Social Scene Understanding: End-To-End Multi-Person Action Localization and Collective Activity Recognition
Timur Bagautdinov, Alexandre Alahi, Francois Fleuret, Pascal Fua, Silvio Savarese
Abstract
We present a unified framework for understanding human social behaviors in raw image sequences. Our model jointly detects multiple individuals, infers their social actions, and estimates the collective actions with a single feed-forward pass through a neural network. We propose a single architecture that does not rely on external detection algorithms but rather is trained end-to-end to generate dense proposal maps that are refined via a novel inference scheme. The temporal consistency is handled via a person-level matching Recurrent Neural Network. The complete model takes as input a sequence of frames and outputs detections along with the estimates of individual actions and collective activities. We demonstrate state-of-the-art performance of our algorithm on multiple publicly available benchmarks.
BibTeX
@inproceedings{cvpr2017_socialsceneunder,
title = {Social Scene Understanding: End-To-End Multi-Person Action Localization and Collective Activity Recognition},
author = {Timur Bagautdinov and Alexandre Alahi and Francois Fleuret and Pascal Fua and Silvio Savarese},
booktitle = {CVPR 2017},
year = {2017}
}