Henghui Ding

17

Papers

250

Total Citations

Papers (17)

OMG-Seg: Is One Model Good Enough For All Segmentation?

Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation

Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment

Explore In-Context Segmentation via Latent Diffusion Models

Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing

Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation

Free-Form Motion Control: Controlling the 6D Poses of Camera and Objects in Video Generation

Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension

LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers

Referring Image Editing: Object-level Image Editing via Referring Expressions

MOVE: Motion-Guided Few-Shot Video Object Segmentation

QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge

Exploiting Temporal State Space Sharing for Video Semantic Segmentation

CharaConsist: Fine-Grained Consistent Character Generation

AnyI2V: Animating Any Conditional Image with Motion Control

Hierarchical Visual Prompt Learning for Continual Video Instance Segmentation

DViN: Dynamic Visual Routing Network for Weakly Supervised Referring Expression Comprehension