Zehan Wang

11

Papers

44

Total Citations

Papers (11)

Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models

OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup

Diff-Prompt: Diffusion-driven Prompt Generator with Mask Supervision

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Real-Time Video Super-Resolution With Spatio-Temporal Networks and Motion Compensation

Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual Grounding

MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition

Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network

InstructSpeech: Following Speech Editing Instructions via Large Language Models

FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion

Connecting Multi-modal Contrastive Representations