Action Recognition on SS Full v2
79.3AccuracyFSAR-Qwen3
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| FSAR-Qwen3Pre-training=Qwen3-VL-8B, Knowledge Prompt=Known, Shot=5-shot2026.03 | 79.3 | — | — | |
| FSAR-Qwen3Pre-training=Qwen3-VL-2B, Knowledge Prompt=Known, Shot=5-shot2026.03 | 79 | — | — | |
| FSAR-Qwen2Pre-training=Qwen2-VL-7B, Knowledge Prompt=Known, Shot=5-shot2026.03 | 78.8 | — | — | |
| FSAR-LLaVAPre-training=Video-LLaVA-7B, Knowledge Prompt=Known, Shot=5-shot2026.03 | 78.2 | — | — | |
| FSAR-Qwen3Pre-training=Qwen3-VL-8B, Knowledge Prompt=Unknown, Shot=5-shot2026.03 | 77.6 | — | — | |
| FSAR-Qwen2Pre-training=Qwen2-VL-7B, Knowledge Prompt=Unknown, Shot=5-shot2026.03 | 77.2 | — | — | |
| FSAR-Qwen3Pre-training=Qwen3-VL-2B, Knowledge Prompt=Unknown, Shot=5-shot2026.03 | 77.1 | — | — | |
| FSAR-LLaVAPre-training=Video-LLaVA-7B, Knowledge Prompt=Unknown, Shot=5-shot2026.03 | 76.7 | — | — | |
| FSAR-Qwen3Pre-training=Qwen3-VL-8B, Knowledge Prompt=Known, Shot=1-shot2026.03 | 75.2 | — | — | |
| FSAR-Qwen3Pre-training=Qwen3-VL-2B, Knowledge Prompt=Known, Shot=1-shot2026.03 | 74.8 | — | — | |
| FSAR-Qwen2Pre-training=Qwen2-VL-7B, Knowledge Prompt=Known, Shot=1-shot2026.03 | 74.4 | — | — | |
| Task-AdapterPre-training=CLIP-ViT-B, Shot=5-shot2026.03 | 74.2 | — | — | |
| EMP-NetPre-training=CLIP-ViT-B, Shot=5-shot2026.03 | 73 | — | — | |
| CLIP-CPM2CPre-training=CLIP-ViT-B, Shot=5-shot2026.03 | 72.8 | — | — | |
| CLIP-FSARPre-training=CLIP-ViT-B, Shot=5-shot2026.03 | 72.1 | — | — | |
| FSAR-LLaVAPre-training=Video-LLaVA-7B, Knowledge Prompt=Known, Shot=1-shot2026.03 | 71.7 | — | — | |
| Task-AdapterPre-training=CLIP-ViT-B, Shot=1-shot2026.03 | 71.3 | — | — | |
| CapFSARPre-training=BLIP-ViT-B, Shot=5-shot2026.03 | 70.1 | — | — | |
| MoLo (OTAM)Pre-training=INet-RN50, Shot=5-shot2026.03 | 69.6 | — | — | |
| GgHMPre-training=INet-RN50, Shot=5-shot2026.03 | 69.2 | — | — | |
| HyRSMPre-training=INet-RN50, Shot=5-shot2026.03 | 69 | — | — | |
| STRMPre-training=INet-RN50, Shot=5-shot2026.03 | 68.1 | — | — | |
| Huang et al.Pre-training=INet-RN50, Shot=5-shot2026.03 | 67.1 | — | — | |
| HCLPre-training=INet-RN50, Shot=5-shot2026.03 | 64.9 | — | — | |
| TRXPre-training=INet-RN50, Shot=5-shot2026.03 | 64.6 | — | — | |
| EMP-NetPre-training=CLIP-ViT-B, Shot=1-shot2026.03 | 63.1 | — | — | |
| CLIP-FSARPre-training=CLIP-ViT-B, Shot=1-shot2026.03 | 62.1 | — | — | |
| CLIP-CPM2CPre-training=CLIP-ViT-B, Shot=1-shot2026.03 | 62.1 | — | — | |
| Qwen3-VLPre-training=Qwen3-VL-8B, Mode=Frozen Avg, Knowledge Prompt=Known, Shot=5-shot2026.03 | 59.4 | — | — | |
