{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T14:59:48Z","timestamp":1777042788141,"version":"3.51.4"},"reference-count":45,"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":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition Letters"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.patrec.2026.01.013","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T00:21:43Z","timestamp":1768350103000},"page":"109-116","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":4,"special_numbering":"C","title":["DMAGaze : Gaze estimation using feature disentanglement and multi-scale attention"],"prefix":"10.1016","volume":"201","author":[{"given":"Haohan","family":"Chen","sequence":"first","affiliation":[]},{"given":"Hongjia","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Shiyong","family":"Lan","sequence":"additional","affiliation":[]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yixin","family":"Qiao","sequence":"additional","affiliation":[]},{"given":"Yao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Guonan","family":"Deng","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"8","key":"10.1016\/j.patrec.2026.01.013_bib0001","doi-asserted-by":"crossref","first-page":"1913","DOI":"10.1109\/TPAMI.2019.2905607","article-title":"Inferring salient objects from human fixations","volume":"42","author":"Wang","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"10.1016\/j.patrec.2026.01.013_bib0002","doi-asserted-by":"crossref","first-page":"2368","DOI":"10.1109\/TIP.2017.2787612","article-title":"Deep visual attention prediction","volume":"27","author":"Wang","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patrec.2026.01.013_bib0003","series-title":"Proc. 2017 IEEE Virtual Reality","first-page":"413","article-title":"Gaze estimation based on head movements in virtual reality applications using deep learning","author":"Soccini","year":"2017"},{"key":"10.1016\/j.patrec.2026.01.013_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108117","article-title":"A review of driver gaze estimation and application in gaze behavior understanding","volume":"133","author":"Sharma","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.patrec.2026.01.013_bib0005","first-page":"1","article-title":"Toward an attentive robotic architecture: learning-based mutual gaze estimation in human-robot interaction","volume":"9","author":"Lombardi","year":"2022","journal-title":"Front. Rob. AI"},{"issue":"7","key":"10.1016\/j.patrec.2026.01.013_bib0006","doi-asserted-by":"crossref","first-page":"6504","DOI":"10.1109\/TCYB.2022.3165063","article-title":"Appearance-based gaze estimation for ASD diagnosis","volume":"52","author":"Li","year":"2022","journal-title":"IEEE Trans. Cybern."},{"issue":"12","key":"10.1016\/j.patrec.2026.01.013_bib0007","article-title":"Robust and accurate pupil detection for head-mounted eye tracking","volume":"93","author":"Wan","year":"2021","journal-title":"Comput. Electr. Eng."},{"key":"10.1016\/j.patrec.2026.01.013_bib0008","series-title":"Proc. IEEE CVPR","first-page":"4511","article-title":"Appearance-based gaze estimation in the wild","author":"Zhang","year":"2015"},{"key":"10.1016\/j.patrec.2026.01.013_bib0009","series-title":"Proc. IEEE\/CVF CVPR","first-page":"7314","article-title":"Unsupervised representation learning for gaze estimation","author":"Yu","year":"2020"},{"key":"10.1016\/j.patrec.2026.01.013_bib0010","series-title":"Proc. IEEE CVPR Workshops","first-page":"51","article-title":"It\u2019s written all over your face: full-face appearance-based gaze estimation","author":"Zhang","year":"2017"},{"key":"10.1016\/j.patrec.2026.01.013_bib0011","series-title":"Proc. 26th Int. Conf. Pattern Recognit.","first-page":"3341","article-title":"Gaze estimation using transformer","author":"Cheng","year":"2022"},{"key":"10.1016\/j.patrec.2026.01.013_bib0012","series-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","first-page":"6912","article-title":"Gaze360: physically unconstrained gaze estimation in the wild","author":"Kellnhofer","year":"2019"},{"key":"10.1016\/j.patrec.2026.01.013_bib0013","series-title":"Proc. 18th IEEE Int. Conf. Autom. Face Gesture