Wenjie Pei

10

Papers

18

Total Citations

Papers (10)

Robust 3D Tracking with Quality-Aware Shape Completion

WeCromCL: Weakly Supervised Cross-Modality Contrastive Learning for Transcription-only Supervised Text Spotting

Recognition-Synergistic Scene Text Editing

MotionShot: Adaptive Motion Transfer across Arbitrary Objects for Text-to-Video Generation

UniVoxel: Fast Inverse Rendering by Unified Voxelization of Scene Representation

Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation

D2ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition

Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval

SA²VP: Spatially Aligned-and-Adapted Visual Prompt

Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation