SOTAVerified

Self-Supervised Action Recognition

Papers

Showing 125 of 51 papers

TitleStatusHype
Feature Hallucination for Self-supervised Action Recognition0
Cross-Model Cross-Stream Learning for Self-Supervised Human Action RecognitionCode0
A Large-Scale Analysis on Self-Supervised Video Representation Learning0
Part Aware Contrastive Learning for Self-Supervised Action RecognitionCode1
VideoMAE V2: Scaling Video Masked Autoencoders with Dual MaskingCode2
Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton SequencesCode1
Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised LearningCode1
Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation LearningCode1
XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation LearningCode1
EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal TokensCode1
Masked Motion Encoding for Self-Supervised Video Representation LearningCode1
SLIC: Self-Supervised Learning with Iterative Clustering for Human Action VideosCode1
Self-supervised Contrastive Learning for Audio-Visual Action Recognition0
Human-Centered Prior-Guided and Task-Dependent Multi-Task Representation Learning for Action Recognition Pre-Training0
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-TrainingCode3
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action RecognitionCode1
Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal SynchronicityCode1
Self-Supervised Video Representation Learning with Meta-Contrastive Network0
Learning the Predictability of the FutureCode1
Self-supervised Video Representation Learning with Cross-Stream Prototypical ContrastingCode1
A Large-Scale Study on Unsupervised Spatiotemporal Representation LearningCode0
Broaden Your Views for Self-Supervised Video LearningCode1
Self-Supervised Learning via multi-Transformation Classification for Action Recognition0
TCLR: Temporal Contrastive Learning for Video RepresentationCode1
Pretext-Contrastive Learning: Toward Good Practices in Self-supervised Video Representation LeaningCode1
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.