Towards Comprehensive Basketball Understanding
Understanding a basketball game requires recognizing events, localizing actions, identifying players, and relating these to structured game knowledge. Existing benchmarks primarily evaluate these abilities one at a time, leaving the interactions among these abilities under-explored. We introduce BasketballBench, a multimodal benchmark comprising 7,980 questions across ten tasks in text, image, and video. It is built from the 2025-2026 NBA season and includes official playby-play, rosters and profiles for 530 active players, and 2,501 possession-level broadcast clips. We further propose Basketb
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via arxiv author · 85%Yirong Hu →
“Towards Comprehensive Basketball Understanding”
- LinkedLinked via arxiv author · 85%Jiayuan Rao →
“Towards Comprehensive Basketball Understanding”
- LinkedLinked via arxiv author · 85%Gengyu Zhang →
“Towards Comprehensive Basketball Understanding”
- LinkedLinked via arxiv author · 85%Shangzhe Di →
“Towards Comprehensive Basketball Understanding”
- LinkedLinked via arxiv author · 85%Weidi Xie →
“Towards Comprehensive Basketball Understanding”