Xidong Peng

4

Papers

35

Total Citations

Papers (4)

Learning to Adapt SAM for Segmenting Cross-domain Point Clouds

WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Language

UniDemoiré: Towards Universal Image Demoiréing with Data Generation and Synthesis

STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes