Research map / Video / Action recognition
Action Recognition in Video Using Sparse Coding and Relative Features
Check 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 |
|---|---|---|---|
| Use the proposed sparse key-sequence selection rather than uniform selection (ablation) | Action recognition method · HOHA | accuracy: 34.2% -> 71.9% | Helped |
| Use the proposed sparse key-sequence selection rather than K-Means (ablation) | Action recognition method · HOHA | accuracy: 37.2% -> 71.9% | Helped |
| Use the proposed sparse key-sequence selection rather than uniform selection (ablation) | Action recognition method · Olympic | accuracy: 46.3% -> 96.3% | Helped |
| Use the proposed sparse key-sequence selection rather than K-Means (ablation) | Action recognition method · Olympic | accuracy: 63.4% -> 96.3% | Helped |
| Preserve relative local temporal information in the descriptor (ablation) | ITRA · HOHA | accuracy: 42.2% -> 71.9% | Helped |
| Include intra-class relations in addition to inter-class relations (ablation) | ITRA · HOHA | accuracy: 51.3% -> 71.9% | Helped |
| Preserve relative local temporal information in the descriptor (ablation) | ITRA · Olympic | accuracy: 72.4% -> 96.3% | Helped |
| Include intra-class relations in addition to inter-class relations (ablation) | ITRA · Olympic | accuracy: 87.3% -> 96.3% | Helped |
Closest papers by meaning
- Frame-Wise Action Representations for Long Videos via Sequence Contrastive Learning (CVPR 2022 · similarity 0.87)
- No Frame Left Behind: Full Video Action Recognition (CVPR 2021 · similarity 0.87)
- Temporal Alignment-Free Video Matching for Few-shot Action Recognition (CVPR 2025 · similarity 0.87)
- OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition (CVPR 2024 · similarity 0.86)
- TrAction: Action Recognition with Sparse Trajectories (NeurIPS 2026 · similarity 0.86)
- Storyboard-guided Alignment for Fine-grained Video Action Recognition (NeurIPS 2025 · similarity 0.85)
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.