Shengfeng He

ProstaTD: Bridging Surgical Triplet from Classification to Fully Supervised Detection

Healthcare Insurance Fraud Detection via Continual Fiedler Vector Graph Model

Pinpointing Crowd in Bird's Eye View via Proximal Contexts

Latent Wavelet Diffusion For Ultra High-Resolution Image Synthesis

FreeMo: Motion Generation with Structured Joint-Collision Energy

M$^3$E: Continual Vision-and-Language Navigation via Mixture of Macro and Micro Experts

Effortless Event-Augmented Latent Diffusion for Video Frame Interpolation

SeVA: Learning to Ask Discriminative Queries for Fine-Grained Visual Recognition

Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection

StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models

Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking

RecDreamer: Consistent Text-to-3D Generation via Uniform Score Distillation

Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection

Instruct2See: Learning to Remove Any Obstructions Across Distributions

Jury-and-Judge Chain-of-Thought for Uncovering Toxic Data in 3D Visual Grounding

Action Dubber: Timing Audible Actions via Inflectional Flow

SeeThruAnything: Learning to Remove Any Obstructions Across Distributions

Test-time Zero-shot Recognition with Good Attributes

Task-Oriented Diffusion Inversion for High-Fidelity Text-based Editing

Language-driven 3D Human Pose Estimation: Grounding Motion from Text Descriptions