List your company
ResearchFormerly WizWand

Video Action Recognition on HMDB51 (test)

84.3AccuracySMART
27.30842.10456.971.696Mar 30, 2021Oct 14, 2021May 1, 2022Nov 16, 2022Jun 3, 2023Dec 19, 2023Jul 5, 2024
Updated 8mo ago

Evaluation results

MethodLinks
SMARTBackbone=TSN-Inception-V3 (24M), Training Dataset=K400, Training Years=0.07, Protocol=Fine-tuning2021.0384.3
BraVeConfig=V+FA, Backbone=TSM-50x2 (93.9M), Training Dataset=AS, Training Years=1, Training Modalities=VFA, Protocol=Fine-tuning2021.0379.4
BraVeConfig=V+FA, Backbone=TSM-50 (23.5M), Training Dataset=AS, Training Years=1, Training Modalities=VFA, Protocol=Fine-tuning2021.0378
BraVeConfig=V+A, Backbone=TSM-50 (23.5M), Training Dataset=AS, Training Years=1, Training Modalities=VA, Protocol=Fine-tuning2021.0376.5
BraVeConfig=V+F×3, Backbone=R3D50 (31.8M), Training Dataset=K600, Training Years=0.1, Training Modalities=VF, Protocol=Fine-tuning2021.0376
S3DBackbone=S3D (9.1M), Training Dataset=IN+K400, Training Years=0.07, Protocol=Fine-tuning2021.0375.9
ρBYOLBackbone=S3D (9.1M), Training Dataset=K400, Training Years=0.07, Training Modalities=V, Protocol=Fine-tuning2021.0375
BraVeConfig=V+F×3, Backbone=TSM-50 (23.5M), Training Dataset=K600, Training Years=0.1, Training Modalities=VF, Protocol=Fine-tuning2021.0374.9
BraVeConfig=V+F×3, Backbone=R3D50 (31.8M), Training Dataset=K400, Training Years=0.07, Training Modalities=VF, Protocol=Fine-tuning2021.0374.6
BraVeConfig=V+V×3, Backbone=TSM-50 (23.5M), Training Dataset=K600, Training Years=0.1, Training Modalities=V, Protocol=Fine-tuning2021.0374.6
BraVeConfig=V+V×3, Backbone=R3D50 (31.8M), Training Dataset=K600, Training Years=0.1, Training Modalities=V, Protocol=Fine-tuning2021.0374.2
ρBYOLBackbone=R3D50 (31.8M), Training Dataset=K400, Training Years=0.07, Training Modalities=V, Protocol=Fine-tuning2021.0373.6
BraVeConfig=V+FA, Backbone=R(2+1)D-50 (46.9M), Training Dataset=AS, Training Years=1, Training Modalities=VFA, Protocol=Fine-tuning2021.0373.5
BraVeConfig=V+V×3, Backbone=R3D50 (31.8M), Training Dataset=K400, Training Years=0.07, Training Modalities=V, Protocol=Fine-tuning2021.0371.9
R(2+1)D-50Backbone=R(2+1)D-50 (46.9M), Training Dataset=K400, Training Years=0.07, Protocol=Fine-tuning2021.0371.5
BraVeConfig=V+A, Backbone=R(2+1)D-18 (33.3M), Training Dataset=AS, Training Years=1, Training Modalities=VA, Protocol=Fine-tuning2021.0370.8
MMVBackbone=R(2+1)D-18 (33.3M), Training Dataset=AS, Training Years=1, Training Modalities=VA, Protocol=Fine-tuning2021.0370.1
BraVeConfig=V+FA, Backbone=TSM-50x2 (93.9M), Training Dataset=AS, Training Years=1, Training Modalities=VFA, Protocol=Linear2021.0369.9
BraVeConfig=V+F×3, Backbone=R3D50 (31.8M), Training Dataset=K600, Training Years=0.1, Training Modalities=VF, Protocol=Linear2021.0369.5
BraVeConfig=V+A, Backbone=TSM-50 (23.5M), Training Dataset=AS, Training Years=1, Training Modalities=VA, Protocol=Linear2021.0369.4
BraVeConfig=V+FA, Backbone=TSM-50 (23.5M), Training Dataset=AS, Training Years=1, Training Modalities=VFA, Protocol=Linear2021.0369.2
XDCBackbone=R(2+1)D-18 (33.3M), Training Dataset=IG65M, Training Years=21, Training Modalities=VA, Protocol=Fine-tuning2021.0368.9
BraVeConfig=V+F×3, Backbone=R3D50 (31.8M), Training Dataset=K400, Training Years=0.07, Training Modalities=VF, Protocol=Linear2021.0368.3
CVRLBackbone=R3D50 (31.8M), Training Dataset=K600, Training Years=0.1, Training Modalities=V, Protocol=Fine-tuning2021.0368
ELoBackbone=R(2+1)D-50 (46.9M), Training Dataset=YT8M, Training Years=13, Training Modalities=VFA, Protocol=Fine-tuning2021.0367.4
BraVeConfig=V+F×3, Backbone=TSM-50 (23.5M), Training Dataset=K600, Training Years=0.1, Training Modalities=VF, Protocol=Linear2021.0366.8
BraVeConfig=V+V×3, Backbone=R3D50 (31.8M), Training Dataset=K600, Training Years=0.1, Training Modalities=V, Protocol=Linear2021.0366.7
BraVeConfig=V+FA, Backbone=R(2+1)D-50 (46.9M), Training Dataset=AS, Training Years=1, Training Modalities=VFA, Protocol=Linear2021.0366.6
GDTBackbone=R(2+1)D-18 (33.3M), Training Dataset=AS, Training Years=1, Training Modalities=VA, Protocol=Fine-tuning2021.0366.1
BraVeConfig=V+V×3, Backbone=TSM-50 (23.5M), Training Dataset=K600, Training Years=0.1, Training Modalities=V, Protocol=Linear2021.0365.4
CVRLBackbone=R3D, Resolution=224, Pre-training=Kinetics-400, Evaluation Protocol=Fine-tuning2021.0865.4
R(2+1)D-18Backbone=R(2+1)D-18 (33.3M), Training Dataset=K400, Training Years=0.07, Protocol=Fine-tuning2021.0365.1
AVIDBackbone=R(2+1)D-50 (46.9M), Training Dataset=AS, Training Years=1, Training Modalities=VA, Protocol=Fine-tuning2021.0364.7
ELoBackbone=R(2+1)D-50 (46.9M), Training Dataset=YT8M, Training Years=13, Training Modalities=VFA, Protocol=Linear2021.0364.5
BraVeConfig=V+V×3, Backbone=R3D50 (31.8M), Training Dataset=K400, Training Years=0.07, Training Modalities=V, Protocol=Linear2021.0364.4
XDCBackbone=R(2+1)D-18 (33.3M), Training Dataset=AS, Training Years=1, Training Modalities=VA, Protocol=Fine-tuning2021.0363.7
BraVeConfig=V+A, Backbone=R(2+1)D-18 (33.3M), Training Dataset=AS, Training Years=1, Training Modalities=VA, Protocol=Linear2021.0363.6
MMVBackbone=R(2+1)D-18 (33.3M), Training Dataset=AS, Training Years=1, Training Modalities=VA, Protocol=Linear2021.0360
CVRLBackbone=R3D50 (31.8M), Training Dataset=K600, Training Years=0.1, Training Modalities=V, Protocol=Linear2021.0359.7
MCNBackbone=R3D, Resolution=128, Pre-training=Kinetics-400, Evaluation Protocol=Fine-tuning2021.0859.3
MCNBackbone=R(2+1)D, Resolution=128, Pre-training=Kinetics-400, Evaluation Protocol=Fine-tuning2021.0858.8
AWTEvaluation Protocol=EP2, Zero-shot=true2024.0757.2
AWTEvaluation Protocol=EP1, Zero-shot=true2024.0756.1
FROSTEREvaluation Protocol=EP2, Zero-shot=true2024.0754.8
CoCLRBackbone=S3D (9.1M), Training Dataset=K400, Training Years=0.07, Training Modalities=VF, Protocol=Fine-tuning2021.0354.6
CoCLRBackbone=S3D, Resolution=128, Pre-training=Kinetics-400, Evaluation Protocol=Fine-tuning2021.0854.6
FROSTEREvaluation Protocol=EP1, Zero-shot=true2024.0754.5
Open-VCLIPEvaluation Protocol=EP2, Zero-shot=true2024.0753.9
Open-VCLIPEvaluation Protocol=EP1, Zero-shot=true2024.0753.2
ViFi-CLIPEvaluation Protocol=EP2, Zero-shot=true2024.0751.3
ST-AdapterEvaluation Protocol=EP2, Zero-shot=true2024.0751.1
AdaptFormerEvaluation Protocol=EP2, Zero-shot=true2024.0751
AdaptFormerEvaluation Protocol=EP1, Zero-shot=true2024.0750.5
AIMEvaluation Protocol=EP2, Zero-shot=true2024.0750.3
ST-AdapterEvaluation Protocol=EP1, Zero-shot=true2024.0750.3
Text4VisEvaluation Protocol=EP1, Zero-shot=true2024.0749.8
AIMEvaluation Protocol=EP1, Zero-shot=true2024.0749.5
SpeedNetBackbone=S3D-G, Resolution=224, Pre-training=Kinetics-400, Evaluation Protocol=Fine-tuning2021.0848.8
Vita-CLIPEvaluation Protocol=EP2, Zero-shot=true2024.0748.6
ActionCLIPEvaluation Protocol=EP2, Zero-shot=true2024.0748.2
ActionCLIPEvaluation Protocol=EP1, Zero-shot=true2024.0748
CoCLRBackbone=S3D (9.1M), Training Dataset=K400, Training Years=0.07, Training Modalities=VF, Protocol=Linear2021.0346.1
X-CLIPEvaluation Protocol=EP2, Zero-shot=true2024.0744.6
Ju et al.Evaluation Protocol=EP2, Zero-shot=true2024.0744.3
MCNEvaluation Protocol=Linear probe, Backbone=R3D-182021.0842.9
MCNEvaluation Protocol=Linear probe, Backbone=R(2+1)D2021.0842.2
CoCLREvaluation Protocol=Linear probe2021.0839.1
PPBackbone=R(2+1)D, Resolution=112, Pre-training=Kinetics-400, Evaluation Protocol=Fine-tuning2021.0835.9
DPCBackbone=R2D-3D, Resolution=128, Pre-training=Kinetics-400, Evaluation Protocol=Fine-tuning2021.0835.7
3D-RotNetBackbone=R3D, Resolution=112, Pre-training=Kinetics-400, Evaluation Protocol=Fine-tuning2021.0833.7
ST-PuzzleBackbone=R3D, Resolution=224, Pre-training=Kinetics-400, Evaluation Protocol=Fine-tuning2021.0833.7
MemDPCEvaluation Protocol=Linear probe2021.0830.5
CBTEvaluation Protocol=Linear probe2021.0829.5