{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T12:02:45Z","timestamp":1774440165077,"version":"3.50.1"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s00530-025-02081-0","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T07:21:17Z","timestamp":1764832877000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Mixgaze: a dually supervised mixed attention network for gaze estimation"],"prefix":"10.1007","volume":"32","author":[{"given":"Ziyang","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yin","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hu","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Caihua","family":"Kong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,4]]},"reference":[{"issue":"12","key":"2081_CR1","doi-asserted-by":"crossref","first-page":"7509","DOI":"10.1109\/TPAMI.2024.3393571","volume":"46","author":"Y Cheng","year":"2024","unstructured":"Cheng, Y., Wang, H., Bao, Y., Lu, F.: Appearance-based gaze estimation with deep learning: a review and benchmark. IEEE Trans. Patt. Anal. Mach. Intell. 46(12), 7509\u20137528 (2024)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"issue":"2","key":"2081_CR2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3361330","volume":"39","author":"R Konrad","year":"2020","unstructured":"Konrad, R., Angelopoulos, A., Wetzstein, G.: Gaze-contingent ocular parallax rendering for virtual reality. ACM Trans. Gr. (TOG) 39(2), 1\u201312 (2020)","journal-title":"ACM Trans. Gr. (TOG)"},{"key":"2081_CR3","first-page":"1","volume-title":"ACM symposium on eye tracking research and applications","author":"N Castner","year":"2020","unstructured":"Castner, N., Kuebler, T.C., Scheiter, K., Richter, J., Eder, T., H\u00fcttig, F., Keutel, C., Kasneci, E.: Deep semantic gaze embedding and scanpath comparison for expertise classification during opt viewing. In: Step, A. (ed.) ACM symposium on eye tracking research and applications, pp. 1\u201310. ACM Digital Library, New York (2020)"},{"issue":"6","key":"2081_CR4","doi-asserted-by":"crossref","first-page":"3683","DOI":"10.1109\/JBHI.2024.3388836","volume":"28","author":"W Nie","year":"2024","unstructured":"Nie, W., Zhou, B., Wang, Z., Chen, B., Wang, X., Hu, C., Li, H., Xu, Q., Xu, X., Liu, H.: Computational interpersonal communication model for screening autistic toddlers: A case study of response-to-name. IEEE J. Biomed. Health Inform. 28(6), 3683\u20133694 (2024)","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"2081_CR5","first-page":"165","volume-title":"Proceedings of the IEEE international symposium on mixed and augmented reality adjunct","author":"Z Wang","year":"2020","unstructured":"Wang, Z., Yu, H., Wang, H., Wang, Z., Lu, F.: Comparing single-modal and multimodal interaction in an augmented reality system. In: Proceedings of the IEEE international symposium on mixed and augmented reality adjunct, pp. 165\u2013166. IEEE, Geneva (2020)"},{"key":"2081_CR6","first-page":"2052","volume-title":"Procedings of the AAAI conference on Artificial Intelligence","author":"H Chen","year":"2025","unstructured":"Chen, H., Wu, S., Wang, Z., Yin, Y., Jiao, Y., Lyu, Y., Liu, Z.: Causal-inspired multitask learning for video-based human pose estimation. In: Procedings of the AAAI conference on Artificial Intelligence, vol. 39, pp. 2052\u20132060. ACM Digital Library, New York (2025)"},{"key":"2081_CR7","first-page":"7632","volume-title":"Proceedings of the AAAI conference on Artificial Intelligence","author":"F Zhou","year":"2024","unstructured":"Zhou, F., Yin, J., Li, P.: Lifting by image-leveraging image cues for accurate 3D human pose estimation. In: Proceedings of the AAAI conference on Artificial Intelligence, vol. 38, pp. 7632\u20137640. ACM Digital Library, New York (2024)"},{"key":"2081_CR8","volume-title":"IEEE transactions on pattern analysis and machine intelligence","author":"J Gao","year":"2025","unstructured":"Gao, J., Chen, M., Xu, C.: Learning probabilistic presence-absence evidence for weakly-supervised audio-visual event perception. In: IEEE transactions on pattern analysis and machine intelligence. IEEE, Geneva (2025)"},{"key":"2081_CR9","first-page":"4511","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"X Zhang","year":"2015","unstructured":"Zhang, X., Sugano, Y., Fritz, M., Bulling, A.: Appearance-based gaze estimation in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4511\u20134520. IEEE, Geneva (2015)"},{"key":"2081_CR10","first-page":"100","volume-title":"Proceedings of the European conference on computer vision","author":"Y Cheng","year":"2018","unstructured":"Cheng, Y., Lu, F., Zhang, X.: Appearance-based gaze estimation via evaluation-guided asymmetric regression. In: Proceedings of the European conference on computer vision, pp. 100\u2013115. Springer, Cham (2018)"},{"issue":"11","key":"2081_CR11","doi-asserted-by":"crossref","first-page":"3680","DOI":"10.1109\/TIP.2015.2445295","volume":"24","author":"F Lu","year":"2015","unstructured":"Lu, F., Sugano, Y., Okabe, T., Sato, Y.: Gaze estimation from eye appearance: a head pose-free method via eye image synthesis. IEEE Trans. Image Process. 24(11), 3680\u20133693 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"2081_CR12","first-page":"87","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition workshops","author":"LA Jeni","year":"2016","unstructured":"Jeni, L.A., Cohn, J.F.: Person-independent 3d gaze estimation using face frontalization. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp. 87\u201395. IEEE, Geneva (2016)"},{"key":"2081_CR13","first-page":"98","volume-title":"Proceedings of the international conference on frontiers of signal processing","author":"AA Abdelrahman","year":"2023","unstructured":"Abdelrahman, A.A., Hempel, T., Khalifa, A., Al-Hamadi, A., Dinges, L.: L2cs-net: fine-grained gaze estimation in unconstrained environments. In: Proceedings of the international conference on frontiers of signal processing, pp. 98\u2013102. IEEE (2023)"},{"key":"2081_CR14","first-page":"2176","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"K Krafka","year":"2016","unstructured":"Krafka, K., Khosla, A., Kellnhofer, P., Kannan, H., Bhandarkar, S., Matusik, W., Torralba, A.: Eye tracking for everyone. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2176\u20132184. IEEE, Geneva (2016)"},{"key":"2081_CR15","first-page":"51","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition workshops","author":"X Zhang","year":"2017","unstructured":"Zhang, X., Sugano, Y., Fritz, M., Bulling, A.: It\u2019s written all over your face: Full-face appearance-based gaze estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp. 51\u201360. IEEE, Geneva (2017)"},{"key":"2081_CR16","first-page":"4197","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"M Zhang","year":"2022","unstructured":"Zhang, M., Liu, Y., Lu, F.: Gazeonce: real-time multi-person gaze estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 4197\u20134206. IEEE, Geneva (2022)"},{"key":"2081_CR17","first-page":"20","volume-title":"Proceedings of the 2020 2nd international conference on big-data service and intelligent computation","author":"Y Zhang","year":"2020","unstructured":"Zhang, Y., Yang, X., Ma, Z.: Driver\u2019s gaze zone estimation method: a four-channel convolutional neural network model. In: Proceedings of the 2020 2nd international conference on big-data service and intelligent computation, pp. 20\u201324. ACM Digital Library, New York (2020)"},{"key":"2081_CR18","first-page":"3443","volume-title":"Proceedings of the IEEE\/CVF Winter conference on applications of computer vision","author":"Z Wang","year":"2020","unstructured":"Wang, Z., Zhao, J., Lu, C., Yang, F., Huang, H., Guo, Y., et al.: Learning to detect head movement in unconstrained remote gaze estimation in the wild. In: Proceedings of the IEEE\/CVF Winter conference on applications of computer vision, pp. 3443\u20133452. IEEE, Geneva (2020)"},{"key":"2081_CR19","doi-asserted-by":"crossref","unstructured":"Catruna, A., Cosma, A., Radoi, E.: Crossgaze: A strong method for 3d gaze estimation in the wild. CoRR (2024)","DOI":"10.1109\/FG59268.2024.10581977"},{"key":"2081_CR20","volume-title":"IEEE transactions on image processing","author":"W Nie","year":"2025","unstructured":"Nie, W., Wang, Z., Ren, W., Zhang, H., Liu, H.: Iris geometric transformation guided deep appearance-based gaze estimation. In: IEEE transactions on image processing. IEEE, Geneva (2025)"},{"key":"2081_CR21","first-page":"3143","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"W Zhu","year":"2017","unstructured":"Zhu, W., Deng, H.: Monocular free-head 3d gaze tracking with deep learning and geometry constraints. In: Proceedings of the IEEE international conference on computer vision, pp. 3143\u20133152. IEEE, Geneva (2017)"},{"key":"2081_CR22","first-page":"10623","volume-title":"Procedings of the AAAI conference on Artificial Intelligence","author":"Y Cheng","year":"2020","unstructured":"Cheng, Y., Huang, S., Wang, F., Qian, C., Lu, F.: A coarse-to-fine adaptive network for appearance-based gaze estimation. In: Step, A. (ed.) Procedings of the AAAI conference on Artificial Intelligence, vol. 34, pp. 10623\u201310630. ACM Digital Library, New York (2020)"},{"key":"2081_CR23","unstructured":"Cai, X., Chen, B., Zeng, J., Zhang, J., Sun, Y., Wang, X., Ji, Z., Liu, X., Chen, X., Shan, S.: Gaze estimation with an ensemble of four architectures. arXiv:2107.01980 (2021)"},{"key":"2081_CR24","doi-asserted-by":"crossref","first-page":"111244","DOI":"10.1016\/j.patcog.2024.111244","volume":"161","author":"L Xia","year":"2025","unstructured":"Xia, L., Li, Y., Cai, X., Cui, Z., Xu, C., Chan, A.B.: Collaborative contrastive learning for cross-domain gaze estimation. Pattern Recogn. 161, 111244 (2025)","journal-title":"Pattern Recogn."},{"key":"2081_CR25","doi-asserted-by":"crossref","unstructured":"Park, S., Zhang, X., Bulling, A., Hilliges, O.: Learning to find eye region landmarks for remote gaze estimation in unconstrained settings (2018)","DOI":"10.1145\/3204493.3204545"},{"issue":"4","key":"2081_CR26","first-page":"31","volume":"24","author":"K Shen","year":"2024","unstructured":"Shen, K., Li, Y., Guo, Z., Gao, J., Wu, Y.: Model-based 3d gaze estimation using a TOF camera. Sensors 24(4), 31 (2024)","journal-title":"Sensors"},{"issue":"6","key":"2081_CR27","doi-asserted-by":"crossref","first-page":"174","DOI":"10.3390\/app6060174","volume":"6","author":"J Wang","year":"2016","unstructured":"Wang, J., Zhang, G., Shi, J.: 2D Gaze estimation based on pupil-glint vector using an artificial neural network. Appl. Sci. 6(6), 174\u2013174 (2016)","journal-title":"Appl. Sci."},{"issue":"6","key":"2081_CR28","doi-asserted-by":"crossref","first-page":"1124","DOI":"10.1109\/TBME.2005.863952","volume":"53","author":"ED Guestrin","year":"2006","unstructured":"Guestrin, E.D., Eizenman, M.: General theory of remote gaze estimation using the pupil center and corneal reflections. IEEE Trans. Biomed. Eng. 53(6), 1124\u20131133 (2006)","journal-title":"IEEE Trans. Biomed. Eng."},{"issue":"4","key":"2081_CR29","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/S0262-8856(99)00053-0","volume":"18","author":"CH Morimoto","year":"2007","unstructured":"Morimoto, C.H., Koons, D., Amir, A., Flickner, M.: Pupil detection and tracking using multiple light sources. Image Vis. Comput. 18(4), 331\u2013335 (2007)","journal-title":"Image Vis. Comput."},{"key":"2081_CR30","first-page":"3341","volume-title":"Proceedings of the international conference on pattern recognition (ICPR)","author":"Y Cheng","year":"2022","unstructured":"Cheng, Y., Lu, F.: Gaze estimation using transformer. In: Proceedings of the international conference on pattern recognition (ICPR), pp. 3341\u20133347. IEEE (2022)"},{"key":"2081_CR31","unstructured":"Ji, J.C.Q.: 3d gaze estimation with a single camera without ir illumination. In: International conference on pattern recognition (2008)"},{"key":"2081_CR32","first-page":"109","volume-title":"International conference on pattern recognition","author":"C Kuang","year":"2022","unstructured":"Kuang, C., Kephart, J.O., Ji, Q.: Towards an accurate 3D deformable eye model for gaze estimation. In: International conference on pattern recognition, pp. 109\u2013123. Springer (2022)"},{"issue":"9","key":"2081_CR33","doi-asserted-by":"crossref","first-page":"237","DOI":"10.3390\/jimaging10090237","volume":"10","author":"C Miron","year":"2024","unstructured":"Miron, C., Ciubotariu, G., Psric, A., Timofte, R.: Efficient end-to-end convolutional architecture for point-of-gaze estimation. J. Imaging 10(9), 237 (2024)","journal-title":"J. Imaging"},{"key":"2081_CR34","first-page":"334","volume-title":"Proceedings of the European conference on computer vision","author":"T Fischer","year":"2018","unstructured":"Fischer, T., Chang, H.J., Demiris, Y.: Rt-gene: Real-time eye gaze estimation in natural environments. In: Proceedings of the European conference on computer vision, pp. 334\u2013352. Springer, Cham (2018)"},{"key":"2081_CR35","doi-asserted-by":"crossref","unstructured":"Funes\u00a0Mora, K.A., Monay, F., Odobez, J.-M.: Eyediap: A database for the development and evaluation of gaze estimation algorithms from rgb and rgb-d cameras. In: Proceedings of the symposium on eye tracking research and applications, pp. 255\u2013258 (2014)","DOI":"10.1145\/2578153.2578190"},{"key":"2081_CR36","first-page":"6912","volume-title":"Procedings of the IEEE\/CVF international conference on computer vision","author":"P Kellnhofer","year":"2019","unstructured":"Kellnhofer, P., Recasens, A., Stent, S., Matusik, W., Torralba, A.: Gaze360: physically unconstrained gaze estimation in the wild. In: Procedings of the IEEE\/CVF international conference on computer vision, pp. 6912\u20136921. IEEE, Geneva (2019)"},{"key":"2081_CR37","unstructured":"Alexey, D.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv: 2010.11929 (2020)"},{"key":"2081_CR38","first-page":"5581","volume-title":"Proceedings of the AAAI conference on Artificial Intelligence","author":"S Wang","year":"2024","unstructured":"Wang, S., Huang, Y.: Suppressing uncertainty in gaze estimation. In: Proceedings of the AAAI conference on Artificial Intelligence, vol. 38, pp. 5581\u20135589. ACM Digital Library, New York (2024)"},{"issue":"1","key":"2081_CR39","first-page":"436","volume":"36","author":"Y Cheng","year":"2021","unstructured":"Cheng, Y., Bao, Y., Lu, F.: Puregaze: purifying gaze feature for generalizable gaze estimation. Proc. AAAI Conf. Artif. Intell. 36(1), 436\u2013443 (2021)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"2081_CR40","doi-asserted-by":"crossref","unstructured":"Liang, Z., Bao, Y., Lu, F.: De-confounded gaze estimation. In: European Conference on Computer Vision (2025)","DOI":"10.1007\/978-3-031-73337-6_13"},{"key":"2081_CR41","doi-asserted-by":"crossref","first-page":"1687","DOI":"10.1109\/LSP.2023.3332569","volume":"30","author":"YEA Guan","year":"2023","unstructured":"Guan, Y.E.A.: End-to-end video gaze estimation via capturing head-face-eye spatial-temporal interaction context. IEEE Signal Process. Lett. 30, 1687\u20131691 (2023)","journal-title":"IEEE Signal Process. Lett."},{"key":"2081_CR42","doi-asserted-by":"crossref","first-page":"9936","DOI":"10.1109\/ICPR48806.2021.9412205","volume-title":"2020 25th International conference on pattern recognition (ICPR)","author":"Y Bao","year":"2021","unstructured":"Bao, Y., Cheng, Y., Liu, Y., Lu, F.: Adaptive feature fusion network for gaze tracking in mobile tablets. In: 2020 25th International conference on pattern recognition (ICPR), pp. 9936\u20139943. IEEE (2021)"},{"key":"2081_CR43","doi-asserted-by":"crossref","unstructured":"Gheini, M., Ren, X., May, J.: Cross-attention is all you need: Adapting pretrained transformers for machine translation. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.132"},{"key":"2081_CR44","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"B Liu","year":"2024","unstructured":"Liu, B., Wang, C., Cao, T., Jia, K., Huang, J.: Towards understanding cross and self-attention in stable diffusion for text-guided image editing. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. IEEE, Geneva (2024)"},{"key":"2081_CR45","first-page":"13608","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern Recognition","author":"Y Cui","year":"2022","unstructured":"Cui, Y., Jiang, C., Wang, L., Wu, G.: Mixformer: end-to-end tracking with iterative mixed attention. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern Recognition, pp. 13608\u201313618. IEEE, Geneva (2022)"},{"issue":"6","key":"2081_CR46","first-page":"18","volume":"46","author":"Y Cui","year":"2024","unstructured":"Cui, Y., Jiang, C., Wu, G., Wang, L.: Mixformer: end-to-end tracking with iterative mixed attention. IEEE Trans. Pattern Anal. Mach. Intell. 46(6), 18 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2081_CR47","first-page":"341","volume-title":"Proceedings of the European conference on computer vision","author":"B Ye","year":"2022","unstructured":"Ye, B., Chang, H., Ma, B., Shan, S., Chen, X.: Joint feature learning and relation modeling for tracking: a one-stream framework. In: Proceedings of the European conference on computer vision, pp. 341\u2013357. Springer (2022)"},{"key":"2081_CR48","first-page":"152","volume-title":"Proceedings of the European conference on computer vision","author":"J Guo","year":"2020","unstructured":"Guo, J., Zhu, X., Yang, Y., Yang, F., Lei, Z., Li, S.Z.: Towards fast, accurate and stable 3D dense face