{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T16:48:04Z","timestamp":1742921284093,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781032"},{"type":"electronic","value":"9783031781049"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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\/978-3-031-78104-9_27","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T21:43:57Z","timestamp":1733089437000},"page":"399-414","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["IPHGaze: Image Pyramid Gaze Estimation with\u00a0Head Pose Guidance"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9243-7936","authenticated-orcid":false,"given":"Hekuangyi","family":"Che","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1579-3942","authenticated-orcid":false,"given":"Dongchen","family":"Zhu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2882-2981","authenticated-orcid":false,"given":"Wenjun","family":"Shi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0432-7329","authenticated-orcid":false,"given":"Guanghui","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9875-696X","authenticated-orcid":false,"given":"Hang","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6655-188X","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7478-4544","authenticated-orcid":false,"given":"Jiamao","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Abdelrahman, A.A., Hempel, T., Khalifa, A., Al-Hamadi, A., Dinges, L.: L2CS-Net: fine-grained gaze estimation in unconstrained environments. In: 2023 8th International Conference on Frontiers of Signal Processing (ICFSP), pp. 98\u2013102. IEEE (2023)","DOI":"10.1109\/ICFSP59764.2023.10372944"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Bao, Y., Cheng, Y., Liu, Y., Lu, F.: Adaptive feature fusion network for gaze tracking in mobile tablets. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 9936\u20139943. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412205"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Bao, Y., Wang, J., Wang, Z., Lu, F.: Exploring 3D interaction with gaze guidance in augmented reality. In: 2023 IEEE Conference Virtual Reality and 3D User Interfaces (VR), pp. 22\u201332. IEEE (2023)","DOI":"10.1109\/VR55154.2023.00018"},{"key":"27_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2024.103909","volume":"119","author":"K Bekta\u015f","year":"2024","unstructured":"Bekta\u015f, K., Strecker, J., Mayer, S., Garcia, K.: Gaze-enabled activity recognition for augmented reality feedback. Comput. Graph. 119, 103909 (2024)","journal-title":"Comput. Graph."},{"key":"27_CR5","unstructured":"Cai, X., et al.: Gaze estimation with an ensemble of four architectures. arXiv preprint arXiv:2107.01980 (2021)"},{"key":"27_CR6","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1007\/978-3-031-18907-4_43","volume-title":"PRCV 2022","author":"H Che","year":"2022","unstructured":"Che, H., et al.: EFG-Net: a unified framework for estimating eye gaze and face gaze simultaneously. In: Yu, S., et al. (eds.) PRCV 2022. LNCS, vol. 13534, pp. 552\u2013565. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-18907-4_43"},{"key":"27_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/978-3-030-20876-9_20","volume-title":"Computer Vision \u2013 ACCV 2018","author":"Z Chen","year":"2019","unstructured":"Chen, Z., Shi, B.E.: Appearance-based gaze estimation using dilated-convolutions. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11366, pp. 309\u2013324. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20876-9_20"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Huang, S., Wang, F., Qian, C., Lu, F.: A coarse-to-fine adaptive network for appearance-based gaze estimation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 10623\u201310630 (2020)","DOI":"10.1609\/aaai.v34i07.6636"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Lu, F.: Gaze estimation using transformer. In: 2022 26th International Conference on Pattern Recognition (ICPR), pp. 3341\u20133347. IEEE (2022)","DOI":"10.1109\/ICPR56361.2022.9956687"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Lu, F.: DVGaze: dual-view gaze estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20632\u201320641 (2023)","DOI":"10.1109\/ICCV51070.2023.01886"},{"key":"27_CR11","doi-asserted-by":"publisher","first-page":"7509","DOI":"10.1109\/TPAMI.2024.3393571","volume":"46","author":"Y Cheng","year":"2024","unstructured":"Cheng, Y., Wang, H., Bao, Y., Lu, F.: Appearance-based gaze estimation with deep learning: a review and benchmark. IEEE Trans. Pattern Anal. Mach. Intell. 46, 7509\u20137528 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, Y., et al.: What do you see in vehicle? Comprehensive vision solution for in-vehicle gaze estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1556\u20131565 (2024)","DOI":"10.1109\/CVPR52733.2024.00154"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., Sun, J.: RepVGG: making VGG-style convnets great again. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13733\u201313742 (2021)","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"27_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1007\/978-3-030-01249-6_21","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Fischer","year":"2018","unstructured":"Fischer, T., Chang, H.J., Demiris, Y.: RT-GENE: real-time eye gaze estimation in natural environments. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 339\u2013357. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_21"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Funes\u00a0Mora, K.A., Monay, F., Odobez, J.M.: EYEDIAP: a database for the development and evaluation of gaze estimation algorithms from RGB and RGB-D cameras. In: Proceedings of the Symposium on Eye Tracking Research and Applications, pp. 255\u2013258 (2014)","DOI":"10.1145\/2578153.2578190"},{"key":"27_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121688","volume":"237","author":"J Gao","year":"2024","unstructured":"Gao, J., Geng, X., Zhang, Y., Wang, R., Shao, K.: Augmented weighted bidirectional feature pyramid network for marine object detection. Expert Syst. Appl. 237, 121688 (2024)","journal-title":"Expert Syst. Appl."