Self Supervised Action Recognition On Hmdb51 1

Metrics

Top-1 Accuracy

Results

Performance results of various models on this benchmark

		Paper Title
BraVe:V-FA (TSM-50x2)	77.8	Broaden Your Views for Self-Supervised Video Learning
MMV	70.1	Self-Supervised MultiModal Versatile Networks
CVRL (R3D-152 2x; K600)	69.9	Spatiotemporal Contrastive Video Representation Learning
XDC	68.9	Self-Supervised Learning by Cross-Modal Audio-Video Clustering
CVRL (R3D-50; K600)	68.0	Spatiotemporal Contrastive Video Representation Learning
ELo	67.4	Evolving Losses for Unsupervised Video Representation Learning
CVRL (R3D-50; K400)	66.7	Spatiotemporal Contrastive Video Representation Learning
AVID	64.7	Audio-Visual Instance Discrimination with Cross-Modal Agreement
ViCC (S3D; R+F)	62.2	Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting
AVTS	61.6	Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization
ViCC (R2+1D; R+F)	61.5	-
CoCLR	54.6	Self-supervised Co-training for Video Representation Learning
ViCC (R2+1D; RGB)	52.4	Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting
ViCC (S3D; RGB))	47.9	Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting

0 of 14 row(s) selected.

Self Supervised Action Recognition On Hmdb51 1 | SOTA | HyperAI