{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T19:06:28Z","timestamp":1768676788289,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Natural Science Foundation of the Jiangsu Higher Education Institutions of China","award":["22KJB520008"],"award-info":[{"award-number":["22KJB520008"]}]},{"name":"Research Fund of Horizon Robotics","award":["H230666"],"award-info":[{"award-number":["H230666"]}]},{"name":"Jiangsu Policy Guidance Program, International Science and Technology Cooperation, The Belt and Road Initiative Innovative Cooperation Projects","award":["BZ2021016"],"award-info":[{"award-number":["BZ2021016"]}]},{"name":"Undergraduate Training Program for Innovation and Entrepreneurship,Soochow University","award":["202310285078Z"],"award-info":[{"award-number":["202310285078Z"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3657618","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"1140-1144","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["YawnNet: A Visual-Centric Approach for Yawning Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5180-2954","authenticated-orcid":false,"given":"Ruoxi","family":"Sun","sequence":"first","affiliation":[{"name":"School of Future Science and Engineering, Soochow University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8319-4851","authenticated-orcid":false,"given":"Xinyu","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Future Science and Engineering, Soochow University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9632-0433","authenticated-orcid":false,"given":"Cong","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Future Science and Engineering, Soochow University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6240-9985","authenticated-orcid":false,"given":"Chenyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Future Science and Engineering, Soochow University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5182-5621","authenticated-orcid":false,"given":"Wei","family":"Sui","sequence":"additional","affiliation":[{"name":"Horizon Robotics, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9778-9164","authenticated-orcid":false,"given":"Zeyd","family":"Boukhers","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Applied Information Technology & University Hospital of Cologne, Sankt Augustin, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8314-0935","authenticated-orcid":false,"given":"Cong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Future Science and Engineering, Soochow University, Suzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2557642.2563678"},{"key":"e_1_3_2_1_2_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/IAdCC.2014.6779459"},{"key":"e_1_3_2_1_4_1","volume-title":"Effect of Drowsiness on Driver Performance and Traffic Safety. In Advances in Science and Engineering Technology International Conferences. 1--6.","author":"Elbaz Yousef","year":"2020","unstructured":"Yousef Elbaz, Marwan Naeem, Muamer Abuzwidah, and Samer Barakat. 2020. Effect of Drowsiness on Driver Performance and Traffic Safety. In Advances in Science and Engineering Technology International Conferences. 1--6."},{"key":"e_1_3_2_1_5_1","volume-title":"A CNN-LSTM-based Deep Learning Approach for Driver Drowsiness Prediction. Journal of Engineering Research","author":"Gomaa Mohamed Waheed","year":"2022","unstructured":"Mohamed Waheed Gomaa, Rasha O Mahmoud, and Amany M Sarhan. 2022. A CNN-LSTM-based Deep Learning Approach for Driver Drowsiness Prediction. Journal of Engineering Research (2022)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2015.02.006"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00091"},{"key":"e_1_3_2_1_8_1","unstructured":"HA Kassem Morshed Chowdhury Jemal Abawajy and Ahmed Raad Abdul Hussein Al-Sudani. 2020. Yawn Based Driver Fatigue Level Prediction. (2020)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_10_1","volume-title":"When does label smoothing help? Advances in neural information processing systems 32","author":"M\u00fcller Rafael","year":"2019","unstructured":"Rafael M\u00fcller, Simon Kornblith, and Geoffrey E Hinton. 2019. When does label smoothing help? Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/VECIMS.2011.6053857"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/IBSSC56953.2022.10037264"},{"key":"e_1_3_2_1_13_1","volume-title":"Shyam Sunder Prasad, and Sanjay Singh","author":"Saurav Sumeet","year":"2020","unstructured":"Sumeet Saurav, Shubhad Mathur, Ishan Sang, Shyam Sunder Prasad, and Sanjay Singh. 2020. Yawn detection for driver's drowsiness prediction using bidirectional LSTM with CNN features. In Intelligent Human Computer. 189--200."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2000.902999"},{"key":"e_1_3_2_1_15_1","volume-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. Advances in neural information processing systems 35","author":"Tong Zhan","year":"2022","unstructured":"Zhan Tong, Yibing Song, Jue Wang, and Limin Wang. 2022. Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. Advances in neural information processing systems 35 (2022), 10078--10093."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICACTE.2010.5579830"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2018.8628881"},{"key":"e_1_3_2_1_18_1","volume-title":"Fatigue View: A Multi-Camera Video Dataset for Vision-Based Drowsiness Detection","author":"Yang Cong","year":"2022","unstructured":"Cong Yang, Zhenyu Yang, Weiyu Li, and John See. 2022. Fatigue View: A Multi-Camera Video Dataset for Vision-Based Drowsiness Detection. IEEE Transactions on Intelligent Transportation Systems (2022)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8285343"},{"key":"e_1_3_2_1_20_1","volume-title":"Generalized cross entropy loss for training deep neural networks with noisy labels. Advances in neural information processing systems 31","author":"Zhang Zhilu","year":"2018","unstructured":"Zhilu Zhang and Mert Sabuncu. 2018. Generalized cross entropy loss for training deep neural networks with noisy labels. Advances in neural information processing systems 31 (2018)."}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","location":"Phuket Thailand","acronym":"ICMR '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3657618","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3657618","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:49:12Z","timestamp":1755766152000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3657618"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":20,"alternative-id":["10.1145\/3652583.3657618","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3657618","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}