Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports

TL;DR

This paper introduces Sports-QA, a large-scale dataset for sports video question answering, and proposes the Auto-Focus Transformer model to improve understanding of complex sports videos, achieving state-of-the-art results.

Contribution

The paper presents the first sports-specific VideoQA dataset and a novel Auto-Focus Transformer model for fine-grained temporal reasoning in sports videos.

Findings

AFT achieves state-of-the-art performance on Sports-QA.

Sports-QA covers diverse question types and multiple sports.

Auto-Focus mechanism improves temporal information focus.

Abstract

Reasoning over sports videos for question answering is an important task with numerous applications, such as player training and information retrieval. However, this task has not been explored due to the lack of relevant datasets and the challenging nature it presents. Most datasets for video question answering (VideoQA) focus mainly on general and coarse-grained understanding of daily-life videos, which is not applicable to sports scenarios requiring professional action understanding and fine-grained motion analysis. In this paper, we introduce the first dataset, named Sports-QA, specifically designed for the sports VideoQA task. The Sports-QA dataset includes various types of questions, such as descriptions, chronologies, causalities, and counterfactual conditions, covering multiple sports. Furthermore, to address the characteristics of the sports VideoQA task, we propose a new Auto-Focus Transformer (AFT) capable of automatically focusing on particular scales of temporal information for question answering. We conduct extensive experiments on Sports-QA, including baseline studies and the evaluation of different methods. The results demonstrate that our AFT achieves state-of-the-art performance.