-title":["20th International Conference on Content-based Multimedia Indexing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3617233.3617238","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3617233.3617238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T16:58:30Z","timestamp":1756486710000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3617233.3617238"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,20]]},"references-count":34,"alternative-id":["10.1145\/3617233.3617238","10.1145\/3617233"],"URL":"https:\/\/doi.org\/10.1145\/3617233.3617238","relation":{},"subject":[],"published":{"date-parts":[[2023,9,20]]},"assertion":[{"value":"2023-12-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}