Segment-level Music-to-Video Retrieval on MovieClips (test)
21Median RankMVPt
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| MVPtArchitecture=Transformer, Audio Features=DeepSim, Visual Features=CLIP, Loss Function=InfoNCE2022.06 | 21 | 14.99 | 25.94 | 36.87 | 36.56 | |
| MVPt + X3D featuresArchitecture=Transformer, Audio Features=DeepSim, Visual Features=CLIP + X3D, Loss Function=InfoNCE2022.06 | 28 | 8.9 | 19.74 | 29.69 | 29.11 | |
| Baseline + DeepSim + CLIP + InfoNCEArchitecture=MLP, Audio Features=DeepSim, Visual Features=CLIP, Loss Function=InfoNCE2022.06 | 58 | 4.05 | 12.93 | 23.85 | 19.42 | |
| Baseline + DeepSim + CLIPArchitecture=MLP, Audio Features=DeepSim, Visual Features=CLIP, Loss Function=Triplet2022.06 | 128 | 2.94 | 8.48 | 13.34 | 11.35 | |
| Chance2022.06 | 1,000 | 0.05 | 0.25 | 0.5 | 0.5 |