Shijie Ma

5

Papers

51

Total Citations

Papers (5)

Active Generalized Category Discovery

GenHancer: Imperfect Generative Models are Secretly Strong Vision-Centric Enhancers

Aligned Better, Listen Better for Audio-Visual Large Language Models

CrossMAE: Cross-Modality Masked Autoencoders for Region-Aware Audio-Visual Pre-Training

Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization