Haotian Wang

6

Papers

13

Total Citations

Papers (6)

A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech Recognition

Scaling Few-Shot Learning for the Open World

Breaking the Gradient Barrier: Unveiling Large Language Models for Strategic Classification

EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion

PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistency

Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees