LOGO: A Long-Form Video Dataset for Group Action Quality Assessment

TL;DR

LOGO is a new long-form video dataset for group action quality assessment featuring multi-person scenes, detailed annotations, and a proposed group-aware attention method to improve analysis of complex group actions.

Contribution

We introduce LOGO, a challenging multi-person long-form video dataset with rich annotations and propose a novel group-aware attention module for better group action analysis.

Findings

Our dataset reveals the challenges in group action quality assessment.

The proposed method achieves state-of-the-art performance on LOGO.

LOGO enables systematic benchmarking of AQA methods in complex scenarios.

Abstract

Action quality assessment (AQA) has become an emerging topic since it can be extensively applied in numerous scenarios. However, most existing methods and datasets focus on single-person short-sequence scenes, hindering the application of AQA in more complex situations. To address this issue, we construct a new multi-person long-form video dataset for action quality assessment named LOGO. Distinguished in scenario complexity, our dataset contains 200 videos from 26 artistic swimming events with 8 athletes in each sample along with an average duration of 204.2 seconds. As for richness in annotations, LOGO includes formation labels to depict group information of multiple athletes and detailed annotations on action procedures. Furthermore, we propose a simple yet effective method to model relations among athletes and reason about the potential temporal logic in long-form videos. Specifically, we design a group-aware attention module, which can be easily plugged into existing AQA methods, to enrich the clip-wise representations based on contextual group information. To benchmark LOGO, we systematically conduct investigations on the performance of several popular methods in AQA and action segmentation. The results reveal the challenges our dataset brings. Extensive experiments also show that our approach achieves state-of-the-art on the LOGO dataset. The dataset and code will be released at \url{https://github.com/shiyi-zh0408/LOGO }.