{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T07:23:59Z","timestamp":1780730639247,"version":"3.54.1"},"reference-count":73,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T00:00:00Z","timestamp":1703808000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T00:00:00Z","timestamp":1703808000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61922009"],"award-info":[{"award-number":["61922009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61902401"],"award-info":[{"award-number":["61902401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61876013"],"award-info":[{"award-number":["61876013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["62250001"],"award-info":[{"award-number":["62250001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["62231002"],"award-info":[{"award-number":["62231002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["62192785"],"award-info":[{"award-number":["62192785"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61972071"],"award-info":[{"award-number":["61972071"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Beijing Natural Science Foundation","award":["JQ20020"],"award-info":[{"award-number":["JQ20020"]}]},{"name":"Beijing Natural Science Foundation","award":["M22005"],"award-info":[{"award-number":["M22005"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1007\/s11263-023-01950-3","type":"journal-article","created":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T10:02:46Z","timestamp":1703844166000},"page":"2003-2025","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Joint Learning of Audio\u2013Visual Saliency Prediction and Sound Source Localization on Multi-face Videos"],"prefix":"10.1007","volume":"132","author":[{"given":"Minglang","family":"Qiao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0277-3301","authenticated-orcid":false,"given":"Mai","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiming","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Borji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,12,29]]},"reference":[{"key":"1950_CR1","doi-asserted-by":"crossref","unstructured":"Alc\u00e1zar, J. L., Caba, F., Mai, L., Perazzi, F., Lee, J. Y., Arbel\u00e1ez, P., & Ghanem, B. (2020). Active speakers in context. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 12465\u201312474).","DOI":"10.1109\/CVPR42600.2020.01248"},{"key":"1950_CR2","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., & Zisserman, A. (2018). Objects that sound. In Proceedings of the European conference on computer vision (ECCV) (pp. 435\u2013451).","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"1950_CR3","doi-asserted-by":"crossref","unstructured":"Aytar, Y., Vondrick, C., & Torralba, A. (2016). Soundnet: Learning sound representations from unlabeled video. arXiv preprint arXiv:1610.09001","DOI":"10.1109\/CVPR.2016.18"},{"issue":"7","key":"1950_CR4","doi-asserted-by":"publisher","first-page":"1688","DOI":"10.1109\/TMM.2017.2777665","volume":"20","author":"C Bak","year":"2017","unstructured":"Bak, C., Kocak, A., Erdem, E., & Erdem, A. (2017). Spatio-temporal saliency networks for dynamic saliency prediction. IEEE Transactions on Multimedia, 20(7), 1688\u20131698.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1950_CR5","doi-asserted-by":"publisher","first-page":"3216","DOI":"10.1007\/s11263-021-01519-y","volume":"129","author":"G Bellitto","year":"2021","unstructured":"Bellitto, G., ProiettoSalanitri, F., Palazzo, S., Rundo, F., Giordano, D., & Spampinato, C. (2021). Hierarchical domain-adapted feature learning for video saliency prediction. International Journal of Computer Vision, 129, 3216\u20133232.","journal-title":"International Journal of Computer Vision"},{"key":"1950_CR6","doi-asserted-by":"crossref","unstructured":"Boccignone, G., Cuculo, V., D\u2019Amelio, A., Grossi, G., & Lanzarotti, R. (2018). Give ear to my face: Modelling multimodal attention to social interactions. In Proceedings of the European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-11012-3_27"},{"key":"1950_CR7","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TPAMI.2019.2935715","volume":"43","author":"A Borji","year":"2019","unstructured":"Borji, A. (2019). Saliency prediction in the deep learning era: Successes and limitations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43, 679\u2013700.