{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T07:22:08Z","timestamp":1785741728007,"version":"3.56.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031263156","type":"print"},{"value":"9783031263163","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-26316-3_22","type":"book-chapter","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:02:32Z","timestamp":1677657752000},"page":"363-378","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["MGTR: End-to-End Mutual Gaze Detection with\u00a0Transformer"],"prefix":"10.1007","author":[{"given":"Hang","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengxi","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingtai","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,3,2]]},"reference":[{"issue":"2","key":"22_CR1","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/BF01000006","volume":"10","author":"A Abele","year":"1986","unstructured":"Abele, A.: Functions of gaze in social interaction: communication and monitoring. J. Nonverbal Behav. 10(2), 83\u2013101 (1986)","journal-title":"J. Nonverbal Behav."},{"issue":"1","key":"22_CR2","doi-asserted-by":"publisher","first-page":"25","DOI":"10.5898\/JHRI.6.1.Admoni","volume":"6","author":"H Admoni","year":"2017","unstructured":"Admoni, H., Scassellati, B.: Social eye gaze in human-robot interaction: a review. J. Hum.-Robot Interact. 6(1), 25\u201363 (2017)","journal-title":"J. Hum.-Robot Interact."},{"key":"22_CR3","unstructured":"Argyle, M., Cook, M.: Gaze and mutual gaze (1976)"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Bello, I., Zoph, B., Vaswani, A., Shlens, J., Le, Q.V.: Attention augmented convolutional networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3286\u20133295 (2019)","DOI":"10.1109\/ICCV.2019.00338"},{"key":"22_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Doosti, B., Chen, C.H., Vemulapalli, R., Jia, X., Zhu, Y., Green, B.: Boosting image-based mutual gaze detection using pseudo 3D gaze. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 1273\u20131281 (2021)","DOI":"10.1609\/aaai.v35i2.16215"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Fan, L., Chen, Y., Wei, P., Wang, W., Zhu, S.C.: Inferring shared attention in social scene videos. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6460\u20136468. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00676"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Fan, L., Wang, W., Huang, S., Tang, X., Zhu, S.C.: Understanding human gaze communication by spatio-temporal graph reasoning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5724\u20135733 (2019)","DOI":"10.1109\/ICCV.2019.00582"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"1","key":"22_CR10","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1037\/0033-2909.100.1.78","volume":"100","author":"CL Kleinke","year":"1986","unstructured":"Kleinke, C.L.: Gaze and eye contact: a research review. Psychol. Bull. 100(1), 78 (1986)","journal-title":"Psychol. Bull."},{"issue":"6","key":"22_CR11","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017)","journal-title":"Commun. ACM"},{"issue":"1\u20132","key":"22_CR12","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logist. Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logist. Q."},{"key":"22_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-030-20893-6_3","volume-title":"Computer Vision \u2013 ACCV 2018","author":"D Lian","year":"2019","unstructured":"Lian, D., Yu, Z., Gao, S.: Believe it or not, we know what you are looking at! In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11363, pp. 35\u201350. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20893-6_3"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"22_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"22_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot MultiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"22_CR17","unstructured":"Loeb, B.K.: Mutual eye contact and social interaction and their relationship to affiliation (1972)"},{"key":"22_CR18","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"22_CR19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3048482","author":"MJ Mar\u00edn-Jim\u00e9nez","year":"2021","unstructured":"Mar\u00edn-Jim\u00e9nez, M.J., Kalogeiton, V., Medina-Su\u00e1rez, P., Zisserman, A.: LAEO-Net++: revisiting people looking at each other in videos. IEEE Trans. Pattern Anal. Mach. Intell. (2021). https:\/\/doi.org\/10.1109\/TPAMI.2020.3048482","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Marin-Jimenez, M.J., Kalogeiton, V., Medina-Suarez, P., Zisserman, A.: LAEO-Net: revisiting people looking at each other in videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3477\u20133485 (2019)","DOI":"10.1109\/CVPR.2019.00359"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Murray, N., Marchesotti, L., Perronnin, F.: AVA: a large-scale database for aesthetic visual analysis. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2408\u20132415. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"22_CR22","unstructured":"Parmar, N., et al.: Image transformer. In: International Conference on Machine Learning, pp. 4055\u20134064. PMLR (2018)"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"22_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhu, X., Lei, Z., Shi, H., Wang, X., Li, S.Z.: S3FD: single shot scale-invariant face detector. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 192\u2013201 (2017)","DOI":"10.1109\/ICCV.2017.30"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-IoU loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12993\u201313000 (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"issue":"10","key":"22_CR28","doi-asserted-by":"publisher","first-page":"3637","DOI":"10.1109\/TCSVT.2019.2940479","volume":"30","author":"N Zhuang","year":"2019","unstructured":"Zhuang, N., et al.: Muggle: multi-stream group gaze learning and estimation. IEEE Trans. Circuits Syst. Video Technol. 30(10), 3637\u20133650 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Zou, C., et al.: End-to-end human object interaction detection with HOI transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11825\u201311834 (2021)","DOI":"10.1109\/CVPR46437.2021.01165"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26316-3_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:26:50Z","timestamp":1677659210000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26316-3_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031263156","9783031263163"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26316-3_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"2 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"277","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"For the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}