HyperAI
StartseiteNeuigkeitenNeueste ForschungsarbeitenTutorialsDatensätzeWikiSOTALLM-ModelleGPU-RanglisteVeranstaltungen
Suche
Über
HyperAI

Self Supervised Action Recognition On Hmdb51 1

Metriken

Top-1 Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname
Top-1 Accuracy
Paper TitleRepository
ELo67.4Evolving Losses for Unsupervised Video Representation Learning-
AVTS61.6Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization-
ViCC (R2+1D; RGB)52.4Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting
BraVe:V-FA (TSM-50x2)77.8Broaden Your Views for Self-Supervised Video Learning
XDC68.9Self-Supervised Learning by Cross-Modal Audio-Video Clustering
CVRL (R3D-152 2x; K600)69.9Spatiotemporal Contrastive Video Representation Learning
MMV70.1Self-Supervised MultiModal Versatile Networks
CVRL (R3D-50; K600)68.0Spatiotemporal Contrastive Video Representation Learning
AVID64.7Audio-Visual Instance Discrimination with Cross-Modal Agreement
CoCLR54.6Self-supervised Co-training for Video Representation Learning-
ViCC (R2+1D; R+F)61.5--
ViCC (S3D; RGB))47.9Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting
ViCC (S3D; R+F)62.2Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting
CVRL (R3D-50; K400)66.7Spatiotemporal Contrastive Video Representation Learning
0 of 14 row(s) selected.