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"1950_CR8","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1109\/TPAMI.2012.89","volume":"35","author":"A Borji","year":"2012","unstructured":"Borji, A., & Itti, L. (2012). State-of-the-art in visual attention modeling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(1), 185\u2013207.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"1950_CR9","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1109\/TPAMI.2018.2815601","volume":"41","author":"Z Bylinskii","year":"2018","unstructured":"Bylinskii, Z., Judd, T., Oliva, A., Torralba, A., & Durand, F. (2018). What do different evaluation metrics tell us about saliency models? IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(3), 740\u2013757.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1950_CR10","unstructured":"Cerf, M., Harel, J., Einh\u00e4user, W., & Koch, C. (2008). Predicting human gaze using low-level saliency combined with face detection. In Advances in neural information processing systems (pp. 241\u2013248)."},{"key":"1950_CR11","doi-asserted-by":"crossref","unstructured":"Chakravarty, P., & Tuytelaars, T. (2016). Cross-modal supervision for learning active speaker detection in video. In European conference on computer vision (pp. 285\u2013301). Springer.","DOI":"10.1007\/978-3-319-46454-1_18"},{"key":"1950_CR12","doi-asserted-by":"crossref","unstructured":"Chen, H,, Xie, W., Afouras, T., Nagrani, A., Vedaldi, A., & Zisserman, A. (2021). Localizing visual sounds the hard way. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16867\u201316876).","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"1950_CR13","doi-asserted-by":"crossref","unstructured":"Chen, Z. M., Wei, X. S., Wang, P., & Guo, Y. (2019). Multi-label image recognition with graph convolutional networks. In The IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00532"},{"key":"1950_CR14","doi-asserted-by":"crossref","unstructured":"Chung, J. S., & Zisserman, A. (2016). Out of time: Automated lip sync in the wild. In Asian conference on computer vision (pp. 251\u2013263). Springer.","DOI":"10.1007\/978-3-319-54427-4_19"},{"issue":"10","key":"1950_CR15","doi-asserted-by":"publisher","first-page":"5142","DOI":"10.1109\/TIP.2018.2851672","volume":"27","author":"M Cornia","year":"2018","unstructured":"Cornia, M., Baraldi, L., Serra, G., & Cucchiara, R. (2018). Predicting human eye fixations via an LSTM-based saliency attentive model. IEEE Transactions on Image Processing, 27(10), 5142\u20135154.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1950_CR16","doi-asserted-by":"crossref","unstructured":"Coutrot, A., & Guyader, N. (2013). Toward the introduction of auditory information in dynamic visual attention models. In 2013 14th International workshop on image analysis for multimedia interactive services (WIAMIS) (pp. 1\u20134). IEEE.","DOI":"10.1109\/WIAMIS.2013.6616164"},{"key":"1950_CR17","doi-asserted-by":"crossref","unstructured":"Coutrot, A., & Guyader, N. (2014a). An audiovisual attention model for natural conversation scenes. In 2014 IEEE international conference on image processing (ICIP) (pp. 1100\u20131104). IEEE.","DOI":"10.1109\/ICIP.2014.7025219"},{"issue":"8","key":"1950_CR18","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. (2014). How saliency, faces, and sound influence gaze in dynamic social scenes. Journal of Vision, 14(8), 5.","journal-title":"Journal of Vision"},{"key":"1950_CR19","doi-asserted-by":"crossref","unstructured":"Coutrot, A., & Guyader, N. (2015). An efficient audiovisual saliency model to predict eye positions when looking at conversations. In 2015 23rd European signal processing conference (EUSIPCO) (pp. 1531\u20131535). IEEE.","DOI":"10.1109\/EUSIPCO.2015.7362640"},{"key":"1950_CR20","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Fischer, P., Ilg, E., H\u00e4usser, P., Haz\u0131rba\u015f, C., Golkov, V., Van Der Smagt, P., Cremers, D., & Brox, T. (2015). Flownet: Learning optical flow with convolutional networks. In IEEE international conference on computer vision (ICCV). http:\/\/lmb.informatik.uni-freiburg.de\/Publications\/2015\/DFIB15","DOI":"10.1109\/ICCV.2015.316"},{"key":"1950_CR21","doi-asserted-by":"crossref","unstructured":"Droste, R., Jiao, J., & Noble, J. A. (2020). Unified image and video saliency modeling. In Proceedings of the 16th European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-58558-7_25"},{"key":"1950_CR22","doi-asserted-by":"crossref","unstructured":"Gao, R., Feris, R., & Grauman, K. (2018). Learning to separate object sounds by watching unlabeled video. In Proceedings of the European conference on computer vision (ECCV) (pp. 35\u201353).","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"1950_CR23","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., & Satoh, Y. (2018). Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and imagenet? In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6546\u20136555).","DOI":"10.1109\/CVPR.2018.00685"},{"key":"1950_CR24","doi-asserted-by":"crossref","unstructured":"Harel, J., Koch, C., & Perona. P. (2007). Graph-based visual saliency. In Advances in neural information processing systems (pp. 545\u2013552)","DOI":"10.7551\/mitpress\/7503.003.0073"},{"key":"1950_CR25","doi-asserted-by":"crossref","unstructured":"Hossein\u00a0Khatoonabadi, S., Vasconcelos, N., Bajic, I. V., & Shan, Y. (2015). How many bits does it take for a stimulus to be salient? In CVPR.","DOI":"10.1109\/CVPR.2015.7299189"},{"key":"1950_CR26","first-page":"10077","volume":"33","author":"D Hu","year":"2020","unstructured":"Hu, D., Qian, R., Jiang, M., Tan, X., Wen, S., Ding, E., Lin, W., & Dou, D. (2020). Discriminative sounding objects localization via self-supervised audiovisual matching. Advances in Neural Information Processing Systems, 33, 10077\u201310087.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1950_CR27","doi-asserted-by":"crossref","unstructured":"Huan, X., Shen, C., Boix, X., & Zhao, Q. (2015) Salicon: Reducing the semantic gap in saliency prediction by adapting deep neural networks. In ICCV.","DOI":"10.1109\/ICCV.2015.38"},{"key":"1950_CR28","unstructured":"Ioffe, S., & Szegedy, C. (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning, PMLR (pp. 448\u2013456)."},{"key":"1950_CR29","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/34.730558","volume":"11","author":"L Itti","year":"1998","unstructured":"Itti, L., Koch, C., & Niebur, E. (1998). A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis & Machine Intelligence, 11, 1254\u20131259.","journal-title":"IEEE Transactions on Pattern Analysis & Machine Intelligence"},{"key":"1950_CR30","doi-asserted-by":"crossref","unstructured":"Jain, S., Yarlagadda, P., Jyoti, S., Karthik, S., Subramanian, R., & Gandhi, V. (2020) Vinet: Pushing the limits of visual modality for audio\u2013visual saliency prediction. arXiv preprint arXiv:2012.06170","DOI":"10.1109\/IROS51168.2021.9635989"},{"key":"1950_CR31","doi-asserted-by":"crossref","unstructured":"Jia, R., Wang, X., Pang, S., Zhu, J., & Xue, J. (2020). Look, listen and infer. In Proceedings of the 28th ACM international conference on multimedia (pp. 3911\u20133919).","DOI":"10.1145\/3394171.3414023"},{"key":"1950_CR32","doi-asserted-by":"crossref","unstructured":"Jiang, L., Xu, M., Liu, T., Qiao, M., & Wang, Z. (2018) Deepvs: A deep learning based video saliency prediction approach. In Proceedings of the European conference on computer vision (ECCV) (pp. 602\u2013617).","DOI":"10.1007\/978-3-030-01264-9_37"},{"key":"1950_CR33","doi-asserted-by":"crossref","unstructured":"Jiang, L., Xu, M., Wang, Z., & Sigal, L. (2021). Deepvs2.0: A saliency-structured deep learning method for predicting dynamic visual attention. International Journal of Computer Vision, 129(1), 203\u2013224.","DOI":"10.1007\/s11263-020-01371-6"},{"key":"1950_CR34","doi-asserted-by":"crossref","unstructured":"Judd, T., Ehinger, K., Durand, F., & Torralba, A. (2009). Learning to predict where humans look. In 2009 IEEE 12th international conference on computer vision (pp. 2106\u20132113). IEEE.","DOI":"10.1109\/ICCV.2009.5459462"},{"issue":"21","key":"1950_CR35","doi-asserted-by":"publisher","first-page":"1943","DOI":"10.1016\/j.cub.2005.09.040","volume":"15","author":"C Kayser","year":"2005","unstructured":"Kayser, C., Petkov, C. I., Lippert, M., & Logothetis, N. K. (2005). Mechanisms for allocating auditory attention: An auditory saliency map. Current Biology, 15(21), 1943\u20131947.","journal-title":"Current Biology"},{"key":"1950_CR36","unstructured":"Knyazev, B., Taylor, G. W., & Amer, M. (2019). Understanding attention and generalization in graph neural networks. In Advances in neural information processing systems (pp. 4202\u20134212)."},{"key":"1950_CR37","doi-asserted-by":"crossref","unstructured":"Kumar, K., Chen, T., & Stern, R. M. (2007). Profile view lip reading. In 2007 IEEE international conference on acoustics, speech and signal processing-ICASSP\u201907 (vol.\u00a04, pp. IV\u2013429). IEEE.","DOI":"10.1109\/ICASSP.2007.366941"},{"issue":"19","key":"1950_CR38","doi-asserted-by":"publisher","first-page":"2483","DOI":"10.1016\/j.visres.2007.06.015","volume":"47","author":"O Le Meur","year":"2007","unstructured":"Le Meur, O., Le Callet, P., & Barba, D. (2007). Predicting visual fixations on video based on low-level visual features. Vision Research, 47(19), 2483\u20132498.","journal-title":"Vision Research"},{"issue":"3","key":"1950_CR39","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1007\/s11263-013-0678-0","volume":"107","author":"J Li","year":"2014","unstructured":"Li, J., Tian, Y., & Huang, T. (2014). Visual saliency with statistical priors. International Journal of Computer Vision, 107(3), 239\u2013253.","journal-title":"International Journal of Computer Vision"},{"issue":"2","key":"1950_CR40","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1007\/s11263-010-0354-6","volume":"90","author":"J Li","year":"2010","unstructured":"Li, J., Tian, Y., Huang, T., & Gao, W. (2010). Probabilistic multi-task learning for visual saliency estimation in video. International Journal of Computer Vision, 90(2), 150\u2013165.","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"1950_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.imavis.2010.07.001","volume":"29","author":"Z Li","year":"2011","unstructured":"Li, Z., Qin, S., & Itti, L. (2011). Visual attention guided bit allocation in video compression. Image and Vision Computing, 29(1), 1\u201314.","journal-title":"Image and Vision Computing"},{"key":"1950_CR42","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1007\/978-3-030-58565-5_25","volume-title":"Computer Vision-ECCV 2020","author":"Y Liu","year":"2020","unstructured":"Liu, Y., Qiao, M., Xu, M., Li, B., Hu, W., & Borji, A. (2020). Learning to predict salient faces: A novel visual-audio saliency model. In A. Vedaldi, H. Bischof, T. Brox, & J. M. Frahm (Eds.), Computer Vision-ECCV 2020 (pp. 413\u2013429). Springer."},{"key":"1950_CR43","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, S., Xu, M., & He, X. (2017). Predicting salient face in multiple-face videos. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4420\u20134428).","DOI":"10.1109\/CVPR.2017.343"},{"key":"1950_CR44","doi-asserted-by":"crossref","unstructured":"Marighetto, P., Coutrot, A., Riche, N., Guyader, N., Mancas, M., Gosselin, B., & Laganiere, R. (2017) Audio\u2013visual attention: Eye-tracking dataset and analysis toolbox. In 2017 IEEE international conference on image processing (ICIP) (pp. 1802\u20131806).","DOI":"10.1109\/ICIP.2017.8296592"},{"key":"1950_CR45","unstructured":"Merritt, L., Vanam, R. (2006). x264: A high performance h.264\/avc encoder. online]. https:\/\/www.neuron2net\/library\/avc\/overview_x264_v8_5.pdf"},{"key":"1950_CR46","doi-asserted-by":"crossref","unstructured":"Min, K., & Corso, J. J. (2019). Tased-net: Temporally-aggregating spatial encoder-decoder network for video saliency detection. arXiv preprint arXiv:1908.05786","DOI":"10.1109\/ICCV.2019.00248"},{"key":"1950_CR47","doi-asserted-by":"crossref","unstructured":"Owens, A., & Efros, A. A. (2018). Audio-visual scene analysis with self-supervised multisensory features. In Proceedings of the European conference on computer vision (ECCV) (pp. 631\u2013648).","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"1950_CR48","unstructured":"Pan, J., Ferrer, C. C., McGuinness, K., O\u2019Connor, N. E., Torres, J., Sayrol, E., & Giro-i Nieto, X. (2017). Salgan: Visual saliency prediction with generative adversarial networks. arXiv preprint arXiv:1701.01081"},{"issue":"4","key":"1950_CR49","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1109\/TIP.2008.917218","volume":"17","author":"U Rajashekar","year":"2008","unstructured":"Rajashekar, U., Van Der Linde, I., Bovik, A. C., & Cormack, L. K. (2008). Gaffe: A gaze-attentive fixation finding engine. IEEE Transactions on Image Processing, 17(4), 564\u2013573.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1950_CR50","doi-asserted-by":"crossref","unstructured":"Roth, J., Chaudhuri, S., Klejch, O., Marvin, R., Gallagher, A., Kaver, L., Ramaswamy, S., Stopczynski, A., Schmid, C., Xi, Z., et\u00a0al. (2020). Ava active speaker: An audio-visual dataset for active speaker detection. In ICASSP 2020\u20142020 IEEE international conference on acoustics (pp. 4492\u20134496). IEEE: Speech and Signal Processing (ICASSP).","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"1950_CR51","doi-asserted-by":"crossref","unstructured":"Senocak, A., Oh, T. H., Kim, J., Yang, M. H., & So\u00a0Kweon, I. (2018). Learning to localize sound source in visual scenes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 4358\u20134366).","DOI":"10.1109\/CVPR.2018.00458"},{"key":"1950_CR52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2952095","author":"A Senocak","year":"2019","unstructured":"Senocak, A., Oh, T. H., Kim, J., Yang, M. H., & Kweon, I. S. (2019). Learning to localize sound sources in visual scenes: Analysis and applications. IEEE Transactions on Pattern Analysis and Machine Intelligence. https:\/\/doi.org\/10.1109\/TPAMI.2019.2952095","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1950_CR53","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In 3rd International conference on learning representations, ICLR 2015, conference track proceedings."},{"issue":"1","key":"1950_CR54","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/s11263-015-0853-6","volume":"117","author":"N Souly","year":"2016","unstructured":"Souly, N., & Shah, M. (2016). Visual saliency detection using group lasso regularization in videos of natural scenes. International Journal of Computer Vision, 117(1), 93\u2013110.","journal-title":"International Journal of Computer Vision"},{"key":"1950_CR55","unstructured":"SR-Research. (2010). Eyelink 1000 plus. https:\/\/www.sr-research.com\/products\/eyelink-1000-plus\/"},{"key":"1950_CR56","unstructured":"Tavakoli, H. R., Borji, A., Rahtu, E., & Kannala, J. (2019). Dave: A deep audio\u2013visual embedding for dynamic saliency prediction. arXiv preprint arXiv:1905.10693"},{"key":"1950_CR57","unstructured":"Thomas, C. L. (2016). Opensalicon: An open source implementation of the salicon saliency model. Technical Report. TR-2016-02, University of Pittsburgh."},{"key":"1950_CR58","doi-asserted-by":"crossref","unstructured":"Tian, Y., Shi, J., Li, B., Duan, Z., & Xu, C. (2018). Audio\u2013visual event localization in unconstrained videos. In Proceedings of the European conference on computer vision (ECCV) (pp. 247\u2013263).","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"1950_CR59","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015). Learning spatiotemporal features with 3D convolutional networks. In Proceedings of the IEEE international conference on computer vision (pp. 4489\u20134497).","DOI":"10.1109\/ICCV.2015.510"},{"key":"1950_CR60","doi-asserted-by":"crossref","unstructured":"Tsiami, A., Katsamanis, A., Maragos, P., & Vatakis, A. (2016). Towards a behaviorally-validated computational audiovisual saliency model. In 2016 IEEE international conference on acoustics (pp. 2847\u20132851). IEEE: Speech and Signal Processing (ICASSP).","DOI":"10.1109\/ICASSP.2016.7472197"},{"key":"1950_CR61","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 5998\u20136008.