{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T13:05:48Z","timestamp":1777381548912,"version":"3.51.4"},"reference-count":48,"publisher":"SAGE Publications","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AIS"],"published-print":{"date-parts":[[2017,2,22]]},"DOI":"10.3233\/ais-170424","type":"journal-article","created":{"date-parts":[[2017,2,21]],"date-time":"2017-02-21T11:31:41Z","timestamp":1487676701000},"page":"225-238","source":"Crossref","is-referenced-by-count":1,"title":["Computer vision analysis for children\u2019s social play classification in peer-play scenarios"],"prefix":"10.1177","volume":"9","author":[{"given":"Dingrui","family":"Duan","sequence":"first","affiliation":[{"name":"Key Laboratory of Machine Perception, Peking University, China. E-mails:\u00a0ddr@pku.edu.cn,\u00a0cjs@cis.pku.edu.cn,\u00a0zha@cis.pku.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingning","family":"Huang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Machine Perception, Peking University, China. E-mails:\u00a0ddr@pku.edu.cn,\u00a0cjs@cis.pku.edu.cn,\u00a0zha@cis.pku.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinshi","family":"Cui","sequence":"additional","affiliation":[{"name":"Key Laboratory of Machine Perception, Peking University, China. E-mails:\u00a0ddr@pku.edu.cn,\u00a0cjs@cis.pku.edu.cn,\u00a0zha@cis.pku.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Psychology and Beijing Key Laboratory of Behavior and Mental Health, Peking University, China. E-mail:\u00a0liwang@pku.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Psychology and Beijing Key Laboratory of Behavior and Mental Health, Peking University, China. E-mail:\u00a0liwang@pku.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbin","family":"Zha","sequence":"additional","affiliation":[{"name":"Key Laboratory of Machine Perception, Peking University, China. E-mails:\u00a0ddr@pku.edu.cn,\u00a0cjs@cis.pku.edu.cn,\u00a0zha@cis.pku.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/AIS-170424_ref1","unstructured":"M.\u00a0Argyle, Social Interaction, Travistock Publications, 1969."},{"key":"10.3233\/AIS-170424_ref2","doi-asserted-by":"crossref","unstructured":"S.\u00a0Ba and J.-M.\u00a0Odobez, Head pose tracking and focus of attention recognition algorithms in meeting rooms, in: Multimodal Technologies for Perception of Humans, Vol.\u00a0200, pp.\u00a0345\u2013357.","DOI":"10.1007\/978-3-540-69568-4_32"},{"key":"10.3233\/AIS-170424_ref3","doi-asserted-by":"crossref","unstructured":"B.\u00a0Benfold and I.\u00a0Reid, Guiding visual surveillance by tracking human attention, in: British Machine Vision Conference, 2009.","DOI":"10.5244\/C.23.14"},{"key":"10.3233\/AIS-170424_ref4","doi-asserted-by":"crossref","unstructured":"I.\u00a0Chakraborty, H.\u00a0Cheng and O.\u00a0Javed, 3D visual proxemics: Recognizing human interactions in 3D from a single image, in: IEEE Conference on Computer Vision and Pattern Recognition, 2013, 3406\u20133413.","DOI":"10.1109\/CVPR.2013.437"},{"key":"10.3233\/AIS-170424_ref5","doi-asserted-by":"crossref","unstructured":"C.-W.\u00a0Chen, R.\u00a0Ugarte, C.\u00a0Wu and H.\u00a0Aghajan, Discovering social interactions in real work environments, in: IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, 2011, pp.\u00a0933\u2013938.","DOI":"10.1109\/FG.2011.5771376"},{"key":"10.3233\/AIS-170424_ref6","doi-asserted-by":"crossref","unstructured":"Y.-Y.\u00a0Chen, W.\u00a0Hsu and H.-Y.\u00a0Liao, Discovering informative social subgraphs and predicting pairwise relationships from group photos, in: 20th ACM International Conference on Multimedia, 2012, 669\u2013678.","DOI":"10.1145\/2393347.2393439"},{"key":"10.3233\/AIS-170424_ref7","unstructured":"H.\u00a0Choi, C.\u00a0Yu, L.\u00a0Smith and O.\u00a0Sporns, From data streams to information flow: Information exchange in child\u2013parent interaction, in: Proceedings of the 33rd Annual Conference of the Cognitive Science Society, 2011, pp.\u00a0868\u2013873."},{"key":"10.3233\/AIS-170424_ref8","doi-asserted-by":"crossref","unstructured":"W.\u00a0Choi, Y.-W.\u00a0Chao, C.\u00a0Pantofaru and S.\u00a0Savarese, Discovering groups of people in images, in: European Conference on Computer Vision, 2014, pp.\u00a0417\u2013433.","DOI":"10.1007\/978-3-319-10593-2_28"},{"key":"10.3233\/AIS-170424_ref9","doi-asserted-by":"crossref","first-page":"1242","DOI":"10.1109\/TPAMI.2013.220","article-title":"Understanding collective activities of people from videos","volume":"36","author":"Choi","year":"2014","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.3233\/AIS-170424_ref10","first-page":"177","author":"Cupillard","year":"2002","journal-title":"Sixth IEEE Workshop on Applications of Computer Vision"},{"key":"10.3233\/AIS-170424_ref11","doi-asserted-by":"crossref","unstructured":"C.\u00a0Direko\u011flu and N.\u00a0O\u2019Connor, Team activity recognition in sports, in: 12th European Conference on Computer Vision, 2012, 69\u201383.","DOI":"10.1007\/978-3-642-33786-4_6"},{"key":"10.3233\/AIS-170424_ref12","doi-asserted-by":"publisher","DOI":"10.1109\/VSPETS.2005.1570899"},{"key":"10.3233\/AIS-170424_ref13","doi-asserted-by":"crossref","unstructured":"L.\u00a0Dong, H.\u00a0Di, L.\u00a0Tao, G.\u00a0Xu et al., Visual focus of attention recognition in the ambient kitchen, in: Proc. of the Asian Conference on Computer Vision, Vol.\u00a03, 2009, pp.\u00a0548\u2013559.","DOI":"10.1007\/978-3-642-12297-2_53"},{"key":"10.3233\/AIS-170424_ref14","first-page":"760","author":"Duan","year":"2013","journal-title":"2nd IAPR Asian Conference on Pattern Recognition"},{"key":"10.3233\/AIS-170424_ref15","doi-asserted-by":"crossref","unstructured":"A.\u00a0Fathi, J.\u00a0Hodgins and J.\u00a0Rehg, Social interactions: A first-person perspective, in: IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp.\u00a01226\u20131233.","DOI":"10.1109\/CVPR.2012.6247805"},{"key":"10.3233\/AIS-170424_ref16","doi-asserted-by":"crossref","unstructured":"E.\u00a0Hall, A system for the notation of proxemic behavior, American Anthropologist (1963).","DOI":"10.1525\/aa.1963.65.5.02a00020"},{"key":"10.3233\/AIS-170424_ref17","doi-asserted-by":"crossref","unstructured":"J.\u00a0Hashemi, M.\u00a0Tepper, T.\u00a0Spina, A.\u00a0Esler et al., Computer vision tools for low-cost and noninvasive measurement of autism-related behaviors in infants, Autism Research and Treatment (2014).","DOI":"10.1155\/2014\/935686"},{"key":"10.3233\/AIS-170424_ref18","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Huang, D.\u00a0Duan, J.\u00a0Cui, F.\u00a0Davoine et al., Joint estimation of head pose and visual focus of attention, in: IEEE International Conference on Image Processing, 2014, pp.\u00a03332\u20133336.","DOI":"10.1109\/ICIP.2014.7025674"},{"key":"10.3233\/AIS-170424_ref20","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Ji, G.\u00a0Ye and H.\u00a0Cheng, Interactive body part contrast mining for human interaction recognition, in: IEEE International Conference on Multimedia and Expo Workshops, 2014.","DOI":"10.1109\/ICMEW.2014.6890714"},{"key":"10.3233\/AIS-170424_ref21","unstructured":"J.\u00a0Kagan, Galen\u2019s Prophecy, Basic Books, New York, 1994."},{"key":"10.3233\/AIS-170424_ref22","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1111\/j.1467-8624.1998.tb06171.x","article-title":"Childhood derivatives of high and low reactivity in infancy","volume":"69","author":"Kagan","year":"1998","journal-title":"Child Development"},{"key":"10.3233\/AIS-170424_ref23","doi-asserted-by":"crossref","unstructured":"T.\u00a0Lan, L.\u00a0Sigal and G.\u00a0Mori, Social roles in hierarchical models for human activity recognition, in: IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp.\u00a01354\u20131361.","DOI":"10.1109\/CVPR.2012.6247821"},{"issue":"8","key":"10.3233\/AIS-170424_ref24","doi-asserted-by":"crossref","first-page":"1549","DOI":"10.1109\/TPAMI.2011.228","article-title":"Discriminative latent models for recognizing contextual group activities","volume":"34","author":"Lan","year":"2012","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.3233\/AIS-170424_ref25","doi-asserted-by":"crossref","unstructured":"R.\u00a0Li, R.\u00a0Chellappa and S.\u00a0Zhou, Learning multi-modal densities on discriminative temporal interaction manifold for group activity recognition, in: IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp.\u00a02450\u20132457.","DOI":"10.1109\/CVPR.2009.5206676"},{"key":"10.3233\/AIS-170424_ref26","doi-asserted-by":"crossref","unstructured":"J.\u00a0Liu, J.\u00a0Luo and M.\u00a0Shah, Recognizing realistic actions from videos \u201cin the wild\u201d, in: IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp.\u00a01996\u20132003.","DOI":"10.1109\/CVPR.2009.5206744"},{"key":"10.3233\/AIS-170424_ref27","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1007\/s11263-013-0655-7","article-title":"Detecting people looking at each other in videos","volume":"106","author":"Marin-Jimenez","year":"2013","journal-title":"International Journal of Computer Vision"},{"key":"10.3233\/AIS-170424_ref28","doi-asserted-by":"crossref","unstructured":"F.\u00a0Martinez, A.\u00a0Carbone and E.\u00a0Pissaloux, Combining first-person and third-person gaze for attention recognition, in: 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, 2013.","DOI":"10.1109\/FG.2013.6553735"},{"key":"10.3233\/AIS-170424_ref29","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Nagai, A.\u00a0Nakatani, S.\u00a0Qin, H.\u00a0Fukuyama et al., Co-development of information transfer within and between infant and caregiver, in: 2nd IEEE International Conference on Development and Learning and on Epigenetic Robotics, 2012.","DOI":"10.1109\/DevLrn.2012.6400879"},{"key":"10.3233\/AIS-170424_ref30","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/s11263-007-0122-4","article-title":"Unsupervised learning of human action categories using spatio-temporal words","volume":"79","author":"Niebles","year":"2008","journal-title":"International Journal of Computer Vision"},{"key":"10.3233\/AIS-170424_ref31","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1016\/j.cviu.2010.11.013","article-title":"A wearable gaze tracking system for children in unconstrained environments","volume":"115","author":"Noris","year":"2011","journal-title":"Computer Vision and Image Understanding"},{"key":"10.3233\/AIS-170424_ref32","doi-asserted-by":"crossref","unstructured":"W.\u00a0Ouyang, X.\u00a0Zeng and X.\u00a0Wang, Modeling mutual visibility relationship in pedestrian detection, in: IEEE Conference on Computer Vision and Pattern Recognition, 2013, pp.\u00a03222\u20133229.","DOI":"10.1109\/CVPR.2013.414"},{"key":"10.3233\/AIS-170424_ref33","doi-asserted-by":"crossref","unstructured":"H.\u00a0Park, E.\u00a0Jain and Y.\u00a0Sheikh, Predicting primary gaze behavior using social saliency fields, in: IEEE International Conference on Computer Vision, 2013, pp.\u00a03503\u20133510.","DOI":"10.1109\/ICCV.2013.435"},{"key":"10.3233\/AIS-170424_ref34","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1080\/09540090802091891","article-title":"Social coordination in toddler\u2019s word learning: Interacting systems of perception and action","volume":"20","author":"Pereira","year":"2008","journal-title":"Connection Science"},{"key":"10.3233\/AIS-170424_ref35","unstructured":"G.\u00a0Pusiol, L.\u00a0Soriano, L.\u00a0Fei-Fei and M.\u00a0Frank, Discovering the signatures of joint attention in child\u2013caregiver interaction, in: The Annual Meeting of the Cognitive Science Society, 2014."},{"key":"10.3233\/AIS-170424_ref36","doi-asserted-by":"crossref","unstructured":"S.\u00a0Rajagopalan, O.V.\u00a0Murthy, R.\u00a0Goecke and A.\u00a0Rozga, Play with me\u00a0\u2013 Measuring a child\u2019s engagement in a social interaction, in: 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), 2015, pp.\u00a01\u20138.","DOI":"10.1109\/FG.2015.7163129"},{"key":"10.3233\/AIS-170424_ref37","doi-asserted-by":"crossref","unstructured":"V.\u00a0Ramanathan, B.\u00a0Yao and L.\u00a0Fei-Fei, Social role discovery in human events, in: IEEE Conference on Computer Vision and Pattern Recognition, 2013, pp.