{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T10:07:53Z","timestamp":1776161273909,"version":"3.50.1"},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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","award":["42401533"],"award-info":[{"award-number":["42401533"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M741702"],"award-info":[{"award-number":["2023M741702"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.jvcir.2026.104776","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T15:59:54Z","timestamp":1773676794000},"page":"104776","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Perceptually diverse visual saliency prediction with global context attention"],"prefix":"10.1016","volume":"117","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9532-4272","authenticated-orcid":false,"given":"Sheng","family":"Jin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufan","family":"Ge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3572-5770","authenticated-orcid":false,"given":"Jiayi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0369-7571","authenticated-orcid":false,"given":"Yifan","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2026.104776_b1","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.patrec.2025.04.027","article-title":"Pyramid-structured multi-scale transformer for efficient semi-supervised video object segmentation with adaptive fusion","volume":"194","author":"Zhang","year":"2025","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.jvcir.2026.104776_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2024.104271","article-title":"Cross-stage feature fusion and efficient self-attention for salient object detection","volume":"104","author":"Xia","year":"2024","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104776_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2025.104522","article-title":"SFEN: Salient feature enhancement network for salient object detection","volume":"111","author":"Du","year":"2025","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104776_b4","article-title":"ORSI salient object detection via progressive interaction and saliency-guided enhancement","volume":"23","author":"Zhang","year":"2025","journal-title":"IEEE Geosci. Remote. Sens. Lett."},{"key":"10.1016\/j.jvcir.2026.104776_b5","article-title":"SCAFNet: A semantic compensated adaptive fusion network for remote sensing images change detection","volume":"23","author":"Zhang","year":"2026","journal-title":"IEEE Geosci. Remote. Sens. Lett."},{"key":"10.1016\/j.jvcir.2026.104776_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.119068","article-title":"\u201cFocusing on the right regions\u201d\u2014Guided saliency prediction for visual SLAM","volume":"213","author":"Jin","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.jvcir.2026.104776_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.105902","article-title":"Loop closure detection with patch-level local features and visual saliency prediction","volume":"120","author":"Jin","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"11","key":"10.1016\/j.jvcir.2026.104776_b8","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1109\/34.730558","article-title":"A model of saliency-based visual attention for rapid scene analysis","volume":"20","author":"Itti","year":"1998","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jvcir.2026.104776_b9","article-title":"Graph-based visual saliency","volume":"19","author":"Harel","year":"2006","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"7","key":"10.1016\/j.jvcir.2026.104776_b10","doi-asserted-by":"crossref","first-page":"3264","DOI":"10.1109\/TIP.2018.2817047","article-title":"A deep spatial contextual long-term recurrent convolutional network for saliency detection","volume":"27","author":"Liu","year":"2018","journal-title":"IEEE Trans. Image Process."},{"issue":"9","key":"10.1016\/j.jvcir.2026.104776_b11","doi-asserted-by":"crossref","first-page":"4446","DOI":"10.1109\/TIP.2017.2710620","article-title":"Deepfix: A fully convolutional neural network for predicting human eye fixations","volume":"26","author":"Kruthiventi","year":"2017","journal-title":"IEEE Trans. Image Process."