{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T18:30:15Z","timestamp":1769625015421,"version":"3.49.0"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:00:00Z","timestamp":1768521600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:00:00Z","timestamp":1768521600000},"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":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s11432-024-4744-5","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T04:02:47Z","timestamp":1769486567000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Weakly supervised visual-auditory fixation prediction with multigranularity perception"],"prefix":"10.1007","volume":"69","author":[{"given":"Guotao","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenglizhao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deng-Ping","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aimin","family":"Hao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinping","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,16]]},"reference":[{"key":"4744_CR1","doi-asserted-by":"publisher","first-page":"7696","DOI":"10.1109\/TCSVT.2023.3278410","volume":"33","author":"X Zhou","year":"2023","unstructured":"Zhou X, Wu S, Shi R, et al. Transformer-based multi-scale feature integration network for video saliency prediction. IEEE Trans Circuits Syst Video Technol, 2023, 33: 7696\u20137707","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"4744_CR2","volume-title":"Proceedings of CVPR","author":"J Xiong","year":"2023","unstructured":"Xiong J, Wang G, Zhang P, et al. Casp-net: rethinking video saliency prediction from an audio-visual consistency perceptual perspective. In: Proceedings of CVPR, 2023"},{"key":"4744_CR3","volume-title":"Proceedings of ICCV","author":"H Li","year":"2019","unstructured":"Li H, Chen G, Li G, et al. Motion guided attention for video salient object detection. In: Proceedings of ICCV, 2019"},{"key":"4744_CR4","doi-asserted-by":"publisher","first-page":"3156","DOI":"10.1109\/TIP.2017.2670143","volume":"26","author":"C Chen","year":"2017","unstructured":"Chen C, Li S, Wang Y, et al. Video saliency detection via spatial-temporal fusion and low-rank coherency diffusion. IEEE Trans Image Process, 2017, 26: 3156\u20133170","journal-title":"IEEE Trans Image Process"},{"key":"4744_CR5","doi-asserted-by":"publisher","first-page":"1090","DOI":"10.1109\/TIP.2019.2934350","volume":"29","author":"C Chen","year":"2020","unstructured":"Chen C, Wang G, Peng C, et al. Improved robust video saliency detection based on long-term spatial-temporal information. IEEE Trans Image Process, 2020, 29: 1090\u20131100","journal-title":"IEEE Trans Image Process"},{"key":"4744_CR6","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1109\/TCYB.2014.2356200","volume":"45","author":"M Jian","year":"2015","unstructured":"Jian M, Lam K M, Dong J, et al. Visual-patch-attention-aware saliency detection. IEEE Trans Cybern, 2015, 45: 1575\u20131586","journal-title":"IEEE Trans Cybern"},{"key":"4744_CR7","first-page":"5572","volume-title":"Proceedings of MM","author":"S Deng","year":"2023","unstructured":"Deng S, Zhuo W, Xie J, et al. QA-CLIMS: question-answer cross language image matching for weakly supervised semantic segmentation. In: Proceedings of MM, 2023. 5572\u20135583"},{"key":"4744_CR8","volume-title":"Proceedings of ICASSP","author":"M Qiao","year":"2024","unstructured":"Qiao M, Xu M, Wen S, et al. Saliency prediction of sports videos: a large-scale database and a self-adaptive approach. In: Proceedings of ICASSP, 2024"},{"key":"4744_CR9","volume-title":"Proceedings of CVPR","author":"J Xiong","year":"2024","unstructured":"Xiong J, Zhang P, You T, et al. Diffsal: joint audio and video learning for diffusion saliency prediction. In: Proceedings of CVPR, 2024"},{"key":"4744_CR10","doi-asserted-by":"publisher","first-page":"3216","DOI":"10.1007\/s11263-021-01519-y","volume":"129","author":"G Bellitto","year":"2021","unstructured":"Bellitto G, Proietto Salanitri F, Palazzo S, et al. Hierarchical domain-adapted feature learning for video saliency prediction. Int J Comput Vis, 2021, 129: 3216\u20133232","journal-title":"Int J Comput Vis"},{"key":"4744_CR11","volume-title":"Proceedings of CVPR","author":"J Pan","year":"2016","unstructured":"Pan J, Sayrol E, GiroiNieto X, et al. Shallow and deep convolutional networks for saliency prediction. In: Proceedings of CVPR, 2016"},{"key":"4744_CR12","doi-asserted-by":"publisher","first-page":"5174","DOI":"10.1109\/TPAMI.2024.3367293","volume":"46","author":"W Yang","year":"2024","unstructured":"Yang W, Huang H, Hu Y, et al. Video coding for machines: compact visual representation compression for intelligent collaborative analytics. IEEE Trans Pattern Anal Mach Intell, 2024, 46: 5174\u20135191","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4744_CR13","doi-asserted-by":"publisher","first-page":"1349","DOI":"10.1109\/TCSVT.2022.3210476","volume":"33","author":"Z Jin","year":"2023","unstructured":"Jin Z, Xie J, Wu B, et al. Weakly supervised pedestrian segmentation for person re-identification. IEEE Trans Circuits Syst Video Technol, 2023, 33: 1349\u20131362","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"4744_CR14","volume-title":"Proceedings of NIPS","author":"J Jiang","year":"2024","unstructured":"Jiang J, Chen B, Pan J, et al. Forkmerge: mitigating negative transfer in auxiliary-task learning. In: Proceedings of NIPS, 2024"},{"key":"4744_CR15","volume-title":"Proceedings of CVPR","author":"A Tsiami","year":"2020","unstructured":"Tsiami A, Koutras P, Maragos P. Stavis: spatio-temporal audiovisual saliency network. In: Proceedings of CVPR, 2020"},{"key":"4744_CR16","unstructured":"Tavakoli H, Borji A, Rahtu E, et al. Dave: a deep audio-visual embedding for dynamic saliency prediction. 2019. ArXiv:1905.10693"},{"key":"4744_CR17","doi-asserted-by":"publisher","first-page":"5935","DOI":"10.1109\/TCSVT.2023.3342903","volume":"34","author":"S Wen","year":"2024","unstructured":"Wen S, Yang L, Xu M, et al. Saliency prediction on mobile videos: a fixation mapping-based dataset and a transformer approach. IEEE Trans Circuits Syst Video Technol, 2024, 34: 5935\u20135950","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"4744_CR18","volume-title":"Proceedings of ECCV","author":"Y Tian","year":"2018","unstructured":"Tian Y, Shi J, Li B, et al. Audio-visual event localization in unconstrained videos. In: Proceedings of ECCV, 2018"},{"key":"4744_CR19","volume-title":"Proceedings of CVPR","author":"B Zhou","year":"2016","unstructured":"Zhou B, Khosla A, Lapedriza A, et al. Learning deep features for discriminative localization. In: Proceedings of CVPR, 2016"},{"key":"4744_CR20","volume-title":"Proceedings of CVPR","author":"J Xie","year":"2022","unstructured":"Xie J, Xiang J, Chen J, et al. C2am: contrastive learning of class-agnostic activation map for weakly supervised object localization and semantic segmentation. In: Proceedings of CVPR, 2022"},{"key":"4744_CR21","doi-asserted-by":"publisher","first-page":"3935","DOI":"10.1109\/TCSVT.2023.3236432","volume":"33","author":"J Chen","year":"2023","unstructured":"Chen J, Lu W, Li Y, et al. Adversarial learning of object-aware activation map for weakly-supervised semantic segmentation. IEEE Trans Circuits Syst Video Technol, 2023, 33: 3935\u20133946","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"4744_CR22","volume-title":"Proceedings of WACV","author":"Z Li","year":"2021","unstructured":"Li Z, Wang W, Li Z, et al. Towards visually explaining video understanding networks with perturbation. In: Proceedings of WACV, 2021"},{"key":"4744_CR23","first-page":"132","volume-title":"Proceedings of ICCV","author":"J Xie","year":"2021","unstructured":"Xie J, Luo C, Zhu X, et al. Online refinement of low-level feature based activation map for weakly supervised object localization. In: Proceedings of ICCV, 2021. 132\u2013141"},{"key":"4744_CR24","doi-asserted-by":"publisher","first-page":"9017","DOI":"10.1109\/TIP.2020.3023591","volume":"29","author":"B Wang","year":"2020","unstructured":"Wang B, Liu W, Han G, et al. Learning long-term structural dependencies for video salient object detection. IEEE Trans Image Process, 2020, 29: 9017\u20139031","journal-title":"IEEE Trans Image Process"},{"key":"4744_CR25","doi-asserted-by":"publisher","first-page":"2334","DOI":"10.1109\/TIP.2024.3374634","volume":"33","author":"Y Huang","year":"2024","unstructured":"Huang Y, Wu Q, Zhang Z, et al. Meta clothing status calibration for long-term person re-identification. IEEE Trans Image Process, 2024, 33: 2334\u20132346","journal-title":"IEEE Trans Image Process"},{"key":"4744_CR26","volume-title":"Proceedings of CVPR","author":"G Wang","year":"2021","unstructured":"Wang G, Chen C, Fan D P, et al. From semantic categories to fixations: a novel weakly-supervised visual-auditory saliency detection approach. In: Proceedings of CVPR, 2021"},{"key":"4744_CR27","first-page":"2935","volume":"50","author":"J Sun","year":"2019","unstructured":"Sun J, Han G, Zeng Z, et al. Memristor-based neural network circuit of full-function Pavlov associative memory with time delay and variable learning rate. IEEE Trans Cybern, 2019, 50: 2935\u20132945","journal-title":"IEEE Trans Cybern"},{"key":"4744_CR28","volume-title":"Proceedings of CVPR","author":"Y Zeng","year":"2019","unstructured":"Zeng Y, Zhuge Y, Lu H, et al. Multi-source weak supervision for saliency detection. In: Proceedings of CVPR, 2019"},{"key":"4744_CR29","volume-title":"Proceedings of CVPR","author":"L Wang","year":"2017","unstructured":"Wang L, Lu H, Wang Y, et al. Learning to detect salient objects with image-level supervision. In: Proceedings of CVPR, 2017"},{"key":"4744_CR30","volume-title":"Proceedings of WACV","author":"A Chattopadhay","year":"2018","unstructured":"Chattopadhay A, Sarkar A, Howlader P, et al. Grad-cam++: generalized gradient-based visual explanations for deep convolutional networks. In: Proceedings of WACV, 2018"},{"key":"4744_CR31","volume-title":"Proceedings of CVPR","author":"J Zhang","year":"2020","unstructured":"Zhang J, Yu X, Li A, et al. Weakly-supervised salient object detection via scribble annotations. In: Proceedings of CVPR, 2020"},{"key":"4744_CR32","first-page":"4483","volume-title":"Proceedings of CVPR","author":"J Xie","year":"2022","unstructured":"Xie J, Hou X, Ye K, et al. Clims: cross language image matching for weakly supervised semantic segmentation. In: Proceedings of CVPR, 2022. 4483\u20134492"},{"key":"4744_CR33","volume-title":"Proceedings of ICASSP","author":"H Chen","year":"2020","unstructured":"Chen H, Xie W, Vedaldi A, et al. Vggsound: a large-scale audio-visual dataset. In: Proceedings of ICASSP, 2020"},{"key":"4744_CR34","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TPAMI.2019.2935715","volume":"43","author":"A Borji","year":"2021","unstructured":"Borji A. Saliency prediction in the deep learning era: successes and limitations. IEEE Trans Pattern Anal Mach Intell, 2021, 43: 679\u2013700","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4744_CR35","volume-title":"Proceedings of CVPR","author":"D P Fan","year":"2019","unstructured":"Fan D P, Wang W, Cheng M M, et al. Shifting more attention to video salient object detection. In: Proceedings of CVPR, 2019"},{"key":"4744_CR36","doi-asserted-by":"publisher","first-page":"104955","DOI":"10.1016\/j.imavis.2024.104955","volume":"143","author":"J