| Qwen3-VLPre-training=Qwen3-VL-8B, Mode=Frozen Avg, Knowledge Prompt=Unknown, Shot=5-shot2026.03 | 59.2 | — | — | |
| FSAR-Qwen3Pre-training=Qwen3-VL-8B, Knowledge Prompt=Unknown, Shot=1-shot2026.03 | 57.1 | — | — | |
| FSAR-LLaVAPre-training=Video-LLaVA-7B, Knowledge Prompt=Unknown, Shot=1-shot2026.03 | 56.7 | — | — | |
| FSAR-Qwen3Pre-training=Qwen3-VL-2B, Knowledge Prompt=Unknown, Shot=1-shot2026.03 | 56.6 | — | — | |
| FSAR-Qwen2Pre-training=Qwen2-VL-7B, Knowledge Prompt=Unknown, Shot=1-shot2026.03 | 56.3 | — | — | |
| Qwen2-VLPre-training=Qwen2-VL-7B, Mode=Frozen Avg, Knowledge Prompt=Known, Shot=5-shot2026.03 | 55.6 | — | — | |
| MoLo (OTAM)Pre-training=INet-RN50, Shot=1-shot2026.03 | 55 | — | — | |
| Qwen3-VLPre-training=Qwen3-VL-2B, Mode=Frozen Avg, Knowledge Prompt=Known, Shot=5-shot2026.03 | 54.6 | — | — | |
| GgHMPre-training=INet-RN50, Shot=1-shot2026.03 | 54.5 | — | — | |
| Qwen3-VLPre-training=Qwen3-VL-2B, Mode=Frozen Avg, Knowledge Prompt=Unknown, Shot=5-shot2026.03 | 54.5 | — | — | |
| HyRSMPre-training=INet-RN50, Shot=1-shot2026.03 | 54.3 | — | — | |
| CapFSARPre-training=BLIP-ViT-B, Shot=1-shot2026.03 | 54 | — | — | |
| Qwen2-VLPre-training=Qwen2-VL-7B, Mode=Frozen Avg, Knowledge Prompt=Unknown, Shot=5-shot2026.03 | 53.5 | — | — | |
| OTAMPre-training=INet-RN50, Shot=5-shot2026.03 | 52.3 | — | — | |
| Huang et al.Pre-training=INet-RN50, Shot=1-shot2026.03 | 52.3 | — | — | |
| HCLPre-training=INet-RN50, Shot=1-shot2026.03 | 47.3 | — | — | |
| Video-LLaVAPre-training=Video-LLaVA-7B, Mode=Frozen Avg, Knowledge Prompt=Known, Shot=5-shot2026.03 | 45.5 | — | — | |
| Video-LLaVAPre-training=Video-LLaVA-7B, Mode=Frozen Avg, Knowledge Prompt=Unknown, Shot=5-shot2026.03 | 45.2 | — | — | |
| STRMPre-training=INet-RN50, Shot=1-shot2026.03 | 43.1 | — | — | |
| OTAMPre-training=INet-RN50, Shot=1-shot2026.03 | 42.8 | — | — | |
| TRXPre-training=INet-RN50, Shot=1-shot2026.03 | 42 | — | — | |
| Qwen3-VLPre-training=Qwen3-VL-8B, Mode=Frozen Avg, Knowledge Prompt=Known, Shot=1-shot2026.03 | 37.6 | — | — | |
| Qwen3-VLPre-training=Qwen3-VL-8B, Mode=Frozen Avg, Knowledge Prompt=Unknown, Shot=1-shot2026.03 | 37.5 | — | — | |
| Qwen2-VLPre-training=Qwen2-VL-7B, Mode=Frozen Avg, Knowledge Prompt=Known, Shot=1-shot2026.03 | 36.6 | — | — | |
| Qwen3-VLPre-training=Qwen3-VL-2B, Mode=Frozen Avg, Knowledge Prompt=Known, Shot=1-shot2026.03 | 36.2 | — | — | |
| Qwen3-VLPre-training=Qwen3-VL-2B, Mode=Frozen Avg, Knowledge Prompt=Unknown, Shot=1-shot2026.03 | 36 | — | — | |
| Qwen2-VLPre-training=Qwen2-VL-7B, Mode=Frozen Avg, Knowledge Prompt=Unknown, Shot=1-shot2026.03 | 35.3 | — | — | |
| Video-LLaVAPre-training=Video-LLaVA-7B, Mode=Frozen Avg, Knowledge Prompt=Known, Shot=1-shot2026.03 | 31.9 | — | — | |
