Research map / Video / Action recognition
Motion-Modulated Temporal Fragment Alignment Network for Few-Shot Action Recognition
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 MTFAN instead of the strongest listed baseline | Few-shot action recognition · Kinetics 5-way 1-shot | accuracy: 73.0 -> 74.6 | Helped |
| Use MTFAN instead of the strongest listed baseline | Few-shot action recognition · Kinetics 5-way 5-shot | accuracy: 85.9 -> 87.4 | Helped |
| Use MTFAN instead of the strongest listed baseline | Few-shot action recognition · SSv2 5-way 1-shot | accuracy: 42.8 -> 45.7 | Helped |
| Use MTFAN instead of the strongest listed baseline | Few-shot action recognition · SSv2 5-way 5-shot | accuracy: 64.6 -> 60.4 | Hurt |
| Use MTFAN instead of the strongest listed baseline | Few-shot action recognition · UCF101 5-way 1-shot | accuracy: 78.8† -> 84.8 | Helped |
| Use MTFAN instead of the strongest listed baseline | Few-shot action recognition · UCF101 5-way 5-shot | accuracy: 96.1 -> 95.1 | Hurt |
| Use MTFAN instead of the strongest listed baseline | Few-shot action recognition · HMDB51 5-way 1-shot | accuracy: 52.2† -> 59.0 | Helped |
| Use MTFAN instead of the strongest listed baseline | Few-shot action recognition · HMDB51 5-way 5-shot | accuracy: 75.6 -> 74.6 | Hurt |
| Add optimal transport frame-level alignment (ablation) | Few-shot action baseline · SSv2 5-way 1-shot | accuracy: 37.4 -> 39.2 | Helped |
| Add optimal transport frame-level alignment (ablation) | Few-shot action baseline · SSv2 5-way 5-shot | accuracy: 49.5 -> 52.7 | Helped |
| Add segment-level alignment to frame-level alignment (ablation) | Few-shot action baseline · SSv2 5-way 1-shot | accuracy: 39.2 -> 41.6 | Helped |
| Add task-specific motion modulation (ablation) | Few-shot action model with OT · SSv2 5-way 1-shot | accuracy: 39.2 -> 42.4 | Helped |
Closest papers by meaning
- Temporal Alignment-Free Video Matching for Few-shot Action Recognition (CVPR 2025 · similarity 0.90)
- Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition (AAAI 2025 · similarity 0.87)
- TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition (CVPR 2025 · similarity 0.85)
- Understanding Multi-Task Activities from Single-Task Videos (CVPR 2025 · similarity 0.84)
- Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP (AAAI 2025 · similarity 0.84)
- Storyboard-guided Alignment for Fine-grained Video Action Recognition (NeurIPS 2025 · 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.