},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Gideon, J., Su, S., Stent, S.: Unsupervised multi-view gaze representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5001\u20135009 (2022)","DOI":"10.1109\/CVPRW56347.2022.00548"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Hempel, T., Abdelrahman, A.A., Al-Hamadi, A.: 6D rotation representation for unconstrained head pose estimation. In: 2022 IEEE International Conference on Image Processing (ICIP), pp. 2496\u20132500. IEEE (2022)","DOI":"10.1109\/ICIP46576.2022.9897219"},{"key":"27_CR19","doi-asserted-by":"publisher","first-page":"2335","DOI":"10.1109\/TIP.2023.3253253","volume":"32","author":"P Her","year":"2023","unstructured":"Her, P., Manderle, L., Dias, P.A., Medeiros, H., Odone, F.: Uncertainty-aware gaze tracking for assisted living environments. IEEE Trans. Image Process. 32, 2335\u20132347 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Hisadome, Y., Wu, T., Qin, J., Sugano, Y.: Rotation-constrained cross-view feature fusion for multi-view appearance-based gaze estimation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5985\u20135994 (2024)","DOI":"10.1109\/WACV57701.2024.00588"},{"issue":"2","key":"27_CR21","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1080\/17483107.2022.2099988","volume":"19","author":"YH Hsieh","year":"2024","unstructured":"Hsieh, Y.H., Granlund, M., Odom, S.L., Hwang, A.W., Hemmingsson, H.: Increasing participation in computer activities using eye-gaze assistive technology for children with complex needs. Disabil. Rehabil. Assist. Technol. 19(2), 492\u2013505 (2024)","journal-title":"Disabil. Rehabil. Assist. Technol."},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Huang, S., Lu, Z., Cheng, R., He, C.: FAPN: feature-aligned pyramid network for dense image prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 864\u2013873 (2021)","DOI":"10.1109\/ICCV48922.2021.00090"},{"issue":"1","key":"27_CR23","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1109\/TIV.2022.3141071","volume":"8","author":"S Jha","year":"2022","unstructured":"Jha, S., Busso, C.: Estimation of driver\u2019s gaze region from head position and orientation using probabilistic confidence regions. IEEE Trans. Intell. Veh. 8(1), 59\u201372 (2022)","journal-title":"IEEE Trans. Intell. Veh."},{"key":"27_CR24","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":"27_CR25","doi-asserted-by":"crossref","unstructured":"Kim, T., Kim, K., Lee, J., Cha, D., Lee, J., Kim, D.: Revisiting image pyramid structure for high resolution salient object detection. In: Proceedings of the Asian Conference on Computer Vision, pp. 108\u2013124 (2022)","DOI":"10.1007\/978-3-031-26293-7_16"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Lee, H.S., Weidner, F., Sidenmark, L., Gellersen, H.: Snap, pursuit and gain: virtual reality viewport control by gaze. In: Proceedings of the CHI Conference on Human Factors in Computing Systems, pp. 1\u201314 (2024)","DOI":"10.1145\/3613904.3642838"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: MViTv2: improved multiscale vision transformers for classification and detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4804\u20134814 (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"27_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102517","volume":"80","author":"X Luo","year":"2022","unstructured":"Luo, X., et al.: Semi-supervised medical image segmentation via uncertainty rectified pyramid consistency. Med. Image Anal. 80, 102517 (2022)","journal-title":"Med. Image Anal."},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Nagpure, V., Okuma, K.: Searching efficient neural architecture with multi-resolution fusion transformer for appearance-based gaze estimation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 890\u2013899 (2023)","DOI":"10.1109\/WACV56688.2023.00095"},{"key":"27_CR30","first-page":"24261","volume":"34","author":"IO Tolstikhin","year":"2021","unstructured":"Tolstikhin, I.O., et al.: MLP-mixer: an all-MLP architecture for vision. Adv. Neural. Inf. Process. Syst. 34, 24261\u201324272 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"9","key":"27_CR31","doi-asserted-by":"publisher","first-page":"3154","DOI":"10.3390\/s22093154","volume":"22","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Yuan, G., Fu, X.: Driver\u2019s head pose and gaze zone estimation based on multi-zone templates registration and multi-frame point cloud fusion. Sensors 22(9), 3154 (2022)","journal-title":"Sensors"},{"key":"27_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.103945","volume":"240","author":"X Xiang","year":"2024","unstructured":"Xiang, X., Yin, H., Qiao, Y., El Saddik, A.: Temporal adaptive feature pyramid network for action detection. Comput. Vis. Image Underst. 240, 103945 (2024)","journal-title":"Comput. Vis. Image Underst."},{"key":"27_CR33","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1007\/978-3-031-44195-0_14","volume-title":"ICANN 2023","author":"X Yin","year":"2023","unstructured":"Yin, X., Yu, Z., Fei, Z., Lv, W., Gao, X.: PE-YOLO: pyramid enhancement network for dark object detection. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds.) ICANN 2023. LNCS, vol. 14260, pp. 163\u2013174. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-44195-0_14"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Yun, J.S., Na, Y., Kim, H.H., Kim, H.I., Yoo, S.B.: HAZE-Net: high-frequency attentive super-resolved gaze estimation in low-resolution face images. In: Proceedings of the Asian Conference on Computer Vision, pp. 3361\u20133378 (2022)","DOI":"10.1007\/978-3-031-26348-4_9"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, C., Chen, T., Nedungadi, R.R., Shaffer, E., Soltanaghai, E.: FocusFlow: leveraging focal depth for gaze interaction in virtual reality. In: Adjunct Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pp.\u00a01\u20134 (2023)","DOI":"10.1145\/3586182.3615818"},{"key":"27_CR36","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"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, M.: Dynamic feature pyramid networks for object detection. In: Fifteenth International Conference on Signal Processing Systems (ICSPS 2023), vol. 13091, pp. 503\u2013511. SPIE (2024)","DOI":"10.1117\/12.3022812"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, W., Deng, H.: Monocular free-head 3D gaze tracking with deep learning and geometry constraints. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3143\u20133152 (2017)","DOI":"10.1109\/ICCV.2017.341"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78104-9_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T23:30:24Z","timestamp":1733095824000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78104-9_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031781032","9783031781049"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78104-9_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}