alignment. In: Proceedings of the European conference on computer vision, pp. 152\u2013168. Springer (2020)"},{"key":"2081_CR49","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1007\/978-3-030-58558-7_22","volume-title":"Computer Vision-ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part V 16,","author":"X Zhang","year":"2020","unstructured":"Zhang, X., Park, S., Beeler, T., Bradley, D., Tang, S., Hilliges, O.: Eth-xgaze: a large scale dataset for gaze estimation under extreme head pose and gaze variation. In: Computer Vision-ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part V 16, pp. 365\u2013381. Springer, Cham (2020)"},{"key":"2081_CR50","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization 3rd international conference on learning representations. In: ICLR 2015-Conference Track Proceedings, Vol. 1 (2015)"},{"key":"2081_CR51","volume-title":"IEEE Trans. Cybern.","author":"GEA Huang","year":"2023","unstructured":"Huang, G.E.A.: Gaze estimation by attention-induced hierarchical variational auto-encoder. In: IEEE Trans. Cybern. IEEE, Geneva (2023)"},{"key":"2081_CR52","doi-asserted-by":"crossref","first-page":"107150","DOI":"10.1109\/ACCESS.2023.3317013","volume":"11","author":"GEA Ren","year":"2023","unstructured":"Ren, G.E.A.: Gaze estimation based on attention mechanism combined with temporal network. IEEE Access. 11, 107150\u20131007159 (2023)","journal-title":"IEEE Access."},{"key":"2081_CR53","doi-asserted-by":"crossref","unstructured":"Xia, C.e.a.: Cta-net: A gaze estimation network based on dual feature aggregation and attention cross fusion. ComSIS. pp 20\u201320 (2024)","DOI":"10.21203\/rs.3.rs-3377315\/v1"},{"issue":"1","key":"2081_CR54","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1109\/TPAMI.2017.2778103","volume":"41","author":"X Zhang","year":"2017","unstructured":"Zhang, X., Sugano, Y., Fritz, M., Bulling, A.: Mpiigaze: real-world dataset and deep appearance-based gaze estimation. IEEE Trans. Pattern Anal. Mach. Intell. 41(1), 162\u2013175 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2081_CR55","first-page":"4992","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"OJ Oh","year":"2022","unstructured":"Oh, O.J., Chang, H.J., Choi, S.-I.: Self-attention with convolution and deconvolution for efficient eye gaze estimation from a full face image. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 4992\u20135000. IEEE, Geneva (2022)"},{"key":"2081_CR56","first-page":"248","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"J Deng","year":"2009","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 248\u2013255. Ieee (2009)"},{"key":"2081_CR57","first-page":"16000","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"K He","year":"2022","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 16000\u201316009. IEEE, Geneva (2022)"},{"key":"2081_CR58","first-page":"6729","volume":"38","author":"P Yin","year":"2024","unstructured":"Yin, P., Zeng, G., Wang, J., Xie, D.: Clip-gaze: towards general gaze estimation via visual-linguistic model. Proc. AAAI Conf. Artif. Intell. 38, 6729\u20136737 (2024)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"2081_CR59","first-page":"3027","volume":"37","author":"M Xu","year":"2023","unstructured":"Xu, M., Wang, H., Lu, F.: Learning a generalized gaze estimator from gaze-consistent feature. Proc. AAAI Conf. Artif. Intell. 37, 3027\u20133035 (2023)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"2081_CR60","first-page":"219","volume-title":"De-confounded gaze estimation","author":"Z Liang","year":"2024","unstructured":"Liang, Z., Bao, Y., Lu, F.: European conference on computer vision. In: De-confounded gaze estimation, pp. 219\u2013235. Springer, Cham (2024)"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02081-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-02081-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02081-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T08:43:49Z","timestamp":1774428229000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-02081-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,4]]},"references-count":60,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2081"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-02081-0","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,4]]},"assertion":[{"value":"1 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"15"}}