DmrNet: Dual-stream Mutual Information Contraction and Re-discrimination Network for Semi-supervised Temporal Action Detection.

HMSFT: Hierarchical Multi-scale Spatial-Frequency-Temporal collaborative transformer for 3D human pose estimation.

Multi-granularity hierarchical contrastive learning between foreground and background for semi-supervised video action detection.

KCM-Net: Kinematic continuity-aware multi-relational cross-attention interaction network for video-based human pose and mesh reconstruction.

A fused convolutional spatio-temporal progressive approach for 3D human pose estimation.

Multi-class differentiation feature representation guided joint dictionary learning for facial expression recognition.

Motion-guided spatiotemporal multitask feature discrimination for self-supervised video representation learning.

Cross-view motion consistent self-supervised video inter-intra contrastive for action representation understanding.

Temporal refinement network: Combining dynamic convolution and multi-scale information for fine-grained action recognition.

Relation-aware interaction spatio-temporal network for 3D human pose estimation.

Self-supervised pretext task collaborative multi-view contrastive learning for video action recognition.

Continuous frame motion sensitive self-supervised collaborative network for video representation learning.

A discriminatively deep fusion approach with improved conditional GAN (im-cGAN) for facial expression recognition.

Combining filtered dictionary representation based deep subspace filter learning with a discriminative classification criterion for facial expression recognition.