Two-person interaction recognition via spatial multiple instance embedding

Date

2015

Authors

Sener F.
Ikizler-Cinbis, N.

Editor(s)

Advisor

Supervisor

Co-Advisor

Co-Supervisor

Instructor

BUIR Usage Stats
1
views
33
downloads

Citation Stats

Series

Abstract

Abstract In this work, we look into the problem of recognizing two-person interactions in videos. Our method integrates multiple visual features in a weakly supervised manner by utilizing an embedding-based multiple instance learning framework. In our proposed method, first, several visual features that capture the shape and motion of the interacting people are extracted from each detected person region in a video. Then, two-person visual descriptors are formed. Since the relative spatial locations of interacting people are likely to complement the visual descriptors, we propose to use spatial multiple instance embedding, which implicitly incorporates the distances between people into the multiple instance learning process. Experimental results on two benchmark datasets validate that using two-person visual descriptors together with spatial multiple instance learning offers an effective way for inferring the type of the interaction. © 2015 Elsevier Inc.

Source Title

Journal of Visual Communication and Image Representation

Publisher

Academic Press Inc.

Course

Other identifiers

Book Title

Degree Discipline

Degree Level

Degree Name

Citation

Published Version (Please cite this version)

Language

English