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

arXiv: https://arxiv.org/abs/1607.02737 · HTML: https://mlsanity.com/paper/1607.02737/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2016.

## Built on by (most cited first, 18 of 18)

- [Riemannian Local Mechanism for SPD Neural Networks](https://mlsanity.com/paper/2201.10145/) (2022)
- [A Two-stream Neural Network for Pose-based Hand Gesture Recognition](https://mlsanity.com/paper/2101.08926/) (2021)
- [HAN: An Efficient Hierarchical Self-Attention Network for Skeleton-Based Gesture Recognition](https://mlsanity.com/paper/2106.13391/) (2021)
- [Riemannian Self-Attention Mechanism for SPD Networks](https://mlsanity.com/paper/2311.16738/) (2023)
- [Multi-Scale Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition](https://mlsanity.com/paper/2111.03993/) (2021)
- [Skeleton-based Hand-Gesture Recognition with Lightweight Graph Convolutional Networks](https://mlsanity.com/paper/2104.04255/) (2021)
- [DreamNet: A Deep Riemannian Network based on SPD Manifold Learning for Visual Classification](https://mlsanity.com/paper/2206.07967/) (2022)
- [Learning Chebyshev Basis in Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.05482/) (2021)
- [Spatio-Temporal Graph Complementary Scattering Networks](https://mlsanity.com/paper/2110.12150/) (2021)
- [Lightweight Graph Convolutional Networks with Topologically Consistent Magnitude Pruning](https://mlsanity.com/paper/2203.13616/) (2022)
- [Budget-Aware Graph Convolutional Network Design using Probabilistic Magnitude Pruning](https://mlsanity.com/paper/2305.19343/) (2023)
- [Miniaturized Graph Convolutional Networks with Topologically Consistent Pruning](https://mlsanity.com/paper/2306.17590/) (2023)
- [Local Spherical Harmonics Improve Skeleton-Based Hand Action Recognition](https://mlsanity.com/paper/2308.10557/) (2023)
- [One-Shot Multi-Rate Pruning of Graph Convolutional Networks](https://mlsanity.com/paper/2312.17615/) (2023)
- [Designing Semi-Structured Pruning of Graph Convolutional Networks for Skeleton-based Recognition](https://mlsanity.com/paper/2412.11813/) (2024)
- [Label-Efficient Skeleton-based Recognition with Stable-Invertible Graph Convolutional Networks](https://mlsanity.com/paper/2511.17345/) (2025)
- [Active Learning for GCN-based Action Recognition](https://mlsanity.com/paper/2511.21625/) (2025)
- [A Point Cloud Transformer for Remote Monitoring and Automated Assessment of Physical Rehabilitation Exercises](https://mlsanity.com/paper/2606.30309/) (2026)

## Abstract (arXiv)

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.