Recognit.","first-page":"500","article-title":"CrossGaze: a strong method for 3D gaze estimation in the wild","author":"C\u0103trun\u0103","year":"2024"},{"key":"10.1016\/j.patrec.2026.01.013_bib0014","series-title":"Proc. Asian Conf. Comput. Vis.","first-page":"309","article-title":"Appearance-based gaze estimation using dilated-convolutions","author":"Chen","year":"2018"},{"key":"10.1016\/j.patrec.2026.01.013_bib0015","first-page":"10623","article-title":"A coarse-to-fine adaptive network for appearance-based gaze estimation","volume":"34","author":"Cheng","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.patrec.2026.01.013_bib0016","first-page":"6729","article-title":"CLIP-Gaze: towards general gaze estimation via visual-linguistic model","volume":"38","author":"Yin","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.patrec.2026.01.013_bib0017","unstructured":"J. Wang, H. Ruan, M. Wang, C. Zhang, H. Li, J. Zhou, GazeCLIP: towards enhancing gaze estimation via text guidance, (2023). arXiv preprint arXiv: 2401.00260."},{"key":"10.1016\/j.patrec.2026.01.013_bib0018","series-title":"Proc. Int. Conf. Mach. Learn.","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patrec.2026.01.013_bib0019","series-title":"Proc. IEEE\/CVF CVPR","first-page":"13508","article-title":"Enhancing 3D gaze estimation in the wild using weak supervision with gaze following labels","author":"Vuillecard","year":"2025"},{"key":"10.1016\/j.patrec.2026.01.013_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.116894","article-title":"Eye gaze estimation: a survey on deep learning-based approaches","volume":"199","author":"Pathirana","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patrec.2026.01.013_bib0021","unstructured":"S. Wang, Y. Huang, J. Xie, F. Chen, Z. Wang, Cross-dataset gaze estimation by evidential inter-intra fusion, (2024). arXiv preprint arXiv: 2409.04766."},{"key":"10.1016\/j.patrec.2026.01.013_bib0022","doi-asserted-by":"crossref","first-page":"3508","DOI":"10.1109\/TIP.2024.3404241","article-title":"INSURE: an information theory inspired disentanglement and purification model for domain generalization","volume":"33","author":"Yu","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patrec.2026.01.013_bib0023","series-title":"Proc. 29th Int. Conf. Mechatron. Mach. Vis. Pract.","first-page":"1","article-title":"Gaze estimation with multi-scale attention-based convolutional neural networks","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patrec.2026.01.013_bib0024","series-title":"Proc. Eur. Conf. Comput. Vis.","first-page":"3","article-title":"CBAM: convolutional block attention module","author":"Woo","year":"2018"},{"key":"10.1016\/j.patrec.2026.01.013_bib0025","series-title":"Proc. IEEE CVPR","first-page":"7794","article-title":"Non-local neural networks","author":"Wang","year":"2018"},{"key":"10.1016\/j.patrec.2026.01.013_bib0026","first-page":"436","article-title":"PureGaze: purifying gaze feature for generalizable gaze estimation","volume":"36","author":"Cheng","year":"2022","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.patrec.2026.01.013_bib0027","first-page":"1","article-title":"Multibit attention fusion for gaze estimation using 12-Bit RAW data from CMOS sensors","volume":"74","author":"Tian","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.patrec.2026.01.013_bib0028","series-title":"Proc. Eur. Conf. Comput. Vis.","first-page":"334","article-title":"RT-GENE: realtime eye gaze estimation in natural environments","author":"Fischer","year":"2018"},{"key":"10.1016\/j.patrec.2026.01.013_bib0029","series-title":"Proc. IEEE CVPR","first-page":"2176","article-title":"Eye tracking for everyone","author":"Krafka","year":"2016"},{"key":"10.1016\/j.patrec.2026.01.013_bib0030","series-title":"Proc. 8th Int. Conf. Front. Signal Process.","first-page":"98","article-title":"L2CS-Net: fine-grained gaze estimation in unconstrained environments","author":"Abdelrahman","year":"2023"},{"key":"10.1016\/j.patrec.2026.01.013_bib0031","series-title":"2022 2nd Int. Conf. Adv. Res. Comput.","first-page":"206","article-title":"Single-user 2D gaze estimation in retail environment using deep