{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T14:24:03Z","timestamp":1780496643433,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819787913","type":"print"},{"value":"9789819787920","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T00:00:00Z","timestamp":1731110400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T00:00:00Z","timestamp":1731110400000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-8792-0_13","type":"book-chapter","created":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T06:57:57Z","timestamp":1731049077000},"page":"177-191","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Task-Oriented Scanpath Prediction with Spatial-Temporal Information in Driving Scenarios"],"prefix":"10.1007","author":[{"given":"Zhixin","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Gou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,9]]},"reference":[{"issue":"4","key":"13_CR1","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1037\/0033-295X.87.4.329","volume":"87","author":"MA Just","year":"1980","unstructured":"Just, M.A., Carpenter, P.A.: A theory of reading: from eye fixations to comprehension. Psychol. Rev. 87(4), 329 (1980)","journal-title":"Psychol. Rev."},{"key":"13_CR2","unstructured":"K\u00fcmmerer, M., Theis, L., Bethge, M.: Deep gaze i: Boosting saliency prediction with feature maps trained on imagenet (2014). arXiv:1411.1045"},{"issue":"1","key":"13_CR3","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1109\/TIV.2022.3173397","volume":"8","author":"C Gou","year":"2022","unstructured":"Gou, C., Zhou, Y., Xiao, Y., Wang, X., Yu, H.: Cascade learning for driver facial monitoring. IEEE Trans. Intell. Veh. 8(1), 404\u2013412 (2022)","journal-title":"IEEE Trans. Intell. Veh."},{"issue":"6","key":"13_CR4","doi-asserted-by":"publisher","first-page":"8268","DOI":"10.1007\/s11227-021-04151-2","volume":"78","author":"C Gou","year":"2022","unstructured":"Gou, C., Zhou, Y., Li, D.: Driver attention prediction based on convolution and transformers. J. Supercomput. 78(6), 8268\u20138284 (2022)","journal-title":"J. Supercomput."},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Xia, Y., Zhang, D., Kim, J., Nakayama, K., Zipser, K., Whitney, D.: Predicting driver attention in critical situations. In: Computer Vision\u2013ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2\u20136, 2018, Revised Selected Papers, Part V 14, pp. 658\u2013674. Springer (2019)","DOI":"10.1007\/978-3-030-20873-8_42"},{"issue":"5","key":"13_CR6","doi-asserted-by":"publisher","first-page":"2146","DOI":"10.1109\/TITS.2019.2915540","volume":"21","author":"T Deng","year":"2019","unstructured":"Deng, T., Yan, H., Qin, L., Ngo, T., Manjunath, B.: How do drivers allocate their potential attention? driving fixation prediction via convolutional neural networks. IEEE Trans. Intell. Transp. Syst. 21(5), 2146\u20132154 (2019)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Liu, L., Gou, C.: Learning from observer gaze: zero-shot attention prediction oriented by human-object interaction recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 28390\u201328400 (June 2024)","DOI":"10.1109\/CVPR52733.2024.02682"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zhou, Y., Zhu, J., Gou, C.: Driver scanpath prediction based on inverse reinforcement learning. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8306\u20138310. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10446034"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Yang, Z., Huang, L., Chen, Y., Wei, Z., Ahn, S., Zelinsky, G., Samaras, D., Hoai, M.: Predicting goal-directed human attention using inverse reinforcement learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 193\u2013202 (2020)","DOI":"10.1109\/CVPR42600.2020.00027"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Sui, X., Fang, Y., Zhu, H., Wang, S., Wang, Z.: Scandmm: A deep markov model of scanpath prediction for 360deg images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6989\u20136999 (2023)","DOI":"10.1109\/CVPR52729.2023.00675"},{"issue":"7","key":"13_CR11","doi-asserted-by":"publisher","first-page":"3502","DOI":"10.1109\/TIP.2019.2897966","volume":"28","author":"C Xia","year":"2019","unstructured":"Xia, C., Han, J., Qi, F., Shi, G.: Predicting human saccadic scanpaths based on iterative representation learning. IEEE Trans. Image Process. 28(7), 3502\u20133515 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Mondal, S., Yang, Z., Ahn, S., Samaras, D., Zelinsky, G., Hoai, M.: Gazeformer: scalable, effective and fast prediction of goal-directed human attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1441\u20131450 (2023)","DOI":"10.1109\/CVPR52729.2023.00145"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Chen, X., Jiang, M., Zhao, Q.: Predicting human scanpaths in visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10876\u201310885 (2021)","DOI":"10.1109\/CVPR46437.2021.01073"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Assens, M., Giro-i Nieto, X., McGuinness, K., O\u2019Connor, N.E.: Pathgan: visual scanpath prediction with generative adversarial networks. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops, pp. 406\u2013422 (2018)","DOI":"10.1007\/978-3-030-11021-5_25"},{"issue":"1","key":"13_CR15","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/0010-0285(80)90005-5","volume":"12","author":"AM Treisman","year":"1980","unstructured":"Treisman, A.M., Gelade, G.: A feature-integration theory of attention. Cogn. Psychol. 12(1), 97\u2013136 (1980)","journal-title":"Cogn. Psychol."},{"issue":"11","key":"13_CR16","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L Itti","year":"1998","unstructured":"Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254\u20131259 (1998)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tan, G., Li, M., Gou, C.: Learning from easy to hard pairs: Multi-step reasoning network for human-object interaction detection. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 4368\u20134377 (2023)","DOI":"10.1145\/3581783.3612581"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Huang, X., Shen, C., Boix, X., Zhao, Q.: Salicon: Reducing the semantic gap in saliency prediction by adapting deep neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 262\u2013270 (2015)","DOI":"10.1109\/ICCV.2015.38"},{"key":"13_CR19","doi-asserted-by":"publisher","unstructured":"Zhou, Y., Tan, G., Gou, C.: Hierarchical home action understanding with implicit and explicit prior knowledge. In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4015\u20134019 (2024). https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10445997","DOI":"10.1109\/ICASSP48485.2024.10445997"},{"key":"13_CR20","doi-asserted-by":"publisher","unstructured":"Zhou, Y., Liu, X., Guo, Z., Cai, M., Gou, C.: Hktsg: A hierarchical knowledge-guided traffic scene graph representation learning framework for intelligent vehicles. IEEE Transactions on Intelligent Vehicles, pp. 1\u201312 (2024). https:\/\/doi.org\/10.1109\/TIV.2024.3384989","DOI":"10.1109\/TIV.2024.3384989"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Judd, T., Ehinger, K., Durand, F., Torralba, A.: Learning to predict where humans look. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 2106\u20132113. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459462"},{"issue":"12","key":"13_CR22","doi-asserted-by":"publisher","first-page":"14213","DOI":"10.1109\/TITS.2023.3309309","volume":"24","author":"Y Zhou","year":"2023","unstructured":"Zhou, Y., Tan, G., Zhong, R., Li, Y., Gou, C.: Pit: progressive interaction transformer for pedestrian crossing intention prediction. IEEE Trans. Intell. Transp. Syst. 24(12), 14213\u201314225 (2023). https:\/\/doi.org\/10.1109\/TITS.2023.3309309","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Bylinskii, Z., Recasens, A., Borji, A., Oliva, A., Torralba, A., Durand, F.: Where should saliency models look next? In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part V 14, pp. 809\u2013824. Springer (2016)","DOI":"10.1007\/978-3-319-46454-1_49"},{"key":"13_CR24","first-page":"8","volume":"69","author":"M Assens","year":"2018","unstructured":"Assens, M., Giro-i Nieto, X., McGuinness, K., O\u2019Connor, N.E.: Scanpath and saliency prediction on 360 degree images. Signal Process.: Image Commun. 69, 8\u201314 (2018)","journal-title":"Signal Process.: Image Commun."},{"issue":"2","key":"13_CR25","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1016\/j.cogbrainres.2004.02.011","volume":"21","author":"JT Coull","year":"2004","unstructured":"Coull, J.T.: FMRI studies of temporal attention: allocating attention within, or towards, time. Cogn. Brain Res. 21(2), 216\u2013226 (2004)","journal-title":"Cogn. Brain Res."},{"issue":"6","key":"13_CR26","doi-asserted-by":"publisher","first-page":"2101","DOI":"10.1109\/TPAMI.2019.2956930","volume":"43","author":"W Sun","year":"2019","unstructured":"Sun, W., Chen, Z., Wu, F.: Visual scanpath prediction using IOR-ROI recurrent mixture density network. IEEE Trans. Pattern Anal. Mach. Intell. 43(6), 2101\u20132118 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR27","doi-asserted-by":"publisher","unstructured":"Li, M., Zhu, J., Huang, Z., Gou, C.: Imitating the human visual system for scanpath predicting. In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3745\u20133749 (2024). https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10447354","DOI":"10.1109\/ICASSP48485.2024.10447354"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, R., Liu, Z., Zhang, L., Whritner, J.A., Muller, K.S., Hayhoe, M.M., Ballard, D.H.: Agil: learning attention from human for visuomotor tasks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 663\u2013679 (2018)","DOI":"10.1007\/978-3-030-01252-6_41"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Saxena, D.M., Bae, S., Nakhaei, A., Fujimura, K., Likhachev, M.: Driving in dense traffic with model-free reinforcement learning. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 5385\u20135392. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9197132"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Baee, S., Pakdamanian, E., Kim, I., Feng, L., Ordonez, V., Barnes, L.: Medirl: predicting the visual attention of drivers via maximum entropy deep inverse reinforcement learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13178\u201313188 (2021)","DOI":"10.1109\/ICCV48922.2021.01293"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Bao, W., Yu, Q., Kong, Y.: Drive: Deep reinforced accident anticipation with visual explanation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7619\u20137628 (2021)","DOI":"10.1109\/ICCV48922.2021.00752"},{"key":"13_CR32","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., Stoyanov, V.: Roberta: a robustly optimized bert pretraining approach (2019). arXiv:1907.11692"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Fang, J., Yan, D., Qiao, J., Xue, J., Wang, H., Li, S.: Dada-2000: can driving accident be predicted by driver attentionf analyzed by a benchmark. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), pp. 4303\u20134309. IEEE (2019)","DOI":"10.1109\/ITSC.2019.8917218"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8792-0_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T07:06:59Z","timestamp":1731049619000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8792-0_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,9]]},"ISBN":["9789819787913","9789819787920"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8792-0_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,9]]},"assertion":[{"value":"9 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}