},{"issue":"5","key":"10.1016\/j.jvcir.2026.104776_b12","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.jvcir.2026.104776_b13","doi-asserted-by":"crossref","unstructured":"Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich, Going deeper with convolutions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10.1016\/j.jvcir.2026.104776_b14","doi-asserted-by":"crossref","unstructured":"Nian Liu, Junwei Han, Dingwen Zhang, Shifeng Wen, Tianming Liu, Predicting eye fixations using convolutional neural networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 362\u2013370.","DOI":"10.1109\/CVPR.2015.7298633"},{"key":"10.1016\/j.jvcir.2026.104776_b15","doi-asserted-by":"crossref","unstructured":"Xun Huang, Chengyao Shen, Xavier Boix, Qi Zhao, Salicon: Reducing the semantic gap in saliency prediction by adapting deep neural networks, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 262\u2013270.","DOI":"10.1109\/ICCV.2015.38"},{"key":"10.1016\/j.jvcir.2026.104776_b16","doi-asserted-by":"crossref","unstructured":"Shaojing Fan, Zhiqi Shen, Ming Jiang, Bryan L Koenig, Juan Xu, Mohan S Kankanhalli, Qi Zhao, Emotional attention: A study of image sentiment and visual attention, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7521\u20137531.","DOI":"10.1109\/CVPR.2018.00785"},{"key":"10.1016\/j.jvcir.2026.104776_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2020.103887","article-title":"Eml-net: An expandable multi-layer network for saliency prediction","volume":"95","author":"Jia","year":"2020","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.jvcir.2026.104776_b18","series-title":"European Conference on Computer Vision","first-page":"419","article-title":"Unified image and video saliency modeling","author":"Droste","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104776_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2021.104149","article-title":"SalED: Saliency prediction with a pithy encoder-decoder architecture sensing local and global information","volume":"109","author":"Wang","year":"2021","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.jvcir.2026.104776_b20","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/j.neunet.2020.05.004","article-title":"Contextual encoder\u2013decoder network for visual saliency prediction","volume":"129","author":"Kroner","year":"2020","journal-title":"Neural Netw."},{"key":"10.1016\/j.jvcir.2026.104776_b21","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/j.neunet.2020.05.004","article-title":"Contextual encoder\u2013decoder network for visual saliency prediction","volume":"129","author":"Kroner","year":"2020","journal-title":"Neural Netw."},{"key":"10.1016\/j.jvcir.2026.104776_b22","doi-asserted-by":"crossref","unstructured":"Xiaolong Wang, Ross Girshick, Abhinav Gupta, Kaiming He, Non-local neural networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7794\u20137803.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"10.1016\/j.jvcir.2026.104776_b23","series-title":"European Conference on Computer Vision","first-page":"52","article-title":"Tensor low-rank reconstruction for semantic segmentation","author":"Chen","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104776_b24","doi-asserted-by":"crossref","unstructured":"Eleonora Vig, Michael Dorr, David Cox, Large-scale optimization of hierarchical features for saliency prediction in natural images, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 2798\u20132805.","DOI":"10.1109\/CVPR.2014.358"},{"key":"10.1016\/j.jvcir.2026.104776_b25","doi-asserted-by":"crossref","unstructured":"Matthias Kummerer, Thomas SA Wallis, Leon A Gatys, Matthias Bethge, Understanding low-and high-level contributions to fixation prediction, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 4789\u20134798.","DOI":"10.1109\/ICCV.2017.513"},{"key":"10.1016\/j.jvcir.2026.104776_b26","doi-asserted-by":"crossref","unstructured":"Akis Linardos, Matthias K\u00fcmmerer, Ori Press, Matthias Bethge, DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling, in: Proceedings of the Ieee\/Cvf International Conference on Computer Vision, 2021, pp. 12919\u201312928.","DOI":"10.1109\/ICCV48922.2021.01268"},{"issue":"10","key":"10.1016\/j.jvcir.2026.104776_b27","doi-asserted-by":"crossref","first-page":"5142","DOI":"10.1109\/TIP.2018.2851672","article-title":"Predicting human eye fixations via an lstm-based saliency attentive model","volume":"27","author":"Cornia","year":"2018","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"10.1016\/j.jvcir.2026.104776_b28","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1007\/s11263-020-01371-6","article-title":"DeepVS2. 0: A saliency-structured deep learning method for predicting dynamic visual attention","volume":"129","author":"Jiang","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.jvcir.2026.104776_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.image.2021.116186","article-title":"Visual attention prediction for autism spectrum disorder with hierarchical semantic fusion","volume":"93","author":"Fang","year":"2021","journal-title":"Signal Process., Image Commun."