Multimodal Deepfake detection, non-critical phoneme-viseme, VA correlation learning, self-supervised learning
ContourAttention MechanismDeep Convolution Neural Network
Deep equilibrium models, Lyapunov theory, Robustness, Image recognition, Adversarial examples
Cross-modal Retrieval, Semi-supervised hash learning, Diffusion model, knowledge distillation, Quintet loss
Domain adaptationSemantic segmentationConsistency regularization Representation learningSelf-training
Super-Resolution, Reference-based Super-Resolution, Temporal Consistency, Semantic Awareness
Domain adaptation, Semantic segmentation, Consistency regularization, Representation learning, Self-training
Anomaly Detection, Few-Shot Learning, Triplet-Loss
Image Denoising, diffusion model, Sampling acceleration
Learned video compression, video frame interpolation, Artifact reduction, Bi-directional motion compensation
3D Gaussian Splatting, Low-light Reconstruction, Novel ViewSynthesis, Frequency-domain Modeling
Extremely Low-Bitrate Image Compression, Masked Compression Model, Dual-Adaptive Masking
