TinyAction Challenge: Recognizing Real-world Low-resolution Activities in Videos

TL;DR

This paper introduces the TinyAction Challenge and TinyVIRAT-v2 dataset to advance recognition of low-resolution, real-world actions in videos, addressing a gap in current high-quality video action recognition research.

Contribution

It presents a new benchmark dataset of low-resolution security videos and organizes a challenge to evaluate action recognition methods in realistic, tiny-region scenarios.

Findings

State-of-the-art methods perform variably on low-resolution data

The dataset reveals challenges in recognizing tiny, low-res actions

Benchmark results highlight the need for specialized approaches

Abstract

This paper summarizes the TinyAction challenge which was organized in ActivityNet workshop at CVPR 2021. This challenge focuses on recognizing real-world low-resolution activities present in videos. Action recognition task is currently focused around classifying the actions from high-quality videos where the actors and the action is clearly visible. While various approaches have been shown effective for recognition task in recent works, they often do not deal with videos of lower resolution where the action is happening in a tiny region. However, many real world security videos often have the actual action captured in a small resolution, making action recognition in a tiny region a challenging task. In this work, we propose a benchmark dataset, TinyVIRAT-v2, which is comprised of naturally occuring low-resolution actions. This is an extension of the TinyVIRAT dataset and consists of actions with multiple labels. The videos are extracted from security videos which makes them realistic and more challenging. We use current state-of-the-art action recognition methods on the dataset as a benchmark, and propose the TinyAction Challenge.