Le Wang

30

Papers

84

Total Citations

Papers (30)

R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection

Towards Generalizable Multi-Object Tracking

PMT: Progressive Mean Teacher via Exploring Temporal Consistency for Semi-Supervised Medical Image Segmentation

Diversifying Query: Region-Guided Transformer for Temporal Sentence Grounding

VisHall3D: Monocular Semantic Scene Completion from Reconstructing the Visible Regions to Hallucinating the Invisible Regions

Towards Precise Embodied Dialogue Localization via Causality Guided Diffusion

PDFactor: Learning Tri-Perspective View Policy Diffusion Field for Multi-Task Robotic Manipulation

Boosting Point-Supervised Temporal Action Localization through Integrating Query Reformation and Optimal Transport

FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic Manipulation

Moment Quantization for Video Temporal Grounding

Enhancing Mamba Decoder with Bidirectional Interaction in Multi-Task Dense Prediction

SAMPO: Scale-wise Autoregression with Motion Prompt for Generative World Models

DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation

NeurIPS 2025arXiv

RefDetector: A Simple Yet Effective Matching-based Method for Referring Expression Comprehension

Temporal Correlation Vision Transformer for Video Person Re-Identification

SGCN: Sparse Graph Convolution Network for Pedestrian Trajectory Prediction

Learning To Refactor Action and Co-Occurrence Features for Temporal Action Localization

MotionTrack: Learning Robust Short-Term and Long-Term Motions for Multi-Object Tracking

Progressive Backdoor Erasing via Connecting Backdoor and Adversarial Attacks

Unlimited Neighborhood Interaction for Heterogeneous Trajectory Prediction

Enriching Local and Global Contexts for Temporal Action Localization

Practical Relative Order Attack in Deep Ranking

Meta Pairwise Relationship Distillation for Unsupervised Person Re-Identification

Trajectory Unified Transformer for Pedestrian Trajectory Prediction

Sparse Instance Conditioned Multimodal Trajectory Prediction

Parallel Attention Interaction Network for Few-Shot Skeleton-Based Action Recognition

Learning from Noisy Pseudo Labels for Semi-Supervised Temporal Action Localization

Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization

A Comprehensive Study of Weight Sharing in Graph Networks for 3D Human Pose Estimation

Adversarial Ranking Attack and Defense