Henghui Ding

51

Papers

245

Total Citations

Papers (51)

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

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

Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation

MOVE: Motion-Guided Few-Shot Video Object Segmentation

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

Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene Segmentation

Semantic Correlation Promoted Shape-Variant Context for Segmentation

A Closer Look at Few-Shot Image Generation

Primitive3D: 3D Object Dataset Synthesis From Randomly Assembled Primitives

Learning Transferable Human-Object Interaction Detector With Natural Language Supervision

Coarse-To-Fine Feature Mining for Video Semantic Segmentation

GRES: Generalized Referring Expression Segmentation

OVTrack: Open-Vocabulary Multiple Object Tracking

Primitive Generation and Semantic-Related Alignment for Universal Zero-Shot Segmentation

Semantic-Promoted Debiasing and Background Disambiguation for Zero-Shot Instance Segmentation

Mask-Free Video Instance Segmentation

Federated Incremental Semantic Segmentation

Boundary-Aware Feature Propagation for Scene Segmentation

Else-Net: Elastic Semantic Network for Continual Action Recognition From Skeleton Data

Interaction via Bi-Directional Graph of Semantic Region Affinity for Scene Parsing

Vision-Language Transformer and Query Generation for Referring Segmentation

Discovering Human Interactions With Large-Vocabulary Objects via Query and Multi-Scale Detection

Prototypical Matching and Open Set Rejection for Zero-Shot Semantic Segmentation

MINE: Towards Continuous Depth MPI With NeRF for Novel View Synthesis

A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder

Meta Navigator: Search for a Good Adaptation Policy for Few-Shot Learning

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

MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions

MOSE: A New Dataset for Video Object Segmentation in Complex Scenes

Global Knowledge Calibration for Fast Open-Vocabulary Segmentation

Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation

PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click

Tracking Every Thing in the Wild

Video Mask Transfiner for High-Quality Video Instance Segmentation

Deep Geometrized Cartoon Line Inbetweening

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

Adaptive Data Augmentation on Temporal Graphs

Directed Graph Contrastive Learning

Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning

Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging

SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process