Wei Yang

20

Papers

605

Total Citations

Papers (20)

FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

DiffusionTrack: Diffusion Model for Multi-Object Tracking

Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models

Ref-GS: Directional Factorization for 2D Gaussian Splatting

Dynamic Feature Pruning and Consolidation for Occluded Person Re-identification

Video Anomaly Detection with Motion and Appearance Guided Patch Diffusion Model

SF2T: Self-supervised Fragment Finetuning of Video-LLMs for Fine-Grained Understanding

Progressive Text-to-Image Diffusion with Soft Latent Direction

Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain

TIKP: Text-to-Image Knowledge Preservation for Continual Semantic Segmentation

Temporal Coherent Object Flow for Multi-Object Tracking

Attacks on Continual Semantic Segmentation by Perturbing Incremental Samples

AMD: Anatomical Motion Diffusion with Interpretable Motion Decomposition and Fusion

MaGS: Reconstructing and Simulating Dynamic 3D Objects with Mesh-adsorbed Gaussian Splatting

Attacking Transformers with Feature Diversity Adversarial Perturbation

Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model

Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields

RP-PGD: Boosting Segmentation Robustness with a Region-and-Prototype Based Adversarial Attack

Stop Diverse OOD Attacks: Knowledge Ensemble for Reliable Defense

AAKR: Adversarial Attack-based Knowledge Retention for Continual Semantic Segmentation