\u00a02475\u20132482.","DOI":"10.1109\/CVPR.2013.320"},{"key":"10.3233\/AIS-170424_ref38","unstructured":"J.\u00a0Rehg, Behavior imaging: Using computer vision to study autism, in: IAPR Conference on Machine Vision Applications, 2011."},{"key":"10.3233\/AIS-170424_ref39","doi-asserted-by":"crossref","unstructured":"J.\u00a0Rehg, G.\u00a0Abowd, A.\u00a0Rozga, M.\u00a0Romero et al., Decoding children\u2019s social behavior, in: IEEE Conference on Computer Vision and Pattern Recognition, 2013, pp.\u00a03414\u20133421.","DOI":"10.1109\/CVPR.2013.438"},{"key":"10.3233\/AIS-170424_ref40","unstructured":"K.\u00a0Rubin, The Play Observation Scale, 1989."},{"issue":"1","key":"10.3233\/AIS-170424_ref41","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1146\/annurev.psych.60.110707.163642","article-title":"Social withdrawal in childhood","volume":"60","author":"Rubin","year":"2009","journal-title":"Annual Review of Psychology"},{"key":"10.3233\/AIS-170424_ref42","doi-asserted-by":"crossref","unstructured":"M.\u00a0Ryoo and J.\u00a0Aggarwal, Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities, in: IEEE 12th International Conference on Computer Vision, 2009, pp.\u00a01593\u20131600.","DOI":"10.1109\/ICCV.2009.5459361"},{"key":"10.3233\/AIS-170424_ref43","doi-asserted-by":"crossref","unstructured":"S.\u00a0Savarese, A.\u00a0DelPozo, J.\u00a0Niebles and L.\u00a0Fei-Fei, Spatial-temporal correlations for unsupervised action classification, in: IEEE Workshop on Motion and Video Computing, 2008.","DOI":"10.1109\/WMVC.2008.4544068"},{"key":"10.3233\/AIS-170424_ref44","doi-asserted-by":"crossref","unstructured":"L.\u00a0Tian, D.\u00a0Duan, J.\u00a0Cui and L.\u00a0Wang, Video based children\u2019s social behavior classification in peer-play scenarios, in: 2nd IAPR Asian Conference on Pattern Recognition (ACPR), 2013, pp.\u00a0770\u2013774.","DOI":"10.1109\/ACPR.2013.180"},{"key":"10.3233\/AIS-170424_ref45","doi-asserted-by":"crossref","unstructured":"M.\u00a0Voit and R.\u00a0Stiefelhagen, Deducing the visual focus of attention from head pose estimation in dynamic multi-view meeting scenarios, in: ACM International Conference on Multimodal Interaction, 2008.","DOI":"10.1145\/1452392.1452425"},{"key":"10.3233\/AIS-170424_ref46","doi-asserted-by":"crossref","unstructured":"P.\u00a0Wang, G.\u00a0Abowd and J.\u00a0Rehg, Quasi-periodic event analysis for social game retrieval, in: IEEE 12th International Conference on Computer Vision, 2009, pp.\u00a0112\u2013119.","DOI":"10.1109\/ICCV.2009.5459151"},{"key":"10.3233\/AIS-170424_ref47","doi-asserted-by":"crossref","unstructured":"T.\u00a0Yu, S.-N.\u00a0Lim, K.\u00a0Patwardhan and N.\u00a0Krahnstoever, Monitoring, recognizing and discovering social networks, in: IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp.\u00a01462\u20131469.","DOI":"10.1109\/CVPR.2009.5206526"},{"key":"10.3233\/AIS-170424_ref48","unstructured":"D.\u00a0Zhang, D.\u00a0Gatica-Perez, S.\u00a0Bengio, I.\u00a0McCowan et al., Modeling individual and group actions in meetings: A two-layer HMM framework, in: Conference on Computer Vision and Pattern Recognition Workshop, 2004."},{"key":"10.3233\/AIS-170424_ref49","unstructured":"B.\u00a0Zhou, X.\u00a0Wang and X.\u00a0Tang, Understanding collective crowd behaviors: Learning a mixture model of dynamic pedestrian-agents, in: IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp.\u00a02871\u20132878."}],"container-title":["Journal of Ambient Intelligence and Smart Environments"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/AIS-170424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T09:21:02Z","timestamp":1777368062000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/AIS-170424"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2,22]]},"references-count":48,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.3233\/ais-170424","relation":{},"ISSN":["1876-1372","1876-1364"],"issn-type":[{"value":"1876-1372","type":"electronic"},{"value":"1876-1364","type":"print"}],"subject":[],"published":{"date-parts":[[2017,2,22]]}}}