Rui Huang

papers

1,758

total citations

papers (21)

On the Importance of Gradients for Detecting Distributional Shifts in the Wild

NEURIPS 2021arXiv

433

citations

MOS: Towards Scaling Out-of-Distribution Detection for Large Semantic Space

CVPR 2021arXiv

306

citations

Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition

NEURIPS 2021arXiv

237

citations

Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification

NEURIPS 2020arXiv

167

citations

SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models

CVPR 2024arXiv

143

citations

BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification

CVPR 2021arXiv

106

citations

Exploring Structure-Aware Transformer Over Interaction Proposals for Human-Object Interaction Detection

CVPR 2022arXiv

citations

DenseGrounding: Improving Dense Language-Vision Semantics for Ego-centric 3D Visual Grounding

ICLR 2025arXiv

citations

Video Perception Models for 3D Scene Synthesis

NEURIPS 2025arXiv

citations

3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection

ICCV 2025arXiv

citations

Learning To Generate Language-Supervised and Open-Vocabulary Scene Graph Using Pre-Trained Visual-Semantic Space

CVPR 2023

citations

Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection

ICCV 2021

citations

Coupled Segmentation and Edge Learning via Dynamic Graph Propagation

NEURIPS 2021

citations

Learning Memory Augmented Cascading Network for Compressed Sensing of Images

ECCV 2020

citations

Salient-to-Broad Transition for Video Person Re-Identification

CVPR 2022

citations

Rui Huang

papers (21)

On the Importance of Gradients for Detecting Distributional Shifts in the Wild

MOS: Towards Scaling Out-of-Distribution Detection for Large Semantic Space

Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition

Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification

SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models

BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification

Exploring Structure-Aware Transformer Over Interaction Proposals for Human-Object Interaction Detection

An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds

Efficient Knowledge Distillation from Model Checkpoints

Learning Camera Localization via Dense Scene Matching

DEFOM-Stereo: Depth Foundation Model Based Stereo Matching

Wavelet-Assisted Multi-Frequency Attention Network for Pansharpening

Deep Semantic Statistics Matching (D2SM) Denoising Network

DenseGrounding: Improving Dense Language-Vision Semantics for Ego-centric 3D Visual Grounding

Video Perception Models for 3D Scene Synthesis

3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection

Learning To Generate Language-Supervised and Open-Vocabulary Scene Graph Using Pre-Trained Visual-Semantic Space

Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection

Coupled Segmentation and Edge Learning via Dynamic Graph Propagation

Learning Memory Augmented Cascading Network for Compressed Sensing of Images

Salient-to-Broad Transition for Video Person Re-Identification

papers (21)

On the Importance of Gradients for Detecting Distributional Shifts in the Wild

MOS: Towards Scaling Out-of-Distribution Detection for Large Semantic Space

Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition

Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification

SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models

BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification

Exploring Structure-Aware Transformer Over Interaction Proposals for Human-Object Interaction Detection

An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds

Efficient Knowledge Distillation from Model Checkpoints

Learning Camera Localization via Dense Scene Matching

DEFOM-Stereo: Depth Foundation Model Based Stereo Matching

Wavelet-Assisted Multi-Frequency Attention Network for Pansharpening

Deep Semantic Statistics Matching (D2SM) Denoising Network

DenseGrounding: Improving Dense Language-Vision Semantics for Ego-centric 3D Visual Grounding

Video Perception Models for 3D Scene Synthesis

3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection

Learning To Generate Language-Supervised and Open-Vocabulary Scene Graph Using Pre-Trained Visual-Semantic Space

Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection

Coupled Segmentation and Edge Learning via Dynamic Graph Propagation

Learning Memory Augmented Cascading Network for Compressed Sensing of Images

Salient-to-Broad Transition for Video Person Re-Identification