| Video-LLaVAPre-training=Video-LLaVA-7B, Mode=Frozen Avg, Knowledge Prompt=Unknown, Shot=1-shot2026.03 | 31.2 | — | — | |
| AIMPretrain=CLIP2026.02 | — | 63.7 | 79.2 | |
| AMFARPre-Backbone=ImageNet-RN502024.12 | — | 61.7 | 79.5 | |
| CLIP-FSARBackbone=CLIP-ViT-B/162025.12 | — | 62.1 | 72.1 | |
| D2ST-AdapterBackbone=CLIP-ViT-B/162025.12 | — | 66.7 | 81.9 | |
| D2ST-AdapterPretrain=CLIP2026.02 | — | 66.7 | 81.9 | |
| DualPathPretrain=CLIP2026.02 | — | 64.5 | 79.8 | |
| EMP-NetBackbone=CLIP-ViT-B/162025.12 | — | 63.1 | 73 | |
| Frame2Freq-MSPretrain=CLIP2026.02 | — | 66.9 | 82 | |
| GgHMBackbone=IN-RN502025.12 | — | 54.5 | 69.2 | |
| GgHMPre-Backbone=ImageNet-RN502024.12 | — | 54.5 | 69.2 | |
| HCLBackbone=IN-RN502025.12 | — | 47.3 | 64.9 | |
| HyRSMBackbone=IN-RN502025.12 | — | 54.3 | 69 | |
| HyRSMPre-Backbone=ImageNet-RN502024.12 | — | 54.1 | 68.7 | |
| HyRSMPre-Backbone=ImageNet-ViT2024.12 | — | 58.8 | 71.3 | |
| HyRSMPre-Backbone=ImageNet-VM2024.12 | — | 58.6 | 71.7 | |
| Lite-MKDPre-Backbone=ImageNet-RN502024.12 | — | 55.7 | 69.9 | |
| Lite-MKDPre-Backbone=ImageNet-ViT2024.12 | — | 59.1 | 73.6 | |
| Lite-MKDPre-Backbone=ImageNet-VM2024.12 | — | 59.3 | 73.8 | |
| MA-FSARBackbone=CLIP-ViT-B/162025.12 | — | 63.3 | 72.3 | |
| MantaPre-Backbone=ImageNet-RN502024.12 | — | 63.4 | 87.4 | |
| MantaPre-Backbone=ImageNet-ViT2024.12 | — | 66.2 | 89.3 | |
| MantaPre-Backbone=ImageNet-VM2024.12 | — | 66.1 | 89.1 | |
| MoLoPre-Backbone=ImageNet-RN502024.12 | — | 56.6 | 70.7 | |
| MoLoPre-Backbone=ImageNet-ViT2024.12 | — | 61.1 | 71.7 | |
| MoLoPre-Backbone=ImageNet-VM2024.12 | — | 61.3 | 72.1 | |
| MTFANPre-Backbone=ImageNet-RN502024.12 | — | 45.7 | 60.4 | |
| NguyenBackbone=IN-RN502025.12 | — | 43.8 | 61.1 | |
| OTAMBackbone=IN-RN502025.12 | — | 42.8 | 52.3 | |
| SA-CTPre-Backbone=ImageNet-RN502024.12 | — | 48.9 | 69.1 | |
| SA-CTPre-Backbone=ImageNet-ViT2024.12 | — | — | 66.3 | |
| SloshNetBackbone=IN-RN502025.12 | — | 46.5 | 68.3 | |
| SloshNetPre-Backbone=ImageNet-RN502024.12 | — | 46.5 | 68.3 | |
| ST-AdapterPretrain=CLIP2026.02 | — | 64.2 | 79.5 | |
| STRMBackbone=IN-RN502025.12 | — | 43.1 | 68.1 | |
| STRMPre-Backbone=ImageNet-RN502024.12 | — | — | 68.1 | |
| STRMPre-Backbone=ImageNet-ViT2024.12 | — | — | 70.2 | |
| TATsPretrain=DINO2026.02 | — | 57.7 | 74.6 | |
| TrokensPretrain=DINOv22026.02 | — | 61.5 | 76.7 | |
| TRXBackbone=IN-RN502025.12 | — | 42 | 64.6 | |
| TRXPre-Backbone=ImageNet-RN502024.12 | — | 53.8 | 68.8 | |
| TRXPre-Backbone=ImageNet-ViT2024.12 | — | 57.2 | 71.4 | |
| TRXPre-Backbone=ImageNet-VM2024.12 | — | 56.9 | 71.5 |