Precondition and Effect Reasoning for Action Recognition

TL;DR

This paper introduces a Cycle-Reasoning model that captures causal relationships among preconditions, actions, and effects to improve human action recognition accuracy in videos.

Contribution

It proposes a novel causal reasoning framework that models precondition and effect relationships, enhancing action recognition performance beyond traditional spatial-temporal feature learning.

Findings

Cycle-Reasoning model effectively captures causal relationships.

Annotated a large-scale action dataset with precondition and effect labels.

Model improves action recognition accuracy.

Abstract

Human action recognition has drawn a lot of attention in the recent years due to the research and application significance. Most existing works on action recognition focus on learning effective spatial-temporal features from videos, but neglect the strong causal relationship among the precondition, action and effect. Such relationships are also crucial to the accuracy of action recognition. In this paper, we propose to model the causal relationships based on the precondition and effect to improve the performance of action recognition. Specifically, a Cycle-Reasoning model is proposed to capture the causal relationships for action recognition. To this end, we annotate precondition and effect for a large-scale action dataset. Experimental results show that the proposed Cycle-Reasoning model can effectively reason about the precondition and effect and can enhance action recognition performance.