OpenCodePapers

self-supervised-action-recognition-on-ucf101-1

Action RecognitionSelf-Supervised Action Recognition
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCode3-fold AccuracyPretrainModelNameReleaseDate
Broaden Your Views for Self-Supervised Video Learning✓ Link95.7BraVe:V-FA (TSM-50x2)2021-03-30
Self-Supervised Learning by Cross-Modal Audio-Video Clustering✓ Link95.5XDC2019-11-28
Spatiotemporal Contrastive Video Representation Learning✓ Link93.9K600CVRL (R3D-152 2x; K600)2020-08-09
Evolving Losses for Unsupervised Video Representation Learning93.8ELo2020-02-26
Spatiotemporal Contrastive Video Representation Learning✓ Link93.4K600CVRL (R3D-50; K600)2020-08-09
Spatiotemporal Contrastive Video Representation Learning✓ Link92.2K400CVRL (R3D-50; K400)2020-08-09
Audio-Visual Instance Discrimination with Cross-Modal Agreement✓ Link91.5AVID2020-04-27
Self-Supervised MultiModal Versatile Networks✓ Link91.5MMV2020-06-29
Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting✓ Link90.5UCF101ViCC (S3D; R+F)2021-06-18
Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization89.0AVTS2018-06-30
Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting✓ Link88.8UCF101ViCC (R2+1D; R+F)2021-06-18
Self-supervised Co-training for Video Representation Learning✓ Link87.9K400CoCLR2020-10-19
Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting✓ Link84.3UCF101ViCC (S3D; RGB)2021-06-18
Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting✓ Link82.8UCF101ViCC (R2+1D; RGB)2021-06-18