Heng Wang

5

Papers

74

Total Citations

Papers (5)

V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models

ROS-SAM: High-Quality Interactive Segmentation for Remote Sensing Moving Object

Stitching Segments and Sentences towards Generalization in Video-Text Pre-training

Video Recognition in Portrait Mode

VISTA-LLAMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens