{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:34:52Z","timestamp":1772908492917,"version":"3.50.1"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T00:00:00Z","timestamp":1768953600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry and Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003626","name":"Defense Acquisition Program Administration","doi-asserted-by":"publisher","award":["23-CM-Al-15"],"award-info":[{"award-number":["23-CM-Al-15"]}],"id":[{"id":"10.13039\/501100003626","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.cviu.2026.104666","type":"journal-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T17:09:42Z","timestamp":1769792982000},"page":"104666","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["FusGaze: Full range gaze estimation with multi-scale fusion"],"prefix":"10.1016","volume":"265","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0535-3398","authenticated-orcid":false,"given":"Dayeon","family":"Yoo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2618-3938","authenticated-orcid":false,"given":"Jaehun","family":"Cho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0586-5594","authenticated-orcid":false,"given":"Kwangho","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104666_b1","doi-asserted-by":"crossref","unstructured":"Abdelrahman,\u00a0A.A., Hussein,\u00a0M.E., Abdelrahman,\u00a0A.H., Abdelrahman,\u00a0H.A., Ali,\u00a0H.A., 2023. L2CS-Net: Fine-grained gaze estimation in unconstrained environments. In: Proc. of 8th International Conf. on Frontiers of Signal Processing. ICFSP, Paris, France, pp. 42\u201346.","DOI":"10.1109\/ICFSP59764.2023.10372944"},{"key":"10.1016\/j.cviu.2026.104666_b2","doi-asserted-by":"crossref","DOI":"10.1109\/THMS.2025.3553404","article-title":"SLYKLatent: A learning framework for gaze estimation using deep facial feature learning","author":"Adebayo","year":"2025","journal-title":"IEEE Trans. Human-Machine Syst."},{"issue":"15","key":"10.1016\/j.cviu.2026.104666_b3","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1016\/j.ifacol.2022.07.627","article-title":"Hand-eye-object tracking for human intention inference","volume":"55","author":"Adebayo","year":"2022","journal-title":"IFAC-PapersOnLine"},{"key":"10.1016\/j.cviu.2026.104666_b4","series-title":"One eye is all you need: Lightweight ensembles for gaze estimation with single encoders","author":"Athavale","year":"2022"},{"key":"10.1016\/j.cviu.2026.104666_b5","doi-asserted-by":"crossref","unstructured":"C\u0103trun\u0103,\u00a0A., Cosma,\u00a0A., R\u0103doi,\u00a0E., 2024. CrossGaze: A Strong Method for 3D Gaze Estimation in the Wild. In: Proc. of IEEE 18th International Conference on Automatic Face and Gesture Recognition. FG.","DOI":"10.1109\/FG59268.2024.10581977"},{"key":"10.1016\/j.cviu.2026.104666_b6","series-title":"360-Degree gaze estimation in the wild using multiple zoom scales","author":"Chen","year":"2020"},{"key":"10.1016\/j.cviu.2026.104666_b7","doi-asserted-by":"crossref","unstructured":"Chen,\u00a0Z., Shi,\u00a0B.E., 2019. Appearance-based gaze estimation using dilated-convolutions. In: Jawahar,\u00a0C.V., Li,\u00a0H., Mori,\u00a0G., Schindler,\u00a0K. (Eds.), Proc. of Asian Conf. on Computer Vision. ACCV, 11366, Cham, Switzerland, pp. 309\u2013324. http:\/\/dx.doi.org\/10.1007\/978-3-030-20876-9_20.","DOI":"10.1007\/978-3-030-20876-9_20"},{"key":"10.1016\/j.cviu.2026.104666_b8","series-title":"DMAGaze: Gaze estimation based on feature disentanglement and multi-scale attention","author":"Chen","year":"2025"},{"key":"10.1016\/j.cviu.2026.104666_b9","series-title":"Proc. of AAAI Conf. on Artificial Intelligence","first-page":"10623","article-title":"A coarse-to-fine adaptive network for appearance-based gaze estimation","volume":"vol. 34","author":"Cheng","year":"2020"},{"key":"10.1016\/j.cviu.2026.104666_b10","doi-asserted-by":"crossref","unstructured":"Cheng,\u00a0Y., Lu,\u00a0F., 2022. Gaze Estimation using Transformer. In: 2022 26th International Conference on Pattern Recognition (ICPR). pp. 3341\u20133347. http:\/\/dx.doi.org\/10.1109\/ICPR56361.2022.9956687.","DOI":"10.1109\/ICPR56361.2022.9956687"},{"issue":"12","key":"10.1016\/j.cviu.2026.104666_b11","doi-asserted-by":"crossref","first-page":"7509","DOI":"10.1109\/TPAMI.2024.3393571","article-title":"Appearance-based gaze estimation with deep learning: A review and benchmark","volume":"46","author":"Cheng","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"10.1016\/j.cviu.2026.104666_b12","first-page":"27","article-title":"Human-robot interaction: from AI to HCI and social robotics","volume":"27","author":"Dautenhahn","year":"2006","journal-title":"AI Mag."},{"key":"10.1016\/j.cviu.2026.104666_b13","doi-asserted-by":"crossref","unstructured":"Dias,\u00a0P., Malafronte,\u00a0D., Medeiros,\u00a0H., Odone,\u00a0F., 2020. Gaze estimation for assisted living environments. In: Proc. of International Conf. on Computer Vision Theory and Applications. VISAPP, Valletta, Malta, pp. 279\u2013288.","DOI":"10.1109\/WACV45572.2020.9093439"},{"issue":"3","key":"10.1016\/j.cviu.2026.104666_b14","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/S0921-8890(02)00372-X","article-title":"A survey of socially interactive robots","volume":"42","author":"Fong","year":"2003","journal-title":"Robot. Auton. Syst."},{"issue":"6","key":"10.1016\/j.cviu.2026.104666_b15","first-page":"443","article-title":"Human-robot interaction in search and rescue","volume":"27","author":"Goodrich","year":"2010","journal-title":"J. Field Robot."},{"issue":"12","key":"10.1016\/j.cviu.2026.104666_b16","article-title":"A dynamic feature interaction gaze estimation network based on dual branches","volume":"vol. 52","author":"Hu","year":"2025"},{"issue":"5","key":"10.1016\/j.cviu.2026.104666_b17","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1006\/rtim.2002.0279","article-title":"Real-time eye, gaze, and face pose tracking for monitoring driver vigilance","volume":"8","author":"Ji","year":"2002","journal-title":"Real-Time Imaging"},{"key":"10.1016\/j.cviu.2026.104666_b18","doi-asserted-by":"crossref","unstructured":"Kellnhofer,\u00a0P., Recasens,\u00a0A., Stent,\u00a0S., Matusik,\u00a0W., Torralba,\u00a0A., 2019. Gaze360: Physically unconstrained gaze estimation in the wild. In: Proc. of IEEE International Conf. on Computer Vision. ICCV, Seoul, South Korea, pp. 6912\u20136921.","DOI":"10.1109\/ICCV.2019.00701"},{"key":"10.1016\/j.cviu.2026.104666_b19","doi-asserted-by":"crossref","unstructured":"Krafka,\u00a0K., Khosla,\u00a0A., Kellnhofer,\u00a0P., Kannan,\u00a0H., Bhandarkar,\u00a0S., Matusik,\u00a0W., Torralba,\u00a0A., 2016. Eye tracking for everyone. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition. CVPR, Las Vegas, NV, USA, pp. 2176\u20132184.","DOI":"10.1109\/CVPR.2016.239"},{"issue":"7","key":"10.1016\/j.cviu.2026.104666_b20","doi-asserted-by":"crossref","first-page":"3684","DOI":"10.3390\/app15073684","article-title":"Gaze estimation based on a multi-stream adaptive feature fusion network","volume":"15","author":"Li","year":"2025","journal-title":"Appl. Sci."},{"key":"10.1016\/j.cviu.2026.104666_b21","doi-asserted-by":"crossref","unstructured":"Lin,\u00a0T.-Y., Doll\u00e1r,\u00a0P., Girshick,\u00a0R., He,\u00a0K., Hariharan,\u00a0B., Belongie,\u00a0S., 2017. Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"issue":"1","key":"10.1016\/j.cviu.2026.104666_b22","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/TAFFC.2017.2740923","article-title":"AffectNet: A database for facial expression, valence, and arousal computing in the wild","volume":"10","author":"Mollahosseini","year":"2019","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.cviu.2026.104666_b23","doi-asserted-by":"crossref","unstructured":"Nagpure,\u00a0V., Okuma,\u00a0K., 2023. Searching efficient neural architecture with multi-resolution fusion transformer for appearance-based gaze estimation. In: Proc. of IEEE\/CVF Winter Conf. on Applications of Computer Vision. WACV, Waikoloa, HI, USA, pp. 5065\u20135074.","DOI":"10.1109\/WACV56688.2023.00095"},{"issue":"2","key":"10.1016\/j.cviu.2026.104666_b24","doi-asserted-by":"crossref","first-page":"456","DOI":"10.3390\/s18020456","article-title":"Deep learning-based gaze detection system for automobile drivers using a NIR camera sensor","volume":"18","author":"Naqvi","year":"2018","journal-title":"Sensors"},{"key":"10.1016\/j.cviu.2026.104666_b25","doi-asserted-by":"crossref","unstructured":"Oh,\u00a0J., Chang,\u00a0H.J., Choi,\u00a0S.-I., 2022. Self-attention with convolution and deconvolution for efficient eye gaze estimation from a full face image. In: Proc. of IEEE\/CVF Conf. on Computer Vision and Pattern Recognition Workshops. CVPRW, New Orleans, LA, USA, pp. 3533\u20133542.","DOI":"10.1109\/CVPRW56347.2022.00547"},{"issue":"9","key":"10.1016\/j.cviu.2026.104666_b26","doi-asserted-by":"crossref","first-page":"2183","DOI":"10.1073\/pnas.1617251114","article-title":"Optimizing virtual reality for all users through gaze-contingent and adaptive focus displays","volume":"114","author":"Padmanaban","year":"2017","journal-title":"Proc. Natl. Acad. Sci. (PNAS)"},{"key":"10.1016\/j.cviu.2026.104666_b27","doi-asserted-by":"crossref","unstructured":"Patney,\u00a0A., Kim,\u00a0J., Salvi,\u00a0M., Kaplanyan,\u00a0A., Wyman,\u00a0C., Benty,\u00a0N., Lefohn,\u00a0A., Luebke,\u00a0D., 2016a. Perceptually-based foveated virtual reality. In: Proc. of ACM SIGGRAPH 2016 Emerging Technologies. SIGGRAPH \u201916, New York, NY, USA.","DOI":"10.1145\/2929464.2929472"},{"issue":"6","key":"10.1016\/j.cviu.2026.104666_b28","doi-asserted-by":"crossref","first-page":"179:1","DOI":"10.1145\/2980179.2980246","article-title":"Towards foveated rendering for gaze-tracked virtual reality","volume":"35","author":"Patney","year":"2016","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.cviu.2026.104666_b29","doi-asserted-by":"crossref","unstructured":"Piumsomboon,\u00a0T., Lee,\u00a0G., Lindeman,\u00a0R.W., Billinghurst,\u00a0M., 2017. Exploring natural eye-gaze-based interaction for immersive virtual reality. In: Proc. of IEEE Symposium on 3D User Interfaces. 3DUI, Los Angeles, CA, USA, pp. 36\u201339.","DOI":"10.1109\/3DUI.2017.7893315"},{"key":"10.1016\/j.cviu.2026.104666_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.jesp.2019.103842","article-title":"Understanding cognitive and affective mechanisms in social psychology through eye-tracking","volume":"85","author":"Rahal","year":"2019","journal-title":"J. Exp. Soc. Psychol."},{"key":"10.1016\/j.cviu.2026.104666_b31","doi-asserted-by":"crossref","unstructured":"Ruiz,\u00a0N., Chong,\u00a0E., Rehg,\u00a0J.M., 2018. Fine-grained head pose estimation without keypoints. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition Workshops. CVPRW, Salt Lake City, UT, USA, pp. 2074\u20132083.","DOI":"10.1109\/CVPRW.2018.00281"},{"key":"10.1016\/j.cviu.2026.104666_b32","series-title":"DHECA-SuperGaze: Dual head-eye cross-attention and super-resolution for unconstrained gaze estimation","author":"\u0160iki\u0107","year":"2025"},{"key":"10.1016\/j.cviu.2026.104666_b33","doi-asserted-by":"crossref","unstructured":"Sinha,\u00a0N., Balazia,\u00a0M., Bremond,\u00a0F., 2021. FLAME: Facial landmark heatmap activated multimodal gaze estimation. In: Proc. of 17th IEEE International Conf. on Advanced Video and Signal Based Surveillance. AVSS, Washington, DC, USA, pp. 1\u20138.","DOI":"10.1109\/AVSS52988.2021.9663816"},{"key":"10.1016\/j.cviu.2026.104666_b34","series-title":"What is YOLOv8? The ultimate guide","author":"Solawetz","year":"2023"},{"key":"10.1016\/j.cviu.2026.104666_b35","unstructured":"Tan,\u00a0K.