Jian Yang

One-Shot Exemplars for Class Grounding in Self-Supervised Learning

VMDiff: Visual Mixing Diffusion for Limitless Cross-Object Synthesis

Boost the Identity-Preserving Embedding for Consistent Text-to-Image Generation

GeoBA: Stealthy Geometric Poisoning on 3D Point Cloud

External Illumination De-Interfering for Remote Photoplethysmography

Enhancing Contrastive Learning with Variable Similarity

One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation

See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction

FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction

SinPoint: A Novel Topological Consistent Augmentation for Point Cloud Understanding

Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation

DH-Fusion: Depth-Aware Hybrid Feature Fusion for Multimodal 3D Object Detection

AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillation

MindAligner: Explicit Brain Functional Alignment for Cross-Subject Visual Decoding from Limited fMRI Data

SceneLock: Reversible Adversarial Learning for Camera-Based Autonomous Driving Protection

Range-Null Latent Prior-guided Consistency Model for Low Light Image Enhancement