{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T23:46:03Z","timestamp":1771458363570,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,4]],"date-time":"2024-06-04T00:00:00Z","timestamp":1717459200000},"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":[[2024,6,4]]},"DOI":"10.1145\/3649902.3653340","type":"proceedings-article","created":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T18:23:51Z","timestamp":1717179831000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Gaze-Guided Graph Neural Network for Action Anticipation Conditioned on Intention"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3390-6154","authenticated-orcid":false,"given":"S\u00fcleyman","family":"\u00d6zdel","sequence":"first","affiliation":[{"name":"Human-Centered Technologies for Learning, Technical University of Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6031-3741","authenticated-orcid":false,"given":"Yao","family":"Rong","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3406-8412","authenticated-orcid":false,"given":"Berat Mert","family":"Albaba","sequence":"additional","affiliation":[{"name":"Department of Computer Science\/AIT Lab, ETH Z\u00fcrich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6433-6713","authenticated-orcid":false,"given":"Yen-Ling","family":"Kuo","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5442-1116","authenticated-orcid":false,"given":"Xi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, ETH, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3146-4484","authenticated-orcid":false,"given":"Enkelejda","family":"Kasneci","sequence":"additional","affiliation":[{"name":"Human-Centered Technologies for Learning, Technical University of Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3171221.3171287"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2017.2743165"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01509"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV). 720\u2013736","author":"Damen Dima","year":"2018","unstructured":"Dima Damen, Hazel Doughty, Giovanni\u00a0Maria Farinella, Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, 2018. Scaling egocentric vision: The epic-kitchens dataset. In Proceedings of the European Conference on Computer Vision (ECCV). 720\u2013736."},{"key":"e_1_3_2_1_6_1","volume-title":"Videograph: Recognizing minutes-long human activities in videos. arXiv preprint arXiv:1905.05143","author":"Hussein Noureldien","year":"2019","unstructured":"Noureldien Hussein, Efstratios Gavves, and Arnold\u00a0WM Smeulders. 2019. Videograph: Recognizing minutes-long human activities in videos. arXiv preprint arXiv:1905.05143 (2019)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413902"},{"key":"e_1_3_2_1_8_1","volume-title":"Creation and validation of a chest X-ray dataset with eye-tracking and report dictation for AI development. Scientific data 8, 1","author":"Karargyris Alexandros","year":"2021","unstructured":"Alexandros Karargyris, Satyananda Kashyap, Ismini Lourentzou, Joy\u00a0T Wu, Arjun Sharma, Matthew Tong, Shafiq Abedin, David Beymer, Vandana Mukherjee, Elizabeth\u00a0A Krupinski, 2021. Creation and validation of a chest X-ray dataset with eye-tracking and report dictation for AI development. Scientific data 8, 1 (2021), 92."},{"key":"e_1_3_2_1_9_1","volume-title":"KURT: A Household Assistance Robot Capable of Proactive Dialogue. In 2022 17th ACM\/IEEE International Conference on Human-Robot Interaction (HRI). IEEE, 855\u2013859","author":"Kraus Matthias","year":"2022","unstructured":"Matthias Kraus, Nicolas Wagner, Wolfgang Minker, Ankita Agrawal, Artur Schmidt, Pranav\u00a0Krishna Prasad, and Wolfgang Ertel. 2022. KURT: A Household Assistance Robot Capable of Proactive Dialogue. In 2022 17th ACM\/IEEE International Conference on Human-Robot Interaction (HRI). IEEE, 855\u2013859."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00332"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298625"},{"key":"e_1_3_2_1_13_1","volume-title":"Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00111"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00024"},{"key":"e_1_3_2_1_16_1","first-page":"4","article-title":"The Tobii I-VT fixation filter","volume":"21","author":"Olsen Anneli","year":"2012","unstructured":"Anneli Olsen. 2012. The Tobii I-VT fixation filter. Tobii Technology 21 (2012), 4\u201319.","journal-title":"Tobii Technology"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2019.2892919"},{"key":"e_1_3_2_1_18_1","volume-title":"2017 26th IEEE international symposium on robot and human interactive communication (RO-MAN). IEEE, 987\u2013992","author":"Xuan\u00a0Ngan Pham Thi","year":"2017","unstructured":"Thi Xuan\u00a0Ngan Pham, Kotaro Hayashi, Christian Becker-Asano, Sebastian Lacher, and Ikuo Mizuuchi. 2017. Evaluating the usability and users\u2019 acceptance of a kitchen assistant robot in household environment. In 2017 26th IEEE international symposium on robot and human interactive communication (RO-MAN). IEEE, 987\u2013992."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00886"},{"key":"e_1_3_2_1_20_1","volume-title":"Watch-and-help: A challenge for social perception and human-ai collaboration. arXiv preprint arXiv:2010.09890","author":"Puig Xavier","year":"2020","unstructured":"Xavier Puig, Tianmin Shu, Shuang Li, Zilin Wang, Yuan-Hong Liao, Joshua\u00a0B Tenenbaum, Sanja Fidler, and Antonio Torralba. 2020. Watch-and-help: A challenge for social perception and human-ai collaboration. arXiv preprint arXiv:2010.09890 (2020)."},{"key":"e_1_3_2_1_21_1","volume-title":"International conference on machine learning. PMLR, 8748\u20138763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_3_2_1_22_1","volume-title":"Human Attention in Fine-grained Classification. BMVC","author":"Rong Yao","year":"2021","unstructured":"Yao Rong, Wenjia Xu, Zeynep Akata, and Enkelejda Kasneci. 2021. Human Attention in Fine-grained Classification. BMVC (2021)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1124772.1124886"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793804"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.11"},{"key":"e_1_3_2_1_26_1","volume-title":"Human\u2013robot interaction in agriculture: A survey and current challenges. Biosystems engineering 179","author":"Vasconez P","year":"2019","unstructured":"Juan\u00a0P Vasconez, George\u00a0A Kantor, and Fernando A\u00a0Auat Cheein. 2019. Human\u2013robot interaction in agriculture: A survey and current challenges. Biosystems engineering 179 (2019), 35\u201348."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2018.02.009"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340893"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093524"},{"key":"e_1_3_2_1_30_1","volume-title":"Predicting driver attention in critical situations","author":"Xia Ye","unstructured":"Ye Xia, Danqing Zhang, Jinkyu Kim, Ken Nakayama, Karl Zipser, and David Whitney. 2019. Predicting driver attention in critical situations. In ACCV. Springer, 658\u2013674."},{"key":"e_1_3_2_1_31_1","volume-title":"Conference on Robot Learning. PMLR, 895\u2013904","author":"Zhao Hang","year":"2021","unstructured":"Hang Zhao, Jiyang Gao, Tian Lan, Chen Sun, Ben Sapp, Balakrishnan Varadarajan, Yue Shen, Yi Shen, Yuning Chai, Cordelia Schmid, 2021. Tnt: Target-driven trajectory prediction. In Conference on Robot Learning. PMLR, 895\u2013904."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_39"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00887"}],"event":{"name":"ETRA '24: The 2024 Symposium on Eye Tracking Research and Applications","location":"Glasgow United Kingdom","acronym":"ETRA '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2024 Symposium on Eye Tracking Research and Applications"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649902.3653340","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649902.3653340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T11:45:40Z","timestamp":1755863140000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649902.3653340"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,4]]},"references-count":33,"alternative-id":["10.1145\/3649902.3653340","10.1145\/3649902"],"URL":"https:\/\/doi.org\/10.1145\/3649902.3653340","relation":{},"subject":[],"published":{"date-parts":[[2024,6,4]]},"assertion":[{"value":"2024-06-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}