Xie","year":"2024","unstructured":"Xie J, Liu Z, Li G, et al. Audio-visual saliency prediction with multisensory perception and integration. Image Vision Computing, 2024, 143: 104955","journal-title":"Image Vision Computing"},{"key":"4744_CR37","doi-asserted-by":"publisher","first-page":"109675","DOI":"10.1016\/j.knosys.2022.109675","volume":"256","author":"H Ning","year":"2022","unstructured":"Ning H, Zhao B, Hu Z, et al. Audio-visual collaborative representation learning for dynamic saliency prediction. Knowledge-Based Syst, 2022, 256: 109675","journal-title":"Knowledge-Based Syst"},{"key":"4744_CR38","doi-asserted-by":"publisher","first-page":"6477","DOI":"10.1109\/TKDE.2024.3389668","volume":"36","author":"F Shao","year":"2024","unstructured":"Shao F, Luo Y, Gao F, et al. Knowledge-guided causal intervention for weakly-supervised object localization. IEEE Trans Knowl Data Eng, 2024, 36: 6477\u20136489","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"4744_CR39","volume-title":"Proceedings of ICLR","author":"T Kipf","year":"2017","unstructured":"Kipf T, Welling M. Semi-supervised classification with graph convolutional networks. In: Proceedings of ICLR, 2017"},{"key":"4744_CR40","volume-title":"Proceedings of CVPR SUNw","author":"J Pan","year":"2017","unstructured":"Pan J, Ferrer C, McGuinness K, et al. Salgan: visual saliency prediction with generative adversarial networks. In: Proceedings of CVPR SUNw, 2017"},{"key":"4744_CR41","volume-title":"Proceedings of Visual Communications and Image Processing (VCIP)","author":"X Min","year":"2016","unstructured":"Min X, Zhai G, Hu C, et al. Fixation prediction through multimodal analysis. In: Proceedings of Visual Communications and Image Processing (VCIP), 2016"},{"key":"4744_CR42","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1167\/14.8.5","volume":"14","author":"A Coutrot","year":"2014","unstructured":"Coutrot A, Guyader N. How saliency, faces, and sound influence gaze in dynamic social scenes. J Vision, 2014, 14: 5","journal-title":"J Vision"},{"key":"4744_CR43","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1007\/978-1-4939-3435-5_16","volume-title":"From Human Attention to Computational Attention","author":"A Coutrot","year":"2016","unstructured":"Coutrot A, Guyader N. Multimodal saliency models for videos. In: From Human Attention to Computational Attention. New York: Springer, 2016. 291\u2013304"},{"key":"4744_CR44","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s12559-010-9074-z","volume":"3","author":"P K Mital","year":"2011","unstructured":"Mital P K, Smith T J, Hill R L, et al. Clustering of gaze during dynamic scene viewing is predicted by motion. Cogn Comput, 2011, 3: 5\u201324","journal-title":"Cogn Comput"},{"key":"4744_CR45","volume-title":"Proceedings of ECCV","author":"M Gygli","year":"2014","unstructured":"Gygli M, Grabner H, Riemenschneider H, et al. Creating summaries from user videos. In: Proceedings of ECCV, 2014"},{"key":"4744_CR46","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.image.2015.08.004","volume":"38","author":"P Koutras","year":"2015","unstructured":"Koutras P, Maragos P. A perceptually based spatio-temporal computational framework for visual saliency estimation. Signal Processing-Image Communication, 2015, 38: 15\u201331","journal-title":"Signal Processing-Image Communication"},{"key":"4744_CR47","volume-title":"Proceedings of CVPR","author":"W Wang","year":"2018","unstructured":"Wang W, Shen J, Guo F, et al. Revisiting video saliency: a large-scale benchmark and a new model. In: Proceedings of CVPR, 2018"},{"key":"4744_CR48","doi-asserted-by":"publisher","first-page":"5875","DOI":"10.1109\/TIP.2021.3089943","volume":"30","author":"P T Jiang","year":"2021","unstructured":"Jiang