List your company

Temporal Action Detection on THUMOS14 (test)

69.6mAPVideoMAE V2
35.07244.0365361.964May 5, 2022Jan 1, 2023Aug 30, 2023Apr 28, 2024Dec 25, 2024Aug 23, 2025Apr 22, 2026

Evaluation results

MethodLinks
VideoMAE V2Optical Flow=false2023.0369.6—
ViT-TADBackbone=ViT-B, Frame rate=8 FPS, Frame resolution=160x160, GPU=NVIDIA TITAN Xp2023.1269.5845
TriDetBackbone=ViT-B, Frame rate=30 FPS, Frame resolution=224x224, GPU=NVIDIA GeForce RTX 30902023.1268.2239
ActionFormerOptical Flow=true2023.0366.8—
ActionFormerBackbone=ViT-B, Frame rate=30 FPS, Frame resolution=224x224, GPU=NVIDIA GeForce RTX 30902023.1265.1268
ViT-TADBackbone=ViT-S, Frame resolution=160x160, GPU=NVIDIA TITAN Xp2023.1264.31,349
ViT-TADBackbone=ViT-S, Frame resolution=112x112, GPU=NVIDIA TITAN Xp2023.12632,135
BasicTADOptical Flow=false2023.0359.6—
TALLFormerOptical Flow=false2023.0359.2—
Explicit Dropout (V)Dropout on Attention Sequence=Explicit (V), Dropout on FF network=Explicit2026.0456.51—
Explicit Dropout (AV)Dropout on Attention Sequence=Explicit (AV), Dropout on FF network=Explicit2026.0456.1—
DropKeyDropout on Attention Sequence=DropKey [20], Dropout on FF network=Implicit2026.0455.87—
Implicit BaselineDropout on Attention Sequence=None, Dropout on FF network=Implicit2026.0455.62—
Explicit Dropout (Q)Dropout on Attention Sequence=Explicit (Q), Dropout on FF network=Explicit2026.0454.98—
Explicit Dropout (FF only)Dropout on Attention Sequence=None, Dropout on FF network=Explicit2026.0454.92—
Explicit Dropout (K)Dropout on Attention Sequence=Explicit (K), Dropout on FF network=Explicit2026.0454.92—
PlusTADModality=RGB, Temporal Resolution=96, Sampling Frame Rate=3 FPS, Spatial Resolution=short-128, Backbone=TP-SlowOnly(x1), Neck=SP-NECK, Head=Anchor-based2022.0554.917,454
PlusTADModality=RGB, Temporal Resolution=96, Sampling Frame Rate=3 FPS, Spatial Resolution=short-128, Backbone=TP-SlowOnly(x1), Neck=SP-NECK, Head=Anchor-free2022.0554.58,377
BasicTADBackbone=SlowOnly, Frame resolution=112x112, GPU=NVIDIA TITAN Xp2023.1254.57,143
TadTROptical Flow=true2023.0354.2—
e2e-tadtrBackbone=ResNet-50-SlowFast, GPU=NVIDIA TITAN Xp2023.1254.25,076
DropAttentionDropout on Attention Sequence=DropAttention [23], Dropout on FF network=Implicit2026.0453.89—
DCANOptical Flow=true2023.0352.3—
AFSDOptical Flow=true2023.0352—
AFSDBackbone=I3D, GPU=NVIDIA GeForce GTX 1080Ti2023.12523,259
BasicTADModality=RGB, Temporal Resolution=768, Sampling Frame Rate=24 FPS, Spatial Resolution=128x128, Backbone=SlowOnly(x8), Neck=TDM, Head=Anchor-free2022.0550.52,702
BasicTADModality=RGB, Temporal Resolution=768, Sampling Frame Rate=24 FPS, Spatial Resolution=128x128, Backbone=SlowOnly(x8), Neck=TDM+TFPN, Head=Anchor-based2022.0550.25,454
DaoTADModality=RGB, Temporal Resolution=768, Sampling Frame Rate=25 FPS, Spatial Resolution=128x128, Backbone=R50-I3D(x8), Neck=TDM+TFPN, Head=RetinaNet2022.05506,668
DaoTADOptical Flow=false2023.0350—
Arora et al. (FF)Dropout on Attention Sequence=None, Dropout on FF network=Arora et al. [1]2026.0448.44—
PBRNetBackbone=I3D, GPU=NVIDIA GeForce GTX 1080Ti2023.1247.11,488
Arora et al. (Q)Dropout on Attention Sequence=(Q) Arora et al. [1], Dropout on FF network=Explicit2026.0446.67—
Arora et al. (K)Dropout on Attention Sequence=(K) Arora et al. [1], Dropout on FF network=Explicit2026.0444.52—
AFSDModality=RGB, Temporal Resolution=256, Sampling Frame Rate=10 FPS, Spatial Resolution=112×112, Backbone=I3D(x8), Neck=TFPN, Head=AFSD2022.0543.84,057
RTD-NetOptical Flow=true2023.0343.6—
Arora et al. (V)Dropout on Attention Sequence=(V) Arora et al. [1], Dropout on FF network=Explicit2026.0436.96—
R-C3DModality=RGB, Temporal Resolution=768, Sampling Frame Rate=25 FPS, Spatial Resolution=112×112, Backbone=C3D(x8), Neck=TDM, Head=R-C3D2022.0536.41,030