Video Classification on Something-Something V1
67.3Top-1 AccSide4Video
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Side4Videobackbone=ViT-E/14, pre-train=Merged-2B, input=16×6, TFLOPs=15.96×6, protocol=Frozen backbone2026.04 | 67.3 | — | |
| MOSS-Lbackbone=ViT-L/14, pre-train=Merged-2B, input=16×6, TFLOPs=1.67×6, protocol=Frozen backbone2026.04 | 67.3 | — | |
| MOSS-Lbackbone=ViT-L/14, pre-train=CLIP400M, input=16×6, TFLOPs=1.67×6, protocol=Frozen backbone2026.04 | 64.8 | — | |
| ATMbackbone=ViT-L/14, pre-train=CLIP400M, input=16×6, TFLOPs=0.84×6, protocol=Full finetuning2026.04 | 64 | — | |
| MOSS-Lbackbone=ViT-L/14, pre-train=CLIP400M, input=8×6, TFLOPs=0.83×6, protocol=Frozen backbone2026.04 | 63.6 | — | |
| UniFormerV2backbone=ViT-L/14, pre-train=CLIP400M, input=32×3, TFLOPs=1.73×3, protocol=Full finetuning2026.04 | 62.7 | — | |
| Side4Videobackbone=ViT-L/14, pre-train=CLIP400M, input=16×6, TFLOPs=1.74×6, protocol=Frozen backbone2026.04 | 62.4 | — | |
| MOSS-Bbackbone=ViT-B/16, pre-train=CLIP400M, input=16×6, TFLOPs=0.36×6, protocol=Frozen backbone2026.04 | 61.8 | — | |
| StructViT-B-4-1pretrain=K400, frame x crop x clip=32x3x1, FLOPs (G)=19632024.04 | 61.3 | 87.8 | |
| StructViT-B-4-2pretrain=K400, frame x crop x clip=32x3x1, FLOPs (G)=7842024.04 | 61.1 | 87.7 | |
| MOSS-Bbackbone=ViT-B/16, pre-train=CLIP400M, input=8×6, TFLOPs=0.18×6, protocol=Frozen backbone2026.04 | 61 | — | |
| UniFormer-Bpretrain=K400, frame x crop x clip=32x3x1, FLOPs (G)=7772024.04 | 60.9 | 87.3 | |
| Side4Videobackbone=ViT-B/16, pre-train=CLIP400M, input=16×6, TFLOPs=0.36×6, protocol=Frozen backbone2026.04 | 60.7 | — | |
| StructViT-S-4-1pretrain=K400, frame x crop x clip=16x3x1, FLOPs (G)=2462024.04 | 58 | 85.5 | |
| StructViT-S-8-1pretrain=K400, frame x crop x clip=16x3x1, FLOPs (G)=4052024.04 | 58 | 85.7 | |
| StructViT-S-4-2pretrain=K400, frame x crop x clip=16x3x1, FLOPs (G)=1262024.04 | 57.6 | 85.3 | |
| UniFormer-Spretrain=K400, frame x crop x clip=16x3x1, FLOPs (G)=1252024.04 | 57.2 | 84.9 | |
| SELFYNetpretrain=IN-1K, frame x crop x clip=16x1x1, FLOPs (G)=772024.04 | 54.3 | 82.9 | |
| RSANetpretrain=IN-1K, frame x crop x clip=16x1x1, FLOPs (G)=722024.04 | 54 | 81.1 | |
| TDNpretrain=IN-1K, frame x crop x clip=16x1x1, FLOPs (G)=722024.04 | 53.9 | 82.1 | |
| CT-Netpretrain=IN-1K, frame x crop x clip=16x1x1, FLOPs (G)=752024.04 | 52.5 | 80.9 | |
| MSNetpretrain=IN-1K, frame x crop x clip=16x1x1, FLOPs (G)=1012024.04 | 52.1 | 82.3 | |
| TEApretrain=IN-1K, frame x crop x clip=16x1x1, FLOPs (G)=702024.04 | 51.9 | 80.3 |