Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection

TL;DR

Transition forests are a novel ensemble method that learns to recognize human actions by modeling both static poses and temporal transitions between frames, improving accuracy in action recognition and detection.

Contribution

The paper introduces transition forests, a new decision tree ensemble that jointly learns static pose discrimination and temporal transitions for improved action recognition.

Findings

Outperforms several baselines and state-of-the-art methods.

Effective in online action detection scenarios.

Applicable to skeleton-based action recognition datasets.

Abstract

A human action can be seen as transitions between one's body poses over time, where the transition depicts a temporal relation between two poses. Recognizing actions thus involves learning a classifier sensitive to these pose transitions as well as to static poses. In this paper, we introduce a novel method called transitions forests, an ensemble of decision trees that both learn to discriminate static poses and transitions between pairs of two independent frames. During training, node splitting is driven by alternating two criteria: the standard classification objective that maximizes the discrimination power in individual frames, and the proposed one in pairwise frame transitions. Growing the trees tends to group frames that have similar associated transitions and share same action label incorporating temporal information that was not available otherwise. Unlike conventional decision trees where the best split in a node is determined independently of other nodes, the transition forests try to find the best split of nodes jointly (within a layer) for incorporating distant node transitions. When inferring the class label of a new frame, it is passed down the trees and the prediction is made based on previous frame predictions and the current one in an efficient and online manner. We apply our method on varied skeleton action recognition and online detection datasets showing its suitability over several baselines and state-of-the-art approaches.