{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T19:23:10Z","timestamp":1774898590840,"version":"3.50.1"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733826","type":"print"},{"value":"9783031733833","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-3-031-73383-3_18","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T12:03:19Z","timestamp":1730548999000},"page":"305-322","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Gaze Target Detection Based on\u00a0Head-Local-Global Coordination"],"prefix":"10.1007","author":[{"given":"Yaokun","family":"Yang","sequence":"first","affiliation":[]},{"given":"Feng","family":"Lu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"18_CR1","unstructured":"Bachman, P., Hjelm, R.D., Buchwalter, W.: Learning representations by maximizing mutual information across views. Advances in neural information processing systems 32 (2019)"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Bao, J., Liu, B., Yu, J.: Escnet: Gaze target detection with the understanding of 3d scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14126\u201314135 (2022)","DOI":"10.1109\/CVPR52688.2022.01373"},{"key":"18_CR3","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"18_CR4","first-page":"22243","volume":"33","author":"T Chen","year":"2020","unstructured":"Chen, T., Kornblith, S., Swersky, K., Norouzi, M., Hinton, G.E.: Big self-supervised models are strong semi-supervised learners. Adv. Neural. Inf. Process. Syst. 33, 22243\u201322255 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR5","doi-asserted-by":"publisher","first-page":"5259","DOI":"10.1109\/TIP.2020.2982828","volume":"29","author":"Y Cheng","year":"2020","unstructured":"Cheng, Y., Zhang, X., Lu, F., Sato, Y.: Gaze estimation by exploring two-eye asymmetry. IEEE Trans. Image Process. 29, 5259\u20135272 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Chong, E., Ruiz, N., Wang, Y., Zhang, Y., Rozga, A., Rehg, J.M.: Connecting gaze, scene, and attention: Generalized attention estimation via joint modeling of gaze and scene saliency. In: Proceedings of the European conference on computer vision (ECCV), pp. 383\u2013398 (2018)","DOI":"10.1007\/978-3-030-01228-1_24"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Chong, E., Wang, Y., Ruiz, N., Rehg, J.M.: Detecting attended visual targets in video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5396\u20135406 (2020)","DOI":"10.1109\/CVPR42600.2020.00544"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"2","key":"18_CR9","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vision 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vision"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Fang, Y., Tang, J., Shen, W., Shen, W., Gu, X., Song, L., Zhai, G.: Dual attention guided gaze target detection in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11390\u201311399 (2021)","DOI":"10.1109\/CVPR46437.2021.01123"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Fischer, T., Chang, H.J., Demiris, Y.: Rt-gene: real-time eye gaze estimation in natural environments. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 334\u2013352 (2018)","DOI":"10.1007\/978-3-030-01249-6_21"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac\u00a0Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3828\u20133838 (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201906), vol.\u00a02, pp. 1735\u20131742. IEEE (2006)","DOI":"10.1109\/CVPR.2006.100"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"18_CR15","unstructured":"Hjelm, R.D., et al.: Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670 (2018)"},{"key":"18_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.104924","volume":"113","author":"T Jin","year":"2022","unstructured":"Jin, T., Yu, Q., Zhu, S., Lin, Z., Ren, J., Zhou, Y., Song, W.: Depth-aware gaze-following via auxiliary networks for robotics. Eng. Appl. Artif. Intell. 113, 104924 (2022)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"18_CR17","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"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Kellnhofer, P., Recasens, A., Stent, S., Matusik, W., Torralba, A.: Gaze360: Physically unconstrained gaze estimation in the wild. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6912\u20136921 (2019)","DOI":"10.1109\/ICCV.2019.00701"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Lian, D., Yu, Z., Gao, S.: Believe it or not, we know what you are looking at! In: Asian Conference on Computer Vision, pp. 35\u201350. Springer (2018)","DOI":"10.1007\/978-3-030-20893-6_3"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: Common objects in context. In: European Conference on Computer Vision, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"3","key":"18_CR21","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1016\/j.imavis.2014.01.005","volume":"32","author":"F Lu","year":"2014","unstructured":"Lu, F., Okabe, T., Sugano, Y., Sato, Y.: Learning gaze biases with head motion for head pose-free gaze estimation. Image Vis. Comput. 32(3), 169\u2013179 (2014)","journal-title":"Image Vis. Comput."},{"issue":"10","key":"18_CR22","doi-asserted-by":"publisher","first-page":"2033","DOI":"10.1109\/TPAMI.2014.2313123","volume":"36","author":"F Lu","year":"2014","unstructured":"Lu, F., Sugano, Y., Okabe, T., Sato, Y.: Adaptive linear regression for appearance-based gaze estimation. IEEE Trans. Pattern Anal. Mach. Intell. 36(10), 2033\u20132046 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Miao, Q., Hoai, M., Samaras, D.: Patch-level gaze distribution prediction for gaze following. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 880\u2013889 (2023)","DOI":"10.1109\/WACV56688.2023.00094"},{"issue":"3","key":"18_CR24","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1623\u20131637 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR25","unstructured":"Recasens, A., Khosla, A., Vondrick, C., Torralba, A.: Where are they looking? Advances in neural information processing systems 28 (2015)"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Sugano, Y., Matsushita, Y., Sato, Y.: Learning-by-synthesis for appearance-based 3d gaze estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1821\u20131828 (2014)","DOI":"10.1109\/CVPR.2014.235"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Tafasca, S., Gupta, A., Odobez, J.M.: Childplay: A new benchmark for understanding children\u2019s gaze behaviour. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20935\u201320946 (2023)","DOI":"10.1109\/ICCV51070.2023.01914"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Tonini, F., Dall\u2019Asen, N., Beyan, C., Ricci, E.: Object-aware gaze target detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21860\u201321869 (2023)","DOI":"10.1109\/ICCV51070.2023.01998"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Tu, D., Min, X., Duan, H., Guo, G., Zhai, G., Shen, W.: End-to-end human-gaze-target detection with transformers. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2192\u20132200. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.00224"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: Large-scale scene recognition from abbey to zoo. In: 2010 IEEE computer society conference on computer vision and pattern recognition. pp. 3485\u20133492. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, M., Liu, Y., Lu, F.: Gazeonce: real-time multi-person gaze estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4197\u20134206 (2022)","DOI":"10.1109\/CVPR52688.2022.00416"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, X., Park, S., Beeler, T., Bradley, D., Tang, S., Hilliges, O.: Eth-xgaze: A large scale dataset for gaze estimation under extreme head pose and gaze variation. In: European Conference on Computer Vision, pp. 365\u2013381. Springer (2020)","DOI":"10.1007\/978-3-030-58558-7_22"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, X., Sugano, Y., Fritz, M., Bulling, A.: Appearance-based gaze estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4511\u20134520 (2015)","DOI":"10.1109\/CVPR.2015.7299081"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, X., Sugano, Y., Fritz, M., Bulling, A.: It\u2019s written all over your face: Full-face appearance-based gaze estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 51\u201360 (2017)","DOI":"10.1109\/CVPRW.2017.284"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73383-3_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T12:10:26Z","timestamp":1730549426000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73383-3_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031733826","9783031733833"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73383-3_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}