Research map / Video / Action recognition
LOGO: A Long-Form Video Dataset for Group Action Quality Assessment
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 GOAT group-aware attention to USDL with I3D features | USDL · LOGO | Spearman's rho: 0.4259 -> 0.4620 | Helped |
| Add GOAT group-aware attention to CoRe with I3D features | CoRe · LOGO | Spearman's rho: 0.4712 -> 0.4935 | Helped |
| Add GOAT group-aware attention to TSA with I3D features | TSA · LOGO | Spearman's rho: 0.4518 -> 0.4855 | Helped |
| Add GOAT group-aware attention with SWIN features | CoRe · LOGO | Spearman's rho: 0.5002 -> 0.5599 | Helped |
| Add GOAT group-aware attention with SWIN features | TSA · LOGO | Spearman's rho: 0.4751 -> 0.4843 | Helped |
| Add GOAT group-aware attention to CoRe | CoRe · FineDiving@2 | Spearman's rho: 0.8991 -> 0.9032 | Helped |
| Add GOAT group-aware attention to CoRe | CoRe · TASD-2@2 | Spearman's rho: 0.9189 -> 0.9334 | Helped |
| Add GOAT group-aware attention to CoRe | CoRe · AQA-7@2 | Spearman's rho: 0.9012 -> 0.9325 | Helped |
| Replace group features with self-attention for temporal fusion (ablation) | GOAT-based AQA · LOGO | Spearman's rho: 0.4712 -> 0.4348; 0.4518 -> 0.4585 | Mixed |
| Replace group features with formation features (ablation) | GOAT-based AQA · LOGO | Spearman's rho: 0.4712 -> 0.4820; 0.4518 -> 0.4241 | Mixed |
| Use action-segmentation features for temporal fusion (ablation) | GOAT-based AQA · LOGO | Spearman's rho: 0.4259 -> 0.4512; 0.4712 -> 0.4825; 0.4518 -> 0.4772 | Helped |
| Replace I3D with SWIN features (ablation) | AQA methods · LOGO | Spearman's rho: 0.4259 -> 0.4725; 0.4712 -> 0.5002; 0.4518 -> 0.4751 | Mixed |
Closest papers by meaning
- LucidAction: A Hierarchical and Multi-model Dataset for Comprehensive Action Quality Assessment (NeurIPS 2024 · similarity 0.89)
- FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment (CVPR 2024 · similarity 0.86)
- GAIA: Rethinking Action Quality Assessment for AI-Generated Videos (NeurIPS 2024 · similarity 0.85)
- ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition (NeurIPS 2024 · similarity 0.84)
- Learning Skill-Attributes for Transferable Assessment in Video (NeurIPS 2025 · similarity 0.83)
- ExpertAF: Expert Actionable Feedback from Video (CVPR 2025 · similarity 0.83)
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.