Predicting dominance in multi-person videos

Chongyang Bai, Maksim Bolonkin, Srijan Kumar, Jure Leskovec, Judee Burgoon, Norah Dunbar, V. S. Subrahmanian

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publicationProceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
EditorsSarit Kraus
PublisherInternational Joint Conferences on Artificial Intelligence
Pages4643-4650
Number of pages8
ISBN (Electronic)9780999241141
StatePublished - Jan 1 2019
Event28th International Joint Conference on Artificial Intelligence, IJCAI 2019 - Macao, China
Duration: Aug 10 2019Aug 16 2019

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
Volume2019-August
ISSN (Print)1045-0823

Conference

Conference28th International Joint Conference on Artificial Intelligence, IJCAI 2019
CountryChina
CityMacao
Period8/10/198/16/19

Fingerprint

Ablation
Testing

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Bai, C., Bolonkin, M., Kumar, S., Leskovec, J., Burgoon, J., Dunbar, N., & Subrahmanian, V. S. (2019). Predicting dominance in multi-person videos. In S. Kraus (Ed.), Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019 (pp. 4643-4650). (IJCAI International Joint Conference on Artificial Intelligence; Vol. 2019-August). International Joint Conferences on Artificial Intelligence.

Predicting dominance in multi-person videos. / Bai, Chongyang; Bolonkin, Maksim; Kumar, Srijan; Leskovec, Jure; Burgoon, Judee; Dunbar, Norah; Subrahmanian, V. S.

Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019. ed. / Sarit Kraus. International Joint Conferences on Artificial Intelligence, 2019. p. 4643-4650 (IJCAI International Joint Conference on Artificial Intelligence; Vol. 2019-August).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bai, C, Bolonkin, M, Kumar, S, Leskovec, J, Burgoon, J, Dunbar, N & Subrahmanian, VS 2019, Predicting dominance in multi-person videos. in S Kraus (ed.), Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019. IJCAI International Joint Conference on Artificial Intelligence, vol. 2019-August, International Joint Conferences on Artificial Intelligence, pp. 4643-4650, 28th International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, China, 8/10/19.
Bai C, Bolonkin M, Kumar S, Leskovec J, Burgoon J, Dunbar N et al. Predicting dominance in multi-person videos. In Kraus S, editor, Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019. International Joint Conferences on Artificial Intelligence. 2019. p. 4643-4650. (IJCAI International Joint Conference on Artificial Intelligence).
Bai, Chongyang ; Bolonkin, Maksim ; Kumar, Srijan ; Leskovec, Jure ; Burgoon, Judee ; Dunbar, Norah ; Subrahmanian, V. S. / Predicting dominance in multi-person videos. Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019. editor / Sarit Kraus. International Joint Conferences on Artificial Intelligence, 2019. pp. 4643-4650 (IJCAI International Joint Conference on Artificial Intelligence).
@inproceedings{790bfc1433de4af4b311ece13711405f,
title = "Predicting dominance in multi-person videos",
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.",
author = "Chongyang Bai and Maksim Bolonkin and Srijan Kumar and Jure Leskovec and Judee Burgoon and Norah Dunbar and Subrahmanian, {V. S.}",
year = "2019",
month = "1",
day = "1",
language = "English (US)",
series = "IJCAI International Joint Conference on Artificial Intelligence",
publisher = "International Joint Conferences on Artificial Intelligence",
pages = "4643--4650",
editor = "Sarit Kraus",
booktitle = "Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019",

}

TY - GEN

T1 - Predicting dominance in multi-person videos

AU - Bai, Chongyang

AU - Bolonkin, Maksim

AU - Kumar, Srijan

AU - Leskovec, Jure

AU - Burgoon, Judee

AU - Dunbar, Norah

AU - Subrahmanian, V. S.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85074916116&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074916116&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85074916116

T3 - IJCAI International Joint Conference on Artificial Intelligence

SP - 4643

EP - 4650

BT - Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019

A2 - Kraus, Sarit

PB - International Joint Conferences on Artificial Intelligence

ER -