Method Drift›LLM reasoning / chain-of-thought
MVP-Shot
MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action RecognitionLLM reasoning / chain-of-thought · first seen May 3, 2024
superseded — cited as a baseline and beaten by newer methods
0 papers critique it · 1 beat it on benchmarks
Beaten on benchmarks
Head-to-head results where a newer method reports beating MVP-Shot. Values are copied from the source paper's tables — verify against the cited paper.
- STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
STAR (Ours) beats MVP-Shot · Top-1 accuracy (1-shot) [CLIP-RN50 backbone, SSv2-Small]
55.6 vs 51.2
- STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
STAR (Ours) beats MVP-Shot · Top-1 accuracy (5-shot) [CLIP-RN50 backbone, SSv2-Small]
59.2 vs 57.0
- STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
STAR (Ours) beats MVP-Shot · Top-1 accuracy (1-shot) [CLIP-RN50 backbone, HMDB51]
74.9 vs 72.5
- STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
STAR (Ours) beats MVP-Shot · Top-1 accuracy (5-shot) [CLIP-RN50 backbone, HMDB51]
85.0 vs 82.5
- STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
STAR (Ours) beats MVP-Shot · Top-1 accuracy (1-shot) [CLIP-RN50 backbone, UCF101]
94.1 vs 92.2
- STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
STAR (Ours) beats MVP-Shot · Top-1 accuracy (5-shot) [CLIP-RN50 backbone, UCF101]
98.2 vs 97.6
- STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
STAR (Ours) beats MVP-Shot · Top-1 accuracy (1-shot) [CLIP-RN50 backbone, Kinetics]
94.0 vs 90.0
- STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
STAR (Ours) beats MVP-Shot · Top-1 accuracy (5-shot) [CLIP-RN50 backbone, Kinetics]
95.6 vs 93.2