Self Supervised Action Recognition On Hmdb51

评估指标

Frozen

Pre-Training Dataset

Top-1 Accuracy

评测结果

各个模型在此基准测试上的表现结果

模型名称	Frozen	Pre-Training Dataset	Top-1 Accuracy	Paper Title	Repository
RSPNet	false	Kinetics400	64.7	RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning
VideoMAE	false	Kinetics400	73.3	VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training	-
PCL (ResNet-18)	false	UCF101	43.2	Pretext-Contrastive Learning: Toward Good Practices in Self-supervised Video Representation Leaning
XDC	false	IG-Random	66.5	Self-Supervised Learning by Cross-Modal Audio-Video Clustering
Motion & Appearance (C3D)	false	UCF101	20.3	Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics
XDC	false	Kinetics400	52.6	Self-Supervised Learning by Cross-Modal Audio-Video Clustering
Video Clip Ordering (R3D)	false	UCF101	29.5	Self-Supervised Spatiotemporal Learning via Video Clip Order Prediction	-
XDC	false	AudioSet	63.7	Self-Supervised Learning by Cross-Modal Audio-Video Clustering
VideoMS (ViT-B)	false	no extra data	65.8	EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens
ViCC (R2+1D; RGB)	false	UCF101	52.4	Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting
CoCLR	false	-	46.1	Self-supervised Co-training for Video Representation Learning	-
SLIC (R3D-18)	false	UCF101	54.5	SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos
3D Cubic Puzzles (3D ResNet-18)	false	Kinetics400	33.7	Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles	-
XDC	false	IG-Kinetics	68.9	Self-Supervised Learning by Cross-Modal Audio-Video Clustering
3D RotNet (3D ResNet-18)	false	Kinetics400	33.7	Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction	-
CVRL (R3D-152 2x; K600)	false	Kinetics600	69.9	Spatiotemporal Contrastive Video Representation Learning
BraVe:V-FA (TSM-50x2)	false	-	70.5	Broaden Your Views for Self-Supervised Video Learning
XKD-Modality-Agnostic (ViT-B/112/16)	-	-	65.9	XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning
Shuffle and Learn (AlexNet)	false	UCF101	19.8	Shuffle and Learn: Unsupervised Learning using Temporal Order Verification	-
DPC (Modified 3D ResNet-18)	false	Kinetics400	34.5	Video Representation Learning by Dense Predictive Coding

0 of 48 row(s) selected.