},{"key":"10.1016\/j.jvcir.2026.104776_b30","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1016\/j.neucom.2022.04.080","article-title":"TranSalNet: Towards perceptually relevant visual saliency prediction","volume":"494","author":"Lou","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.jvcir.2026.104776_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111840","article-title":"Video saliency prediction via single feature enhancement and temporal recurrence","volume":"160","author":"Zhang","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.jvcir.2026.104776_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109806","article-title":"An efficient perceptual video compression scheme based on deep learning-assisted video saliency and just noticeable distortion","volume":"141","author":"Zhang","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.jvcir.2026.104776_b33","series-title":"2025 IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"1597","article-title":"Sum: Saliency unification through mamba for visual attention modeling","author":"Hosseini","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104776_b34","doi-asserted-by":"crossref","first-page":"2287","DOI":"10.1109\/TIP.2019.2945857","article-title":"How is gaze influenced by image transformations? dataset and model","volume":"29","author":"Che","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2026.104776_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128564","article-title":"Spatiotemporal dual-branch feature-guided fusion network for driver attention prediction","volume":"292","author":"Zhang","year":"2025","journal-title":"Expert Syst. Appl."},{"issue":"1","key":"10.1016\/j.jvcir.2026.104776_b36","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1109\/TCDS.2023.3274179","article-title":"Salda: DeepConvNet greets attention for visual saliency prediction","volume":"16","author":"Tang","year":"2023","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"10.1016\/j.jvcir.2026.104776_b37","unstructured":"Fisher Yu, Vladlen Koltun, Thomas Funkhouser, Dilated residual networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 472\u2013480."},{"issue":"3","key":"10.1016\/j.jvcir.2026.104776_b38","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1137\/07070111X","article-title":"Tensor decompositions and applications","volume":"51","author":"Kolda","year":"2009","journal-title":"SIAM Rev."},{"key":"10.1016\/j.jvcir.2026.104776_b39","doi-asserted-by":"crossref","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Delving deep into rectifiers: Surpassing human-level performance on imagenet classification, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1026\u20131034.","DOI":"10.1109\/ICCV.2015.123"},{"key":"10.1016\/j.jvcir.2026.104776_b40","doi-asserted-by":"crossref","unstructured":"Bahar Aydemir, Ludo Hoffstetter, Tong Zhang, Mathieu Salzmann, Sabine S\u00fcsstrunk, Tempsal-uncovering temporal information for deep saliency prediction, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 6461\u20136470.","DOI":"10.1109\/CVPR52729.2023.00625"},{"key":"10.1016\/j.jvcir.2026.104776_b41","series-title":"Cat2000: A large scale fixation dataset for boosting saliency research","author":"Borji","year":"2015"},{"key":"10.1016\/j.jvcir.2026.104776_b42","series-title":"2009 IEEE 12th International Conference on Computer Vision","first-page":"2106","article-title":"Learning to predict where humans look","author":"Judd","year":"2009"},{"issue":"1","key":"10.1016\/j.jvcir.2026.104776_b43","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1167\/14.1.28","article-title":"Predicting human gaze beyond pixels","volume":"14","author":"Xu","year":"2014","journal-title":"J. Vis."},{"key":"10.1016\/j.jvcir.2026.104776_b44","doi-asserted-by":"crossref","unstructured":"Yue Jiang, Luis A Leiva, Hamed Rezazadegan Tavakoli, Paul RB Houssel, Julia Kylm\u00e4l\u00e4, Antti Oulasvirta, Ueyes: Understanding visual saliency across user interface types, in: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, 2023, pp. 1\u201321.","DOI":"10.1145\/3544548.3581096"},{"key":"10.1016\/j.jvcir.2026.104776_b45","doi-asserted-by":"crossref","unstructured":"Lai Jiang, Yifei Li, Shengxi Li, Mai Xu, Se Lei, Yichen Guo, Bo Huang, Does text attract attention on e-commerce images: A novel saliency prediction dataset and method, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 2088\u20132097.","DOI":"10.1109\/CVPR52688.2022.00213"},{"key":"10.1016\/j.jvcir.2026.104776_b46","series-title":"2020 