Home Abstract Video Dataset Paper Related Work Acknowledgement

Abstract

For survival, a living agent (e.g., human in (a)) must have the ability to assess risk (1) by temporally anticipating accidents before they occur (b), and (2) by spatially localizing risky regions (c) in the environment to move away from threats. In this paper, we take an agent-centric approach to study the accident anticipation and risky region localization tasks. We propose a novel soft-attention Recurrent Neural Network (RNN) which explicitly models both spatial and appearance-wise non-linear interaction between the agent triggering the event and another agent or static-region involved. In order to test our proposed method, we introduce the Epic Fail (EF) dataset consisting of 3000 viral videos capturing various accidents. In the experiments, we evaluate the risk assessment accuracy both in the temporal domain (accident anticipation) and spatial domain (risky region localization) on our EF dataset and the Street Accident (SA) dataset. Our method consistently outperforms other baselines on both datasets.

Video Overview

Epic Fail (EF) dataset

Qualitative results:

Following resources are provided:


CVPR 2017

Agent-Centric Risk Assessment: Accident Anticipation and Risky Region Localization

Kuo-Hao Zeng, Shih-Han Chou, Fu-Hsiang Chan, Juan Carlos Niebles, Min Sun

Spotlight

Paper (arXiv)
@inproceedings{ZengCVPR17anticipation,
  title     = {Agent-Centric Risk Assessment: Accident Anticipation and Risky Region Localization},
  author    = {Kuo-Hao Zeng and Shih-Han Chou and Fu-Hsiang Chan and Juan Carlos Niebles and Min Sun},
  year      = {2017},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}
}

Acknowledgement