{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T07:07:43Z","timestamp":1783840063217,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819228669","type":"print"},{"value":"9789819228645","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"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":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-2864-5_25","type":"book-chapter","created":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T06:20:48Z","timestamp":1783837248000},"page":"293-304","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SphereU-Sal360: Spherical U-Shaped Spatio-Temporal Transformer for $$360^\\circ $$ Video Saliency"],"prefix":"10.1007","author":[{"given":"Yanzhi","family":"Ding","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhigeng","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihua","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"issue":"12","key":"25_CR1","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. Vision 129(12), 3216\u20133232 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Benny, Y., Wolf, L.: SphereUFormer: a U-Shaped transformer for spherical 360 perception. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 940\u2013950 (2025)","DOI":"10.1109\/CVPR52734.2025.00096"},{"key":"25_CR3","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.cag.2022.06.002","volume":"106","author":"E Bernal-Berdun","year":"2022","unstructured":"Bernal-Berdun, E., Martin, D., Gutierrez, D., et al.: SST-Sal: a spherical spatio-temporal approach for saliency prediction in $$360^\\circ $$ videos. Comput. Graph. 106, 200\u2013209 (2022)","journal-title":"Comput. Graph."},{"issue":"3","key":"25_CR4","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., et al.: What do different evaluation metrics tell us about saliency models? IEEE Trans. Pattern Anal. Mach. Intell. 41(3), 740\u2013757 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Chao, F.Y., Zhang, L., Hamidouche, W., et\u00a0al.: Salgan360: visual saliency prediction on 360 degree images with generative adversarial networks. In: IEEE International Conference on Multimedia & Expo Workshops, pp.\u00a01\u20134 (2018)","DOI":"10.1109\/ICMEW.2018.8551543"},{"key":"25_CR6","unstructured":"Cokelek, M., Imamoglu, N., Ozcinar, C., Erdem, E., Erdem, A.: Spherical vision transformer for $$360^\\circ $$ video saliency prediction. In: British Machine Vision Conference, pp. 317\u2013319 (2023)"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Dahou, Y., Tliba, M., McGuinness, K., et\u00a0al.: ATSal: an attention based architecture for saliency prediction in $$360^\\circ $$ videos. In: International Conference on Pattern Recognition, pp. 305\u2013320. Springer (2021)","DOI":"10.1007\/978-3-030-68796-0_22"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Djilali, Y.A.D., Krishna, T., McGuinness, K., et\u00a0al.: Rethinking 360deg image visual attention modelling with unsupervised learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15414\u201315424 (2021)","DOI":"10.1109\/ICCV48922.2021.01513"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Huang, X., Shen, C., Boix, X.: Salicon: reducing the semantic gap in saliency prediction by adapting deep neural networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 262\u2013270 (2015)","DOI":"10.1109\/ICCV.2015.38"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Judd, T., Ehinger, K., Durand, F.: Learning to predict where humans look. In: IEEE 12th International Conference on Computer Vision, pp. 2106\u20132113 (2009)","DOI":"10.1109\/ICCV.2009.5459462"},{"issue":"3","key":"25_CR11","doi-asserted-by":"publisher","first-page":"1607","DOI":"10.1109\/TCSVT.2021.3076585","volume":"32","author":"N Kan","year":"2021","unstructured":"Kan, N., Zou, J., Li, C., et al.: RAPT360: reinforcement learning-based rate adaptation for 360-degree video streaming with adaptive prediction and tiling. IEEE Trans. Circuits Syst. Video Technol. 32(3), 1607\u20131623 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Min, K., Corso, J.J.: Tased-net: temporally-aggregating spatial encoder-decoder network for video saliency detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2394\u20132403 (2019)","DOI":"10.1109\/ICCV.2019.00248"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Yan, Z., Nahrstedt, K.: Your attention is unique: detecting 360-degree video saliency in head-mounted display for head movement prediction. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 1190\u20131198 (2018)","DOI":"10.1145\/3240508.3240669"},{"issue":"1","key":"25_CR14","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1109\/JSTSP.2020.2966864","volume":"14","author":"M Xu","year":"2020","unstructured":"Xu, M., Li, C., Zhang, S., et al.: State-of-the-art in 360 video\/image processing: perception, assessment and compression. IEEE J. Sel. Top. Signal Process. 14(1), 5\u201326 (2020)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"issue":"10","key":"25_CR15","doi-asserted-by":"publisher","first-page":"9979","DOI":"10.1109\/TCSVT.2024.3407685","volume":"34","author":"Q Yang","year":"2024","unstructured":"Yang, Q., Gao, W., Li, C., et al.: 360spred: saliency prediction for 360-degree videos based on 3D separable graph convolutional networks. IEEE Trans. Circuits Syst. Video Technol. 34(10), 9979\u20139996 (2024)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"25_CR16","doi-asserted-by":"publisher","first-page":"3061","DOI":"10.1109\/TMM.2023.3306596","volume":"26","author":"Q Yang","year":"2023","unstructured":"Yang, Q., Li, Y., Li, C., et al.: SVGC-AVA: 360-degree video saliency prediction with spherical vector-based graph convolution and audio-visual attention. IEEE Trans. Multimedia 26, 3061\u20133076 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Yun, H., Lee, S., Kim, G.: Panoramic vision transformer for saliency detection in $$360^\\circ $$ videos. In: Proceedings of the European Conference on Computer Vision, vol. 13695, pp. 422\u2013439. Springer (2022)","DOI":"10.1007\/978-3-031-19833-5_25"},{"issue":"12","key":"25_CR18","doi-asserted-by":"publisher","first-page":"3544","DOI":"10.1109\/TCSVT.2018.2883305","volume":"29","author":"K Zhang","year":"2018","unstructured":"Zhang, K., Chen, Z.: Video saliency prediction based on spatial-temporal two-stream network. IEEE Trans. Circuits Syst. Video Technol. 29(12), 3544\u20133557 (2018)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"25_CR19","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.isprsjprs.2022.10.008","volume":"194","author":"K Zhang","year":"2022","unstructured":"Zhang, K., Chen, Z., Li, S., Liu, S.: An efficient saliency prediction model for unmanned aerial vehicle video. ISPRS J. Photogramm. Remote. Sens. 194, 152\u2013166 (2022)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"25_CR20","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1109\/TIP.2020.3036749","volume":"30","author":"K Zhang","year":"2020","unstructured":"Zhang, K., Chen, Z., Liu, S.: A spatial-temporal recurrent neural network for video saliency prediction. IEEE Trans. Image Process. 30, 572\u2013587 (2020)","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"25_CR21","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1109\/JSTSP.2019.2955824","volume":"14","author":"Y Zhang","year":"2019","unstructured":"Zhang, Y., Dai, F., Ma, Y., et al.: Saliency prediction network for $$360^\\circ $$ videos. IEEE J. Sel. Top. Signal Process. 14(1), 27\u201337 (2019)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xu, Y., Yu, J.: Saliency detection in 360 videos. In: Proceedings of the European Conference on Computer Vision, pp. 488\u2013503 (2018)","DOI":"10.1007\/978-3-030-01234-2_30"},{"issue":"12","key":"25_CR23","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. 33(12), 7696\u20137707 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"25_CR24","doi-asserted-by":"publisher","first-page":"3447","DOI":"10.1109\/TIP.2025.3567842","volume":"34","author":"Y Zhu","year":"2025","unstructured":"Zhu, Y., Duan, H., Zhang, K., et al.: How does audio influence visual attention in omnidirectional videos? Database and model. IEEE Trans. Image Process. 34, 3447\u20133462 (2025)","journal-title":"IEEE Trans. Image Process."}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-2864-5_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T06:20:50Z","timestamp":1783837250000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-2864-5_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,13]]},"ISBN":["9789819228669","9789819228645"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-2864-5_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,13]]},"assertion":[{"value":"13 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ksem2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ksem2026.rosc.org.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}