P T, Zhang C B, Hou Q, et al. LayerCAM: exploring hierarchical class activation maps for localization. IEEE Trans Image Process, 2021, 30: 5875\u20135888","journal-title":"IEEE Trans Image Process"},{"key":"4744_CR49","volume-title":"Proceedings of ECCV","author":"X Zhang","year":"2018","unstructured":"Zhang X, Wei Y, Kang G, et al. Self-produced guidance for weakly-supervised object localization. In: Proceedings of ECCV, 2018"},{"key":"4744_CR50","volume-title":"Proceedings of ECCV","author":"L Jiang","year":"2018","unstructured":"Jiang L, Xu M, Liu T, et al. Deepvs: a deep learning based video saliency prediction approach. In: Proceedings of ECCV, 2018"},{"key":"4744_CR51","doi-asserted-by":"publisher","first-page":"111279","DOI":"10.1016\/j.knosys.2023.111279","volume":"284","author":"J Xie","year":"2024","unstructured":"Xie J, Liu Z, Li G, et al. Global semantic-guided network for saliency prediction. Knowledge-Based Syst, 2024, 284: 111279","journal-title":"Knowledge-Based Syst"},{"key":"4744_CR52","doi-asserted-by":"publisher","first-page":"3111","DOI":"10.1109\/TIP.2022.3158064","volume":"31","author":"L Zhou","year":"2022","unstructured":"Zhou L, Zhou T, Khan S, et al. Weakly supervised visual saliency prediction. IEEE Trans Image Process, 2022, 31: 3111\u20133124","journal-title":"IEEE Trans Image Process"},{"key":"4744_CR53","volume-title":"Proceedings of CVPR","author":"S Yasuki","year":"2024","unstructured":"Yasuki S, Taki M. Cam back again: large kernel CNNs from a weakly supervised object localization perspective. In: Proceedings of CVPR, 2024"},{"key":"4744_CR54","first-page":"22910","volume-title":"Proceedings of CVPR","author":"C Huang","year":"2023","unstructured":"Huang C, Tian Y, Kumar A, et al. Egocentric audio-visual object localization. In: Proceedings of CVPR, 2023. 22910\u201322921"},{"key":"4744_CR55","doi-asserted-by":"publisher","first-page":"14175","DOI":"10.1109\/TPAMI.2023.3309621","volume":"45","author":"L Zhu","year":"2023","unstructured":"Zhu L, She Q, Chen Q, et al. Background-aware classification activation map for weakly supervised object localization. IEEE Trans Pattern Anal Mach Intell, 2023, 45: 14175\u201314191","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4744_CR56","volume-title":"Proceedings of CVPRW","author":"H Wang","year":"2020","unstructured":"Wang H, Wang Z, Du M, et al. Score-cam: score-weighted visual explanations for convolutional neural networks. In: Proceedings of CVPRW, 2020"},{"key":"4744_CR57","unstructured":"Omeiza D, Speakman S, Cintas C, et al. Smooth Grad-CAM++: an enhanced inference level visualization technique for deep convolutional neural network models. 2019. ArXiv:1908.01224"},{"key":"4744_CR58","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1007\/s11263-020-01393-0","volume":"129","author":"P Dendorfer","year":"2021","unstructured":"Dendorfer P, Osep A, Milan A, et al. MOTChallenge: a benchmark for single-camera multiple target tracking. Int J Comput Vis, 2021, 129: 845\u2013881","journal-title":"Int J Comput Vis"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4744-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-024-4744-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4744-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T05:03:06Z","timestamp":1769490186000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-024-4744-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,16]]},"references-count":58,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["4744"],"URL":"https:\/\/doi.org\/10.1007\/s11432-024-4744-5","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,16]]},"assertion":[{"value":"28 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 February 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"122101"}}