Research map / Video / Video segmentation and tracking
Am I a Baller? Basketball Performance Assessment From First-Person Videos
Gedas Bertasius, Hyun Soo Park, Stella X. Yu, Jianbo Shi
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add zoom-in cropping (ablation) | event detector · Atomic event detection | mean max F-score: 0.550 -> 0.625 | Improved |
| add multi-path architecture (ablation) | event detector · Atomic event detection | mean max F-score: 0.580 -> 0.625 | Improved |
| add LSTM layers (ablation) | event detector · Atomic event detection | mean max F-score: 0.620 -> 0.625 | No clear effect |
| add LSTM layers without zoom-in (ablation) | event detector · Atomic event detection | mean max F-score: 0.536 -> 0.550 | Improved |
| add Gaussian mixtures (ablation) | assessment model · Basketball assessment | accuracy: 0.477 -> 0.765 | Improved |
| add made-shot event p3 (ablation) | assessment model · Basketball assessment | accuracy: 0.496 -> 0.765 | Improved |
| add possession event p2 (ablation) | assessment model · Basketball assessment | accuracy: 0.515 -> 0.765 | Improved |
| add shooting event p1 (ablation) | assessment model · Basketball assessment | accuracy: 0.536 -> 0.765 | Improved |
| add court zone event p4 (ablation) | assessment model · Basketball assessment | accuracy: 0.649 -> 0.765 | Improved |
| use all 256 Gaussian mixtures instead of top-2 only (ablation) | assessment model · Basketball assessment | accuracy: 0.537 -> 0.765 | Improved |
| use all 256 Gaussian mixtures instead of top-1 only (ablation) | assessment model · Basketball assessment | accuracy: 0.609 -> 0.765 | Improved |
| learn weights w instead of fixing all to 1 (ablation) | assessment model · Basketball assessment | accuracy: 0.583 -> 0.765 | Improved |
Closest papers by meaning
- BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation (CVPR 2025 · similarity 0.89)
- FineSports: A Multi-person Hierarchical Sports Video Dataset for Fine-grained Action Understanding (CVPR 2024 · similarity 0.86)
- ExpertAF: Expert Actionable Feedback from Video (CVPR 2025 · similarity 0.85)
- SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos (CVPR 2024 · similarity 0.84)
- Learning Skill-Attributes for Transferable Assessment in Video (NeurIPS 2025 · similarity 0.84)
- Spot The Ball: A Benchmark for Visual Social Inference (CVPR 2026 · similarity 0.84)
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.
