HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Self Supervised Action Recognition On Ucf101 1

Metrics

3-fold Accuracy
Pretrain

Results

Performance results of various models on this benchmark

Model Name
3-fold Accuracy
Pretrain
Paper TitleRepository
CVRL (R3D-50; K400)92.2K400Spatiotemporal Contrastive Video Representation Learning
ViCC (R2+1D; RGB)82.8UCF101Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting
AVID91.5-Audio-Visual Instance Discrimination with Cross-Modal Agreement
CoCLR87.9K400Self-supervised Co-training for Video Representation Learning-
ViCC (R2+1D; R+F)88.8UCF101Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting
CVRL (R3D-50; K600)93.4K600Spatiotemporal Contrastive Video Representation Learning
ViCC (S3D; R+F)90.5UCF101Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting
CVRL (R3D-152 2x; K600)93.9K600Spatiotemporal Contrastive Video Representation Learning
AVTS89.0-Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization-
BraVe:V-FA (TSM-50x2)95.7-Broaden Your Views for Self-Supervised Video Learning
ViCC (S3D; RGB)84.3UCF101Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting
MMV91.5-Self-Supervised MultiModal Versatile Networks
ELo93.8-Evolving Losses for Unsupervised Video Representation Learning-
XDC95.5-Self-Supervised Learning by Cross-Modal Audio-Video Clustering
0 of 14 row(s) selected.