Two is Better than One: Efficient Ensemble Defense for Robust and Compact Models

MECA: Manipulation with Emotional Intensity-aware Contrastive Learning and Attention-based Discriminative learning

All You Need is Your Voice: Emotional Face Representation with Audio Perspective for Emotional Talking Face Generation

Towards the adversarial robustness of facial expression recognition: Facial attention-aware adversarial training

Beyond superficial emotion recognition: Modality-adaptive emotion recognition system

Fine Gaze Redirection Learning with Gaze Hardness-aware Transformation

NMS-KSD: Efficient Knowledge Distillation for Dense Object Detection via Non-Maximum Suppression and Feature Storage

Robust 3D Human Avatar Reconstruction From Monocular Videos Using Depth Optimization and Camera Pose Estimation

Real-Time Long-Wave Infrared Image Segmentation with Adaptive Noise Reduction and Feature Fusion

Compressing Neural Networks on Limited Computing Resources