{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:14Z","timestamp":1750309454491,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T00:00:00Z","timestamp":1730678400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"JSPS KAKENHI","award":["22H04860, 22K21304, 22H00536, 23H03506"],"award-info":[{"award-number":["22H04860, 22K21304, 22H00536, 23H03506"]}]},{"name":"JST AIP Trilateral AI Research","award":["JPMJCR20G6"],"award-info":[{"award-number":["JPMJCR20G6"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,4]]},"DOI":"10.1145\/3678957.3685718","type":"proceedings-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T04:35:53Z","timestamp":1730262953000},"page":"565-574","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Do We Need To Watch It All? Efficient Job Interview Video Processing with Differentiable Masking"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7014-311X","authenticated-orcid":false,"given":"Hung","family":"Le","sequence":"first","affiliation":[{"name":"Japan Advanced Institute of Science and Technology, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3985-6892","authenticated-orcid":false,"given":"Sixia","family":"Li","sequence":"additional","affiliation":[{"name":"Japan Advanced Institute of Science and Technology, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9853-8893","authenticated-orcid":false,"given":"Candy Olivia","family":"Mawalim","sequence":"additional","affiliation":[{"name":"School of Information Science, Japan Advanced Institute of Science and Technology, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0376-3535","authenticated-orcid":false,"given":"Hung-Hsuan","family":"Huang","sequence":"additional","affiliation":[{"name":"Faculty of Informatics, The University of Fukuchiyama, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2698-9884","authenticated-orcid":false,"given":"Chee Wee","family":"Leong","sequence":"additional","affiliation":[{"name":"NLP, Speech and Multimodal, Educational Testing Service, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9260-0403","authenticated-orcid":false,"given":"Shogo","family":"Okada","sequence":"additional","affiliation":[{"name":"Japan Advanced Institute of Science and Technology, Japan"}]}],"member":"320","published-online":{"date-parts":[[2024,11,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00663"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_16"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0065-2601(00)80006-4"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-03161-3_35"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.3390\/math10091582"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the Workshop on Intelligent Information Processing and Natural Language Generation, Daniel S\u00e1nchez, Raquel Herv\u00e1s","author":"Pooja","year":"2020","unstructured":"Pooja Rao\u00a0S B, Manish Agnihotri, and Dinesh\u00a0Babu Jayagopi. 2020. Automatic Follow-up Question Generation for Asynchronous Interviews. In Proceedings of the Workshop on Intelligent Information Processing and Natural Language Generation, Daniel S\u00e1nchez, Raquel Herv\u00e1s, and Albert Gatt (Eds.). Association for Computational Lingustics, Santiago de Compostela, Spain, 10\u201320. https:\/\/aclanthology.org\/2020.intellang-1.2"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479897"},{"key":"e_1_3_2_1_9_1","volume-title":"Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates","author":"Brown Tom","year":"1877","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared\u00a0D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates, Inc., 1877\u20131901. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475661"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273646"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136801"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.45"},{"key":"e_1_3_2_1_14_1","volume-title":"NIPS 2014 Workshop on Deep Learning","author":"Chung Junyoung","year":"2014","unstructured":"Junyoung Chung, Caglar Gulcehre, Kyunghyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. NIPS 2014 Workshop on Deep Learning, December 2014 (2014)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_17_1","volume-title":"Multi-Class Bias Mitigation for Predicting Speaker Confidence. In International Conference on Educational Data Mining.","author":"Emerson Andrew","year":"2024","unstructured":"Andrew Emerson, Arti Ramesh, Patrick Houghton, Vinay Basheerabad, Navaneeth Jawahar, and Chee\u00a0Wee Leong. 2024. Multimodal, Multi-Class Bias Mitigation for Predicting Speaker Confidence. In International Conference on Educational Data Mining."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1207"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","unstructured":"L\u00e9o Hemamou Ghazi Felhi Vincent Vandenbussche Jean-Claude Martin and Chlo\u00e9 Clavel. 2019. HireNet: a hierarchical attention model for the automatic analysis of asynchronous video job interviews. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence (Honolulu Hawaii USA) (AAAI\u201919\/IAAI\u201919\/EAAI\u201919). AAAI Press Article 71 9\u00a0pages. https:\/\/doi.org\/10.1609\/aaai.v33i01.3301573","DOI":"10.1609\/aaai.v33i01.3301573"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3113159"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493502"},{"key":"e_1_3_2_1_27_1","volume-title":"5th International Conference on Learning Representations, ICLR","author":"Jang Eric","year":"2017","unstructured":"Eric Jang, Shixiang Gu, and Ben Poole. 2017. Categorical Reparameterization with Gumbel-Softmax. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=rkE3y85ee"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW52041.2021.00006"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418888"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-35915-6_27"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3686215.3688377"},{"key":"e_1_3_2_1_32_1","volume-title":"To trust, or not to trust? A study of human bias in automated video interview assessments. arXiv preprint arXiv:1911.13248","author":"Leong Chee\u00a0Wee","year":"2019","unstructured":"Chee\u00a0Wee Leong, Katrina Roohr, Vikram Ramanarayanan, Michelle\u00a0P Martin-Raugh, Harrison Kell, Rutuja Ubale, Yao Qian, Zydrune Mladineo, and Laura McCulla. 2019. To trust, or not to trust? A study of human bias in automated video interview assessments. arXiv preprint arXiv:1911.13248 (2019)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. https:\/\/doi.org\/10.48550\/arXiv.1907.11692 arXiv:1907.11692 [cs].","DOI":"10.48550\/arXiv.1907.11692"},{"key":"e_1_3_2_1_34_1","volume-title":"5th International Conference on Learning Representations, ICLR","author":"Maddison J.","year":"2017","unstructured":"Chris\u00a0J. Maddison, Andriy Mnih, and Yee\u00a0Whye Teh. 2017. The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=S1jE5L5gl"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems -","volume":"2","author":"Maddison J.","year":"2014","unstructured":"Chris\u00a0J. Maddison, Daniel Tarlow, and Tom Minka. 2014. A* sampling. In Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2 (Montreal, Canada) (NIPS\u201914). MIT Press, Cambridge, MA, USA, 3086\u20133094."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418869"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7163127"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2307169"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2820760"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2557058"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3568444.3568461"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3265754"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_32"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","unstructured":"Wasifur Rahman Sazan Mahbub Asif Salekin Md\u00a0Kamrul Hasan and Ehsan Hoque. 2021. HirePreter: A Framework for Providing Fine-grained Interpretation for Automated Job Interview Analysis. In 2021 9th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW). 1\u20135. https:\/\/doi.org\/10.1109\/ACIIW52867.2021.9666201","DOI":"10.1109\/ACIIW52867.2021.9666201"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-08561-6"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"volume-title":"Advances in Neural Information Processing Systems, Vol.\u00a030. Curran Associates","author":"Vaswani Ashish","key":"e_1_3_2_1_48_1","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, Vol.\u00a030. Curran Associates, Inc."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3029425"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00919"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350987"}],"event":{"name":"ICMI '24: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","acronym":"ICMI '24","location":"San Jose Costa Rica"},"container-title":["International Conference on Multimodel Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3678957.3685718","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3678957.3685718","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:12Z","timestamp":1750295412000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3678957.3685718"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,4]]},"references-count":52,"alternative-id":["10.1145\/3678957.3685718","10.1145\/3678957"],"URL":"https:\/\/doi.org\/10.1145\/3678957.3685718","relation":{},"subject":[],"published":{"date-parts":[[2024,11,4]]},"assertion":[{"value":"2024-11-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}