25th International Conference on Pattern Recognition","first-page":"9054","article-title":"FastSal: A computationally efficient network for visual saliency prediction","author":"Hu","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104776_b47","first-page":"106346","article-title":"Uniar: A unified model for predicting human attention and responses on visual content","volume":"37","author":"Li","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104776_b48","series-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"10241","article-title":"Tidying deep saliency prediction architectures","author":"Reddy","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104776_b49","doi-asserted-by":"crossref","unstructured":"Camilo Fosco, Vincent Casser, Amish Kumar Bedi, Peter O\u2019Donovan, Aaron Hertzmann, Zoya Bylinskii, Predicting visual importance across graphic design types, in: Proceedings of the 33rd Annual ACM Symposium on User Interface Software and Technology, 2020, pp. 249\u2013260.","DOI":"10.1145\/3379337.3415825"},{"key":"10.1016\/j.jvcir.2026.104776_b50","doi-asserted-by":"crossref","unstructured":"Lai Jiang, Yifei Li, Shengxi Li, Mai Xu, Se Lei, Yichen Guo, Bo Huang, Does text attract attention on e-commerce images: A novel saliency prediction dataset and method, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 2088\u20132097.","DOI":"10.1109\/CVPR52688.2022.00213"},{"issue":"1","key":"10.1016\/j.jvcir.2026.104776_b51","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1109\/TCDS.2023.3274179","article-title":"Salda: DeepConvNet greets attention for visual saliency prediction","volume":"16","author":"Tang","year":"2023","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"10.1016\/j.jvcir.2026.104776_b52","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.111279","article-title":"Global semantic-guided network for saliency prediction","volume":"284","author":"Xie","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.jvcir.2026.104776_b53","doi-asserted-by":"crossref","first-page":"2192","DOI":"10.1109\/TMM.2021.3077767","article-title":"CCAFNet: Crossflow and cross-scale adaptive fusion network for detecting salient objects in RGB-D images","volume":"24","author":"Zhou","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.jvcir.2026.104776_b54","doi-asserted-by":"crossref","first-page":"1329","DOI":"10.1109\/TIP.2023.3242775","article-title":"LSNet: Lightweight spatial boosting network for detecting salient objects in RGB-thermal images","volume":"32","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2026.104776_b55","doi-asserted-by":"crossref","first-page":"3027","DOI":"10.1109\/TIP.2023.3275538","article-title":"WaveNet: Wavelet network with knowledge distillation for RGB-T salient object detection","volume":"32","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Image Process."},{"issue":"3","key":"10.1016\/j.jvcir.2026.104776_b56","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1109\/TCSVT.2021.3077058","article-title":"ECFFNet: Effective and consistent feature fusion network for RGB-t salient object detection","volume":"32","author":"Zhou","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"8","key":"10.1016\/j.jvcir.2026.104776_b57","doi-asserted-by":"crossref","first-page":"4140","DOI":"10.1109\/TCSI.2024.3521933","article-title":"Knowledge distillation and contrastive learning for detecting visible-infrared transmission lines using separated stagger registration network","volume":"72","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Circuits Syst. I. Regul. Pap."},{"issue":"7","key":"10.1016\/j.jvcir.2026.104776_b58","doi-asserted-by":"crossref","first-page":"9276","DOI":"10.1109\/JIOT.2024.3506624","article-title":"Hybrid knowledge distillation for RGB-T crowd density estimation in smart surveillance systems","volume":"12","author":"Zhou","year":"2024","journal-title":"IEEE Internet Things J."}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326000714?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326000714?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T09:08:22Z","timestamp":1776157702000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320326000714"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":58,"alternative-id":["S1047320326000714"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104776","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Perceptually diverse visual saliency prediction with global context attention","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104776","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104776"}}