AI Paper Atlas

Research map / Video / Video-language understanding

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

Haopeng Li, Andong Deng, Jun Liu, Hossein Rahmani, Yulan Guo, Bernt Schiele, Mohammed Bennamoun, Qiuhong Ke

IJCV 2026 · Video › Video-language understanding · approach: Video question answering · 45 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace standard Transformer encoder with Auto-Focus Transformer (GloVe) (ablation)VideoQA baseline · Sports-QAaccuracy: 58.0 -> 59.2Improved
replace standard Transformer encoder with Auto-Focus Transformer (BERT) (ablation)VideoQA baseline · Sports-QAaccuracy: 57.9 -> 59.1Improved
AFT on counterfactual questions (GloVe) (ablation)VideoQA baseline · Sports-QA counterfactualaccuracy: 59.9 -> 56.3Hurt
use multiple focal lengths 3 and 9 instead of single focal length 3 (ablation)AFT · Sports-QA valaccuracy: 58.6 -> 59.3Improved
use local focal length 9 instead of global attention only (ablation)AFT · Sports-QA valaccuracy: 58.2 -> 59.0Improved
add global focus 80 to focal 9 (ablation)AFT · Sports-QA valaccuracy: 59.0 -> 59.2Improved
pretrain on four other sports before fine-tuning on basketball (ablation)AFT · Sports-QA basketballaccuracy: 57.1 -> 58.3Improved
pretrain on four other sports before fine-tuning on FineGym (ablation)AFT · Sports-QA FineGymaccuracy: 48.5 -> 50.3Improved
use BERT instead of GloVe embeddings in BlindQA (ablation)BlindQA · Sports-QAF1-score: 14.9 -> 15.8Improved
use CoT prompting in Chat-UniVi-7B (ablation)Chat-UniVi-7B · Sports-QAaccuracy: 31.52 -> 30.81Hurt
use CoT prompting in Video-LLaVA-7B (ablation)Video-LLaVA-7B · Sports-QAaccuracy: 30.33 -> 30.55No clear effect
fine-tune Qwen2.5-3B on Sports-QA (ablation)Qwen2.5-3B · Sports-QAaccuracy: 27.77 -> 63.71Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy