ICIP 2023

IKD+: RELIABLE LOW COMPLEXITY DEEP MODELS FOR RETINOPATHY CLASSIFICATION

LT-VIT: A VISION TRANSFORMER FOR MULTI-LABEL CHEST X-RAY CLASSIFICATION

FROM FELINE CLASSIFICATION TO SKILLS EVALUATION: A MULTITASK LEARNING FRAMEWORK FOR EVALUATING MICRO SUTURING NEUROSURGICAL SKILLS

GS-NET: GLOBAL SELF-ATTENTION GUIDED CNN FOR MULTI-STAGE GLAUCOMA CLASSIFICATION

AFNET-M: ADAPTIVE FUSION NETWORK WITH MASKS FOR 2D+3D FACIAL EXPRESSION RECOGNITION

HQRetouch: Learning Professional Face Retouching via Masked Feature Fusion and Semantic-Aware Modulation

IMAGE INPAINTING WITH INFORMATION LOSS REDUCTION AND TEXTURE-STRUCTURE FEATURE FUSION

TAMM: A TASK-ADAPTIVE MULTI-MODAL FUSION NETWORK FOR FACIAL-RELATED HEALTH ASSESSMENTS ON 3D FACIAL IMAGES

COMPOUND MULTI-BRANCH FEATURE FUSION FOR IMAGE DERAINDROP

LOCAL-GLOBAL CONTRAST FOR LEARNING VOICE-FACE REPRESENTATIONS

Tell Your Story: Text-Driven Face Video Synthesis With High Diversity via Adversarial Learning

IMBALANCE-AWARE ADAPTIVE MARGIN LOSS FOR FAIR MULTI-LABEL FACE ATTRIBUTE RECOGNITION