# Curvature: A signature for Action Recognition in Video Sequences

## TL;DR

This paper introduces a novel curvature-based signature for human action recognition in videos, modeling sequences as curves in pixel space to enable effective classification and potential transfer to other sequence recognition tasks.

## Contribution

The paper proposes a new curvature-based approach for action recognition that does not rely on image features, offering a simple yet powerful method with state-of-the-art results.

## Key findings

- Achieves state-of-the-art performance in video action recognition
- Effective in modeling sequences as curves in pixel space
- Potential applicability to other sequence-based recognition tasks

## Abstract

In this paper, a novel signature of human action recognition, namely the curvature of a video sequence, is introduced. In this way, the distribution of sequential data is modeled, which enables few-shot learning. Instead of depending on recognizing features within images, our algorithm views actions as sequences on the universal time scale across a whole sequence of images. The video sequence, viewed as a curve in pixel space, is aligned by reparameterization using the arclength of the curve in pixel space. Once such curvatures are obtained, statistical indexes are extracted and fed into a learning-based classifier. Overall, our method is simple but powerful. Preliminary experimental results show that our method is effective and achieves state-of-the-art performance in video-based human action recognition. Moreover, we see latent capacity in transferring this idea into other sequence-based recognition applications such as speech recognition, machine translation, and text generation.