{"type":"ScholarlyArticle","title":"Predicting dominance in multi-person videos","authors":[{"name":"Chongyang Bai","slug":"chongyang-bai","given":"Chongyang","family":"Bai","affiliation":"Dartmouth College"},{"name":"Maksim Bolonkin","slug":"maksim-bolonkin","given":"Maksim","family":"Bolonkin","affiliation":"Dartmouth College"},{"name":"Srijan Kumar","slug":"srijan-kumar","given":"Srijan","family":"Kumar","affiliation":"Stanford University"},{"name":"Jure Leskovec","slug":"jure-leskovec","given":"Jure","family":"Leskovec","affiliation":"Stanford University"},{"name":"Judee Burgoon","slug":"judee-burgoon","given":"Judee","family":"Burgoon","affiliation":"University of Arizona"},{"name":"Norah Dunbar","slug":"norah-dunbar","given":"Norah","family":"Dunbar","affiliation":"University of California Santa Barbara"},{"name":"V. S. Subrahmanian","slug":"v-s-subrahmanian","given":"V. S.","family":"Subrahmanian","affiliation":"Dartmouth College"}],"abstract":"We consider the problems of predicting (i) the most dominant person in a group of people, and (ii) the more dominant of a pair of people, from videos depicting group interactions. We introduce a novel family of variables called Dominance Rank. We combine features not previously used for dominance prediction (e.g., facial action units, emotions), with a novel ensemble-based approach to solve these two problems. We test our models against four competing algorithms in the literature on two datasets and show that our results improve past performance. We show 2.4% to 16.7% improvement in AUC compared to baselines on one dataset, and a gain of 0.6% to 8.8% in accuracy on the other. Ablation testing shows that Dominance Rank features play a key role.","doi":"10.24963/ijcai.2019/645","url":"https://ijcai.org/proceedings/2019/645","pdf":"https://ijcai.org/proceedings/2019/0645.pdf","markdown":"https://ijcai.org/proceedings/2019/645.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/645","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Multidisciplinary Topics and Applications","track":"Main track","number":645,"pages":{"first":4643,"last":4650},"keywords":["Machine Learning Applications: Applications of Supervised Learning","Multidisciplinary Topics and Applications: Social Sciences","Computer Vision: Video: Events, Activities and Surveillance"],"videos":[],"references":[{"position":1,"raw":"[Aran and Gatica-Perez, 2010] Oya Aran and Daniel Gatica- Perez. Fusing audio-visual nonverbal cues to detect dom- inant people in group conversations. In 2010 20th Inter- national Conference on Pattern Recognition, pages 3687- 3690, Aug 2010.","title":"Fusing audio-visual nonverbal cues to detect dominant people in group conversations","authors":"Aran, Gatica-Perez ;, Oya Aran, Daniel Gatica-Perez","year":"2010","venue":"2010 20th International Conference on Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Aran and Gatica-Perez, 2013] Oya Aran and Daniel Gatica- Perez. One of a kind: Inferring personality impressions in meetings. In Proceedings of the 15th ACM on Interna- tional Conference on Multimodal Interaction, ICMI '13, pages 11-18, New York, NY, USA, 2013.","title":"One of a kind: Inferring personality impressions in meetings","authors":"Aran, Gatica-Perez ;, Oya Aran, Daniel Gatica-Perez","year":"2013","venue":"Proceedings of the 15th ACM on International Conference on Multimodal Interaction, ICMI '13","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ba and Odobez, 2011] Sileye O Ba and Jean-Marc Odobez. Multiperson visual focus of attention from head pose and meeting contextual cues. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(1):101-116, 2011.","title":"Sileye O Ba and Jean-Marc Odobez. Multiperson visual focus of attention from head pose and meeting contextual cues","authors":"Odobez Ba","year":"2011","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Baltrusaitis et al., 2018] Tadas Baltrusaitis, Amirali Bagher Zadeh, Yao Chong Lim, and Louis-Philippe Morency. Openface 2.0: Facial behavior analysis toolkit. In 13th IEEE International Conference on Automatic Face & Ges- ture Recognition (FG 2018), pages 59-66, 2018.","title":"Openface 2.0: Facial behavior analysis toolkit","authors":"Tadas Baltrusaitis, Amirali Bagher Zadeh, Yao, Chong Lim, Louis-Philippe Morency","year":"2018","venue":"13th IEEE International Conference on Automatic Face & Gesture Recognition","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Beyan et al., 2018] Cigdem Beyan, Francesca Capozzi, Cristina Becchio, and Vittorio Murino. Prediction of the leadership style of an emergent leader using audio and vi- sual nonverbal features. IEEE Transactions on Multime- dia, 20(2):441-456, 2018.","title":"Prediction of the leadership style of an emergent leader using audio and visual nonverbal features","authors":"Cigdem Beyan, Francesca Capozzi, Cristina Becchio, Vittorio Murino","year":"2018","venue":"IEEE Transactions on Multimedia","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Davis and Mermelstein, 1980] Steven B. Davis and Paul Mermelstein. Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions on Acoustics, Speech, and Signal Processing, 28(4):357-366, August 1980.","title":"Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences","authors":"Steven B Davis, Paul Mermelstein","year":"1980","venue":"IEEE Transactions on Acoustics, Speech, and Signal Processing","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dillard and Tusing, 2006] James Price Dillard and Kyle James Tusing. The sounds of dominance: Vocal precursors of perceived dominance during interper- sonal influence. Human Communication Research, 26(1):148-172, 01 2006.","title":"The sounds of dominance: Vocal precursors of perceived dominance during interpersonal influence","authors":"Tusing ; Dillard, Price James, Kyle Dillard, Tusing James","year":"2006","venue":"Human Communication Research","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dovidio and Ellyson, 1982] John F. Dovidio and Steve L. Ellyson. Decoding visual dominance: Attributions of power based on relative percentages of looking while speaking and looking while listening. Social Psychology Quarterly, 45(2):106-113, 1982.","title":"Decoding visual dominance: Attributions of power based on relative percentages of looking while speaking and looking while listening","authors":"John F Dovidio, Steve L Ellyson","year":"1982","venue":"Social Psychology Quarterly","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Dunbar and Burgoon, 2005] Norah Dunbar and Judee Bur- goon. Perceptions of power and interactional dominance in interpersonal relationships. Journal of Social and Per- sonal Relationships, 22:207-233, 04 2005.","title":"Norah Dunbar and Judee Burgoon. Perceptions of power and interactional dominance in interpersonal relationships","authors":"Burgoon Dunbar","year":"2005","venue":"Journal of Social and Personal Relationships","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Escalera et al., 2012] Sergio Escalera, Xavier Baró, Jordi Vitria, Petia Radeva, and Bogdan Raducanu. Social net- work extraction and analysis based on multimodal dyadic interaction. Sensors, 12(2):1702-1719, 2012.","title":"Social network extraction and analysis based on multimodal dyadic interaction","authors":"Sergio Escalera, Xavier Baró, Jordi Vitria, Petia Radeva, Bogdan Raducanu","year":"2012","venue":"Sensors","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hall et al., 2005] Judith A Hall, Erik J Coats, and Lavonia Smith LeBeau. Nonverbal behavior and the vertical di- mension of social relations: A meta-analysis. Psychologi- cal bulletin, 131:898-924, 12 2005.","title":"Nonverbal behavior and the vertical dimension of social relations: A meta-analysis","authors":"Judith A Hall, Erik J Coats, Lavonia Smith Lebeau","year":"2005","venue":"Psychological bulletin","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Jayagopi et al., 2009] Dinesh Babu Jayagopi, Hayley Hung, Chuohao Yeo, and Daniel Gatica-Perez. Modeling dom- inance in group conversations using nonverbal activity cues. IEEE Transactions on Audio, Speech, and Language Processing, 17(3):501-513, March 2009.","title":"Modeling dominance in group conversations using nonverbal activity cues","authors":"Dinesh Babu, Jayagopi, Hayley Hung, Chuohao Yeo, Daniel Gatica-Perez","year":"2009","venue":"IEEE Transactions on Audio, Speech, and Language Processing","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Okada et al., 2015] Shogo Okada, Oya Aran, and Daniel Gatica-Perez. Personality trait classification via co- occurrent multiparty multimodal event discovery. In Pro- ceedings of the 2015 ACM on International Conference on Multimodal Interaction, ICMI '15, pages 15-22, New York, NY, USA, 2015.","title":"Personality trait classification via cooccurrent multiparty multimodal event discovery","authors":"Shogo Okada, Oya Aran, Daniel Gatica-Perez","year":"2015","venue":"Proceedings of the 2015 ACM on International Conference on Multimodal Interaction, ICMI '15","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Okada et al., 2018] Shogo Okada, Laurent Son Nguyen, Oya Aran, and Daniel Gatica-Perez. Modeling dyadic and group impressions with inter-modal and inter-person fea- tures. ACM Transactions on Multimedia Computing, Com- munications, and Applications, 2018.","title":"Modeling dyadic and group impressions with inter-modal and inter-person features","authors":"Shogo Okada, Laurent, Son Nguyen, Oya Aran, Daniel Gatica-Perez","year":"2018","venue":"ACM Transactions on Multimedia Computing, Communications, and Applications","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Perronnin et al., 2010] Florent Perronnin, Jorge Sánchez, and Thomas Mensink. Improving the fisher kernel for large-scale image classification. In Proceedings of the 11th European Conference on Computer Vision: Part IV, ECCV'10, pages 143-156, Berlin, Heidelberg, 2010. Springer-Verlag.","title":"Improving the fisher kernel for large-scale image classification","authors":"Florent Perronnin, Jorge Sánchez, Thomas Mensink","year":"2010","venue":"Proceedings of the 11th European Conference on Computer Vision: Part IV, ECCV'10","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Rayner, 2009] Keith Rayner. Eye movements and attention in reading, scene perception, and visual search. The quar- terly journal of experimental psychology, 62(8):1457- 1506, 2009.","title":"Eye movements and attention in reading, scene perception, and visual search","authors":"Keith Rayner","year":"2009","venue":"The quarterly journal of experimental psychology","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Sanchez-Cortes et al., 2012] Dairazalia Sanchez-Cortes, Oya Aran, Marianne Schmid Mast, and Daniel Gatica- Perez. A nonverbal behavior approach to identify emergent leaders in small groups. IEEE Transactions on Multimedia, 14(3):816-832, June 2012.","title":"A nonverbal behavior approach to identify emergent leaders in small groups","authors":"Sanchez-Cortes","year":"2012","venue":"IEEE Transactions on Multimedia","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}