Iterate & Cluster: Iterative Semi-Supervised Action Recognition

TL;DR

This paper introduces an iterative semi-supervised system for action recognition that improves clustering accuracy and reduces annotation effort by actively selecting sequences for labeling, based on latent space embeddings.

Contribution

The novel iterative semi-supervised approach enhances clustering and action recognition accuracy with minimal annotations, outperforming purely unsupervised methods.

Findings

Outperforms non-feature based unsupervised methods on benchmarks.

Achieves comparable accuracy to supervised skeleton-based methods.

Reduces annotation effort significantly.

Abstract

We propose a novel system for active semi-supervised feature-based action recognition. Given time sequences of features tracked during movements our system clusters the sequences into actions. Our system is based on encoder-decoder unsupervised methods shown to perform clustering by self-organization of their latent representation through the auto-regression task. These methods were tested on human action recognition benchmarks and outperformed non-feature based unsupervised methods and achieved comparable accuracy to skeleton-based supervised methods. However, such methods rely on K-Nearest Neighbours (KNN) associating sequences to actions, and general features with no annotated data would correspond to approximate clusters which could be further enhanced. Our system proposes an iterative semi-supervised method to address this challenge and to actively learn the association of clusters and actions. The method utilizes latent space embedding and clustering of the unsupervised encoder-decoder to guide the selection of sequences to be annotated in each iteration. Each iteration, the selection aims to enhance action recognition accuracy while choosing a small number of sequences for annotation. We test the approach on human skeleton-based action recognition benchmarks assuming that only annotations chosen by our method are available and on mouse movements videos recorded in lab experiments. We show that our system can boost recognition performance with only a small percentage of annotations. The system can be used as an interactive annotation tool to guide labeling efforts for 'in the wild' videos of various objects and actions to reach robust recognition.