Dong Wang

80

Papers

567

Total Citations

Papers (80)

GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting

NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions

SUTrack: Towards Simple and Unified Single Object Tracking

Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models

Exploring Enhanced Contextual Information for Video-Level Object Tracking

Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking

EvSign: Sign Language Recognition and Translation with Streaming Events

X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-Modal Knowledge Transfer

Color Event Enhanced Single-Exposure HDR Imaging

Open-Vocabulary Octree-Graph for 3D Scene Understanding

CLIP-driven View-aware Prompt Learning for Unsupervised Vehicle Re-identification

Hybrid Latent Reasoning via Reinforcement Learning

Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games

Efficient Motion Prompt Learning for Robust Visual Tracking

HPL-ESS: Hybrid Pseudo-Labeling for Unsupervised Event-based Semantic Segmentation

Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters

Implicit Event-RGBD Neural SLAM

Learning to Detect Salient Objects With Image-Level Supervision

Correlation Tracking via Joint Discrimination and Reliability Learning

Defocus Blur Detection via Multi-Stream Bottom-Top-Bottom Fully Convolutional Network

Learning Spatial-Aware Regressions for Visual Tracking

Visual Tracking via Adaptive Spatially-Regularized Correlation Filters

ROI Pooled Correlation Filters for Visual Tracking

Listen to the Image

A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision

Cooling-Shrinking Attack: Blinding the Tracker With Imperceptible Noises

FocalMix: Semi-Supervised Learning for 3D Medical Image Detection

High-Performance Long-Term Tracking With Meta-Updater

Transformer Tracking

LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search

Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation

Wasserstein Contrastive Representation Distillation

Balanced Multimodal Learning via On-the-Fly Gradient Modulation

Show, Deconfound and Tell: Image Captioning With Causal Inference

Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline

Fully Self-Supervised Depth Estimation From Defocus Clue

Representation Learning for Visual Object Tracking by Masked Appearance Transfer

SeqTrack: Sequence to Sequence Learning for Visual Object Tracking

Universal Instance Perception As Object Discovery and Retrieval

Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks

Visual Prompt Multi-Modal Tracking

One-Shot High-Fidelity Talking-Head Synthesis With Deformable Neural Radiance Field

Propagate and Calibrate: Real-Time Passive Non-Line-of-Sight Tracking

Low-Rank Matrix Factorization Under General Mixture Noise Distributions

Amulet: Aggregating Multi-Level Convolutional Features for Salient Object Detection

Improving Transferable Targeted Attacks with Feature Tuning Mixup

Stepwise Metric Promotion for Unsupervised Video Person Re-Identification

'Skimming-Perusal' Tracking: A Framework for Real-Time and Robust Long-Term Tracking

GradNet: Gradient-Guided Network for Visual Object Tracking

Pyramid Spatial-Temporal Aggregation for Video-Based Person Re-Identification

Learning Spatio-Temporal Transformer for Visual Tracking

Video Annotation for Visual Tracking via Selection and Refinement

HSR-Diff: Hyperspectral Image Super-Resolution via Conditional Diffusion Models

Towards Nonlinear-Motion-Aware and Occlusion-Robust Rolling Shutter Correction

ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding

Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking

Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement

PointScatter: Point Set Representation for Tubular Structure Extraction

Check and Link: Pairwise Lesion Correspondence Guides Mammogram Mass Detection

Towards Grand Unification of Object Tracking

Learning Uncertain Convolutional Features for Accurate Saliency Detection

Efficient Diffusion as Low Light Enhancer

Phoenix: A Motion-based Self-Reflection Framework for Fine-grained Robotic Action Correction

Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulation

DeformCL: Learning Deformable Centerline Representation for Vessel Extraction in 3D Medical Image

CAT: A Unified Click-and-Track Framework for Realistic Tracking

MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation

Anti-Tamper Protection for Unauthorized Individual Image Generation

VehicleMAE: View-asymmetry Mutual Learning for Vehicle Re-identification Pre-training via Masked AutoEncoders

AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations

Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding

Knowledge Graph Completion with Relation-Aware Anchor Enhancement

Box2Poly: Memory

Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking

BRITS: Bidirectional Recurrent Imputation for Time Series

On Fenchel Mini-Max Learning

Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training

Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization

Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning

Cross-Domain Policy Adaptation via Value-Guided Data Filtering