ICASSP 2023

DIFFICULTY-AWARE DATA AUGMENTOR FOR SCENE TEXT RECOGNITION

Learning interpretable filters in Wav-Unet for speech enhancement

Background Disturbance Mitigation for Video Captioning via Entity-Action Relocation

Sinusoidal Frequency Estimation by Gradient Descent

Multi-view K-means with Laplacian Embedding

Going in Style: Audio Backdoors through Stylistic Transformations

Joint Multi-Level Feature Network for Lightweight Person Re-Identification

AUDIO SIGNAL ENHANCEMENT WITH LEARNING FROM POSITIVE AND UNLABELLED DATA

ACTIVE PERCEPTION SYSTEM FOR ENHANCED VISUAL SIGNAL RECOVERY USING DEEP REINFORCEMENT LEARNING

FEDERATED LEARNING FOR ASR BASED ON WAV2VEC 2.0

Learning on Graphs under Label Noise

ROBUST HYPERSPECTRAL ANOMALY DETECTION WITH SIMULTANEOUS MIXED NOISE REMOVAL VIA CONSTRAINED CONVEX OPTIMIZATION