-H., Kriegman,\u00a0D.J., Ahuja,\u00a0N., 2002. Appearance-based eye gaze estimation. In: Proc. of Sixth IEEE Workshop on Applications of Computer Vision. WACV, Orlando, FL, USA, pp. 191\u2013195."},{"key":"10.1016\/j.cviu.2026.104666_b36","doi-asserted-by":"crossref","unstructured":"Woo,\u00a0S., Park,\u00a0J., Lee,\u00a0J.-Y., Kweon,\u00a0I.S., 2018. CBAM: Convolutional block attention module. In: Proc. of European Conf. on Computer Vision. ECCV, Munich, Germany, pp. 3\u201319.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"10.1016\/j.cviu.2026.104666_b37","doi-asserted-by":"crossref","unstructured":"Xu,\u00a0Y., Dong,\u00a0Y., Wu,\u00a0J., Sun,\u00a0Z., Shi,\u00a0Z., Yu,\u00a0J., Gao,\u00a0S., 2018. Gaze prediction in dynamic 360\u00b0immersive videos. In: Proc. of IEEE\/CVF Conf. on Computer Vision and Pattern Recognition. CVPR, Salt Lake City, UT, USA, pp. 5333\u20135342.","DOI":"10.1109\/CVPR.2018.00559"},{"issue":"10","key":"10.1016\/j.cviu.2026.104666_b38","doi-asserted-by":"crossref","first-page":"5901","DOI":"10.3390\/app13105901","article-title":"Gaze estimation via strip pooling and multi-criss-cross attention networks","volume":"13","author":"Yan","year":"2023","journal-title":"Appl. Sci."},{"key":"10.1016\/j.cviu.2026.104666_b39","doi-asserted-by":"crossref","first-page":"93448","DOI":"10.1109\/ACCESS.2019.2928339","article-title":"Driver gaze detection based on deep residual networks using the combined single image of dual near-infrared cameras","volume":"7","author":"Yoon","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.cviu.2026.104666_b40","doi-asserted-by":"crossref","unstructured":"Zhang,\u00a0X., Sugano,\u00a0Y., Bulling,\u00a0A., 2017a. Everyday eye contact detection using unsupervised gaze target discovery. In: Proc. of the 30th Annual ACM Symposium on User Interface Software and Technology. UIST\u201917, New York, NY, USA, pp. 193\u2013203.","DOI":"10.1145\/3126594.3126614"},{"key":"10.1016\/j.cviu.2026.104666_b41","doi-asserted-by":"crossref","unstructured":"Zhang,\u00a0X., Sugano,\u00a0Y., Fritz,\u00a0M., Bulling,\u00a0A., 2017b. It\u2019s written all over your face: Full-face appearance-based gaze estimation. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition Workshops. CVPRW, Honolulu, HI, USA, pp. 2299\u20132308.","DOI":"10.1109\/CVPRW.2017.284"},{"issue":"3","key":"10.1016\/j.cviu.2026.104666_b42","first-page":"115","article-title":"GazeSymCAT: A symmetric cross-attention transformer for robust gaze estimation under extreme head poses and gaze variations","volume":"12","author":"Zhong","year":"2025","journal-title":"J. Comput. Des. Eng."}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226000330?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226000330?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T02:17:53Z","timestamp":1772849873000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226000330"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":42,"alternative-id":["S1077314226000330"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104666","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FusGaze: Full range gaze estimation with multi-scale fusion","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104666","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Infiniq. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"104666"}}