List your company
ResearchFormerly WizWand

Action Detection on AVA v2.1 (val)

32mAPTubeR
13.818.52523.2527.975Dec 10, 2018Apr 29, 2019Sep 17, 2019Feb 5, 2020Jun 24, 2020Nov 12, 2020Apr 2, 2021
Updated 8mo ago

Evaluation results

MethodLinks
TubeRDetector=X, Input=32 x 2, Backbone=CSN-152, Pre-train=IG + K400, Inference=2 view, GFLOPS=2402021.0432
TubeRDetector=X, Input=32 x 2, Backbone=CSN-152, Pre-train=IG + K400, Inference=1 view, GFLOPS=1202021.0431.7
TubeRDetector=X, Input=32 x 2, Backbone=SF-101, Pre-train=K400 + K700, Inference=1 view, GFLOPS=2402021.0431.6
AIADetector=F-RCNN, Input=32 x 2, Backbone=SF-101, Pre-train=K400 + K700, Inference=18 views, GFLOPS=NA2021.0431.2
ACAR-NetBackbone=R-101, Sampling=8 x 8, inputs=V, Pre-training=Kinetics-4002020.0630
ACAR-NETDetector=F-RCNN, Input=32 x 2, Backbone=SF-101, Pre-train=K400 + K600, Inference=6 views, GFLOPS=NA2021.0430
TubeRDetector=X, Input=32 x 2, Backbone=CSN-50, Pre-train=K400, Inference=1 view, GFLOPS=782021.0428.8
TubeRDetector=X, Input=16 x 4, Backbone=I3D-Res101, Pre-train=K400, Inference=1 view, GFLOPS=2462021.0428.6
ACAR-NetBackbone=R-50, Sampling=8 x 8, inputs=V, Pre-training=Kinetics-4002020.0628.3
ACAR-NETDetector=F-RCNN, Input=32 x 2, Backbone=SF-50, Pre-train=K400, Inference=6 views, GFLOPS=NA2021.0428.3
SlowFast*, +NLflow=false, video pretrain=Kinetics-600, Backbone=R101+NL, TxTau=8x8, Region Proposals=Uses authors' region proposals for training2018.1228.2
SF-101-NLDetector=F-RCNN, Input=32 x 2, Backbone=SF-101 + NL, Pre-train=K400 + K600, Inference=6 views, GFLOPS=9622021.0428.2
WOODetector=X, Input=8 x 8, Backbone=SF-101, Pre-train=K400 + K600, Inference=1 view, GFLOPS=2462021.0428
AVSF-50 4x16Pretrain=K4002021.0427.8
LFBDetector=F-RCNN, Input=32 x 2, Backbone=I3D-101-NL, Pre-train=K400, Inference=18 views, GFLOPS=NA2021.0427.7
LFBBackbone=R-101+NL, inputs=V, Pre-training=Kinetics-4002020.0627.4
SlowFast, +NLflow=false, video pretrain=Kinetics-600, Backbone=R101+NL, TxTau=8x82018.1227.3
CSN-152Detector=F-RCNN, Input=32 x 2, Backbone=CSN-152, Pre-train=IG + K400, Inference=1 views, GFLOPS=3422021.0427.3
SlowFastflow=false, video pretrain=Kinetics-600, Backbone=R101, TxTau=8x82018.1226.8
SlowFastflow=false, video pretrain=Kinetics-400, Backbone=R101, TxTau=8x82018.1226.3
Collaborative Memory (R50+NL)Pretrain=K400, backbone=R50+NL2021.0426.3
SlowFastBackbone=R-101, Sampling=8 x 8, inputs=V, Pre-training=Kinetics-4002020.0626.3
TubeRDetector=X, Input=16 x 4, Backbone=I3D-Res50, Pre-train=K400, Inference=1 view, GFLOPS=1322021.0426.1
X3D-XLDetector=F-RCNN, Input=16 x 5, Backbone=X3D-XL, Pre-train=K400, Inference=1 view, GFLOPS=2902021.0426.1
LFB (R50+NL)Pretrain=K4002021.0425.8
Collaborative Memory (SF-50 4x16)Pretrain=K400, backbone=SF-50 4x162021.0425.8
LFBBackbone=R-50+NL, inputs=V, Pre-training=Kinetics-4002020.0625.8
9 model ensembleflow=true, video pretrain=Kinetics-4002018.1225.6
WOODetector=X, Input=8 x 8, Backbone=SF-50, Pre-train=K400, Inference=1 view, GFLOPS=1422021.0425.2
AT (I3D)Pretrain=K4002021.0425
Action TXBackbone=I3D, inputs=V, Pre-training=Kinetics-4002020.0625
VTrDetector=X, Input=64 x 1, Backbone=I3D-VGG, Pre-train=K400, Inference=1 view, GFLOPS=NA2021.0424.9
SlowFastBackbone=R-50, Sampling=8 x 8, inputs=V, Pre-training=Kinetics-4002020.0624.8
Slowfast-50Detector=F-RCNN, Input=16 x 4, Backbone=SF-50, Pre-train=K400, Inference=1 view, GFLOPS=3082021.0424.2
R50+NLPretrain=K400, reproduced=true2021.0423.6
SF-50 4x16Pretrain=K400, reproduced=true2021.0423.6
Zhang et al.Backbone=I3D, inputs=V, Pre-training=Kinetics-4002020.0622.2
I3Dflow=false, video pretrain=Kinetics-6002018.1221.9
ATR, R50+NLflow=true, video pretrain=Kinetics-4002018.1221.7
ATR, R50+NLflow=false, video pretrain=Kinetics-4002018.1220
STEPDetector=X, Input=32 x 2, Backbone=I3D-VGG, Pre-train=K400, Inference=1 view, GFLOPS=NA2021.0418.6
ACRN, S3Dflow=true, video pretrain=Kinetics-4002018.1217.4
ACRNPretrain=K4002021.0417.4
ACRNBackbone=S3D, inputs=V+F, Pre-training=Kinetics-4002020.0617.4
ACRNDetector=X, Input=32 x 2, Backbone=S3D-G, Pre-train=K400, Inference=1 view, GFLOPS=NA2021.0417.4
I3Dflow=true, video pretrain=Kinetics-4002018.1215.6
I3Dflow=false, video pretrain=Kinetics-4002018.1214.5
I3DDetector=X, Input=32 x 2, Backbone=I3D-VGG, Pre-train=K400, Inference=1 view, GFLOPS=NA2021.0414.5