{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T01:49:23Z","timestamp":1782006563160,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,31]],"date-time":"2026-05-31T00:00:00Z","timestamp":1780185600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1145\/3797246.3805859","type":"proceedings-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:08:10Z","timestamp":1780056490000},"page":"1-3","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Gaze-informed Object Sequences for Egocentric Action Recognition using Deep Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6771-7693","authenticated-orcid":false,"given":"Nora Jane","family":"Castner","sequence":"first","affiliation":[{"name":"Zeiss Vision Science Lab, Zeiss, Aalen, Baden-W\u00fcrttemberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4773-5033","authenticated-orcid":false,"given":"Zhengyu","family":"Su","sequence":"additional","affiliation":[{"name":"Trinity College Dublin, Dublin, Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3437-6711","authenticated-orcid":false,"given":"Siegfried","family":"Wahl","sequence":"additional","affiliation":[{"name":"University of T\u00fcbingen, Institute for Ophthalmic Research, T\u00fcbingen, Germany and Carl Zeiss Vision International GmbH, Aalen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,31]]},"reference":[{"key":"e_1_3_3_1_2_1","doi-asserted-by":"crossref","unstructured":"Maria Barrett and Nora Hollenstein. 2020. Sequence labelling and sequence classification with gaze: Novel uses of eye-tracking data for Natural Language Processing. Language and Linguistics Compass 14 11 (2020) 1\u201316.","DOI":"10.1111\/lnc3.12396"},{"key":"e_1_3_3_1_3_1","doi-asserted-by":"crossref","unstructured":"Jonathan\u00a0FG Boisvert and Neil\u00a0DB Bruce. 2016. Predicting task from eye movements: On the importance of spatial distribution dynamics and image features. Neurocomputing 207 (2016) 653\u2013668.","DOI":"10.1016\/j.neucom.2016.05.047"},{"key":"e_1_3_3_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517031.3529631"},{"key":"e_1_3_3_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379155.3391320"},{"key":"e_1_3_3_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"e_1_3_3_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMIP.2019.00010"},{"key":"e_1_3_3_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-short.21"},{"key":"e_1_3_3_1_9_1","doi-asserted-by":"publisher","DOI":"10.2312\/vmv.20181252"},{"key":"e_1_3_3_1_10_1","unstructured":"Ian Goodfellow Yoshua Bengio and Aaron Courville. 2016. Sequence modeling: recurrent and recursive nets. Deep learning (2016) 367\u2013415."},{"key":"e_1_3_3_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1743666.1743718"},{"key":"e_1_3_3_1_12_1","doi-asserted-by":"crossref","unstructured":"Md\u00a0Mohi\u00a0Uddin Khan Abdullah\u00a0Bin Shams and Mohsin\u00a0Sarker Raihan. 2024. A prospective approach for human-to-human interaction recognition from Wi-Fi channel data using attention bidirectional gated recurrent neural network with GUI application implementation. Multimedia Tools and Applications 83 22 (2024) 62379\u201362422.","DOI":"10.1007\/s11042-023-17487-z"},{"key":"e_1_3_3_1_13_1","volume-title":"ICML 2024 Workshop on LLMs and Cognition","author":"Kiegeland Samuel","year":"2024","unstructured":"Samuel Kiegeland, David\u00a0Robert Reich, Ryan Cotterell, Lena\u00a0Ann J\u00e4ger, and Ethan Wilcox. 2024. The Pupil Becomes the Master: Eye-Tracking Feedback for Tuning LLMs. In ICML 2024 Workshop on LLMs and Cognition. https:\/\/openreview.net\/forum?id=8oLUcBgKua"},{"key":"e_1_3_3_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3649902.3653349"},{"key":"e_1_3_3_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/WRCSARA64167.2024.10685712"},{"key":"e_1_3_3_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"e_1_3_3_1_17_1","unstructured":"Angela Lopez-Cardona Carlos Segura Alexandros Karatzoglou Sergi Abadal and Ioannis Arapakis. 2024. Seeing eye to AI: human alignment via gaze-based response rewards for large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.01532 (2024)."},{"key":"e_1_3_3_1_18_1","doi-asserted-by":"crossref","unstructured":"Catarina Moreira Jeffrey Cockburn and Monica\u00a0S Castelhano. 2025. A Framework for Leveraging LLMs for Scene Analysis and Cognitive Processing. Proceedings of the ACM on Computer Graphics and Interactive Techniques 8 2 (2025) 1\u201318.","DOI":"10.1145\/3729414"},{"key":"e_1_3_3_1_19_1","doi-asserted-by":"crossref","unstructured":"Claudio\u00a0M. Privitera and Lawrence\u00a0W. Stark. 2000. Algorithms for defining visual regions-of-interest: Comparison with eye fixations. IEEE Transactions on Pattern Analysis and Machine Intelligence 22 9 (2000) 970\u2013982.","DOI":"10.1109\/34.877520"},{"key":"e_1_3_3_1_20_1","unstructured":"Karen Simonyan Andrea Vedaldi and Andrew Zisserman. 2013. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. arxiv:https:\/\/arXiv.org\/abs\/1312.6034\u00a0[cs.CV]"},{"key":"e_1_3_3_1_21_1","doi-asserted-by":"publisher","unstructured":"Xiaohan Wang Linchao Zhu Yu Wu and Yi Yang. 2020. Symbiotic Attention for Egocentric Action Recognition With Object-Centric Alignment. IEEE Transactions on Pattern Analysis and Machine Intelligence 45 (2020) 6605\u20136617. 10.1109\/TPAMI.2020.3015894","DOI":"10.1109\/TPAMI.2020.3015894"},{"key":"e_1_3_3_1_22_1","doi-asserted-by":"publisher","DOI":"10.7557\/18.6797"},{"key":"e_1_3_3_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517031.3529628"}],"event":{"name":"ETRA '26: 2026 Symposium on Eye Tracking Research and Applications","location":"Marrakesh Morocco","acronym":"ETRA '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the 2026 Symposium on Eye Tracking Research and Applications"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3797246.3805859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T01:07:15Z","timestamp":1782004035000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797246.3805859"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,31]]},"references-count":22,"alternative-id":["10.1145\/3797246.3805859","10.1145\/3797246"],"URL":"https:\/\/doi.org\/10.1145\/3797246.3805859","relation":{},"subject":[],"published":{"date-parts":[[2026,5,31]]},"assertion":[{"value":"2026-05-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}