Rethinking temporal self-similarity for repetitive action counting

TL;DR

This paper introduces a new framework for counting repetitive actions in videos by learning frame embeddings and start probabilities directly, outperforming existing methods that rely on self-similarity matrices as intermediate representations.

Contribution

It proposes a novel approach that learns embeddings and predicts action starts at full resolution, with a new loss enforcing self-similarity consistency, leading to improved accuracy.

Findings

Achieves state-of-the-art results on RepCount, UCFRep, and Countix datasets.

Outperforms traditional self-similarity matrix-based methods.

Introduces a reference TSM-based loss for better embedding learning.

Abstract

Counting repetitive actions in long untrimmed videos is a challenging task that has many applications such as rehabilitation. State-of-the-art methods predict action counts by first generating a temporal self-similarity matrix (TSM) from the sampled frames and then feeding the matrix to a predictor network. The self-similarity matrix, however, is not an optimal input to a network since it discards too much information from the frame-wise embeddings. We thus rethink how a TSM can be utilized for counting repetitive actions and propose a framework that learns embeddings and predicts action start probabilities at full temporal resolution. The number of repeated actions is then inferred from the action start probabilities. In contrast to current approaches that have the TSM as an intermediate representation, we propose a novel loss based on a generated reference TSM, which enforces that the self-similarity of the learned frame-wise embeddings is consistent with the self-similarity of repeated actions. The proposed framework achieves state-of-the-art results on three datasets, i.e., RepCount, UCFRep, and Countix.