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1950_CR62","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., & Bengio, Y. (2017). Graph attention networks. arXiv preprint arXiv:1710.10903"},{"issue":"5","key":"1950_CR63","doi-asserted-by":"publisher","first-page":"2368","DOI":"10.1109\/TIP.2017.2787612","volume":"27","author":"W Wang","year":"2017","unstructured":"Wang, W., & Shen, J. (2017). Deep visual attention prediction. IEEE Transactions on Image Processing, 27(5), 2368\u20132378.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1950_CR64","doi-asserted-by":"crossref","unstructured":"Wang, W., Shen, J., Guo, F., Cheng, M. M., & Borji, A. (2018). Revisiting video saliency: A large-scale benchmark and a new model. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4894\u20134903).","DOI":"10.1109\/CVPR.2018.00514"},{"key":"1950_CR65","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., & Murphy, K. (2018). Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification. In Proceedings of the European conference on computer vision (ECCV) (pp. 305\u2013321).","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"1950_CR66","unstructured":"Xingjian, S., Chen, Z., Wang, H., Yeung, D. Y., Wong, W. K., & Woo, W. C. (2015). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In Advances in neural information processing systems (pp. 802\u2013810)."},{"key":"1950_CR67","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1016\/j.patcog.2016.05.023","volume":"60","author":"M Xu","year":"2016","unstructured":"Xu, M., Jiang, L., Ye, Z., & Wang, Z. (2016). Bottom-up saliency detection with sparse representation of learnt texture atoms. Pattern Recognition, 60, 348\u2013360.","journal-title":"Pattern Recognition"},{"issue":"9","key":"1950_CR68","doi-asserted-by":"publisher","first-page":"4529","DOI":"10.1109\/TIP.2018.2837106","volume":"27","author":"M Xu","year":"2018","unstructured":"Xu, M., Liu, Y., Hu, R., & He, F. (2018). Find who to look at: Turning from action to saliency. IEEE Transactions on Image Processing, 27(9), 4529\u20134544.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1950_CR69","doi-asserted-by":"crossref","unstructured":"Zanca, D., Melacci, S., & Gori, M. (2019). Gravitational laws of focus of attention. IEEE Transactions on Pattern Analysis and Machine Intelligence.","DOI":"10.1109\/TPAMI.2019.2920636"},{"key":"1950_CR70","doi-asserted-by":"crossref","unstructured":"Zhang, J., & Sclaroff, S. (2016). Exploiting surroundedness for saliency detection: A Boolean map approach. In IEEE TPAMI (pp. 889\u2013902).","DOI":"10.1109\/TPAMI.2015.2473844"},{"key":"1950_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zhang, Z., Li, Z., & Qiao, Y. (2016). Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters, 23(10), 1499\u20131503.","DOI":"10.1109\/LSP.2016.2603342"},{"key":"1950_CR72","doi-asserted-by":"crossref","unstructured":"Zhao, H., Gan, C., Rouditchenko, A., Vondrick, C., McDermott, J., & Torralba, A. (2018). The sound of pixels. In Proceedings of the European conference on computer vision (ECCV) (pp. 570\u2013586).","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"1950_CR73","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2921\u20132929).","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01950-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01950-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01950-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T06:09:05Z","timestamp":1717135745000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01950-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,29]]},"references-count":73,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["1950"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01950-3","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,29]]},"assertion":[{"value":"27 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 December 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}