learning","author":"Pathirana","year":"2022"},{"key":"10.1016\/j.patrec.2026.01.013_bib0032","doi-asserted-by":"crossref","first-page":"64904","DOI":"10.1109\/ACCESS.2022.3183357","article-title":"Customer gaze estimation in retail using deep learning","volume":"10","author":"Senarath","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.patrec.2026.01.013_bib0033","series-title":"Companion Proc. of the 27th Int. Conf. on Intell. User Interfaces","first-page":"38-41","article-title":"Distraction detection in automotive environment using appearance-based gaze estimation","author":"L. R. D","year":"2022"},{"key":"10.1016\/j.patrec.2026.01.013_bib0034","series-title":"Companion Proc. of the 27th Int. Conf. on Intell. User Interfaces","first-page":"81-84","article-title":"PARKS-Gaze - a precision-focused gaze estimation dataset in the wild under extreme head poses","author":"L. R. D","year":"2022"},{"issue":"12","key":"10.1016\/j.patrec.2026.01.013_bib0035","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."},{"key":"10.1016\/j.patrec.2026.01.013_bib0036","unstructured":"I. Loshchilov, Decoupled weight decay regularization, (2017). arXiv preprint arXiv: 1711.05101."},{"key":"10.1016\/j.patrec.2026.01.013_bib0037","series-title":"Proc. IEEE\/CVF CVPR","first-page":"3143","article-title":"Appearance-based gaze estimation using attention and difference mechanism","author":"Murthy","year":"2021"},{"key":"10.1016\/j.patrec.2026.01.013_bib0038","series-title":"Proc. IEEE\/CVF CVPR","first-page":"2669","article-title":"GazeCaps: gaze estimation with self-attention-routed capsules","author":"Wang","year":"2023"},{"key":"10.1016\/j.patrec.2026.01.013_bib0039","doi-asserted-by":"crossref","unstructured":"Z. Cheng, Y. Wang, G. Xia, EM-Net: gaze estimation with expectation maximization algorithm, (2024). arXiv preprint arXiv: 2412.08074.","DOI":"10.2139\/ssrn.4909428"},{"key":"10.1016\/j.patrec.2026.01.013_bib0040","series-title":"Proc. Int. Conf. Pattern Recognit.","first-page":"77","article-title":"Merging multiple datasets for improved appearance-based gaze estimation","author":"Wu","year":"2024"},{"key":"10.1016\/j.patrec.2026.01.013_bib0041","unstructured":"Y. Liu, Z. Shao, N. Hoffmann, Global attention mechanism: retain information to enhance channel-spatial interactions, (2021). arXiv preprint arXiv: 2112.05561."},{"key":"10.1016\/j.patrec.2026.01.013_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129866","article-title":"SCSA: exploring the synergistic effects between spatial and channel attention","volume":"634","author":"Si","year":"2025","journal-title":"Neurocomput."},{"key":"10.1016\/j.patrec.2026.01.013_bib0043","series-title":"Proc. ECCV 2024","article-title":"Agent attention: on the integration of softmax and linear attention","volume":"15108","author":"Han","year":"2025"},{"key":"10.1016\/j.patrec.2026.01.013_bib0044","unstructured":"Y. Bengio, N. L\u00e9onard, A. Courville, Estimating or propagating gradients through stochastic neurons for conditional computation, (2013). arXiv preprint arXiv: 1308.3432."},{"key":"10.1016\/j.patrec.2026.01.013_bib0045","series-title":"Proc. Int. Conf. Mach. Learn.","first-page":"3519","article-title":"Similarity of neural network representations revisited","author":"Kornblith","year":"2019"}],"container-title":["Pattern Recognition Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526000218?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526000218?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T02:03:28Z","timestamp":1770689008000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167865526000218"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":45,"alternative-id":["S0167865526000218"],"URL":"https:\/\/doi.org\/10.1016\/j.patrec.2026.01.013","relation":{},"ISSN":["0167-8655"],"issn-type":[{"value":"0167-8655","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DMAGaze : Gaze estimation using feature disentanglement and multi-scale attention","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition Letters","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patrec.2026.01.013","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}