Peishan Cong

5

Papers

20

Total Citations

Papers (5)

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

SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance

EvolvingGrasp: Evolutionary Grasp Generation via Efficient Preference Alignment

STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes

Human-centric Scene Understanding for 3D Large-scale Scenarios