Changhu Wang

papers

2,550

total citations

papers (22)

DREAM: Decoupled Discriminative Learning with Bigraph-aware Alignment for Semi-supervised 2D-3D Cross-modal Retrieval

AAAI 2025

citations

Changhu Wang

papers (22)

Sparse R-CNN: End-to-End Object Detection With Learnable Proposals

Involution: Inverting the Inherence of Convolution for Visual Recognition

Learning the Best Pooling Strategy for Visual Semantic Embedding

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

Mining Contextual Information Beyond Image for Semantic Segmentation

Cross-Category Video Highlight Detection via Set-Based Learning

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

TrackGo: A Flexible and Efficient Method for Controllable Video Generation

Weakly Supervised Person Search With Region Siamese Networks

Unifying Nonlocal Blocks for Neural Networks

LaVin-DiT: Large Vision Diffusion Transformer

Contextual Text Block Detection towards Scene Text Understanding

MT-ORL: Multi-Task Occlusion Relationship Learning

Adaptive Data Augmentation on Temporal Graphs

TRACI: A Data-centric Approach for Multi-Domain Generalization on Graphs

Non-Local Neural Networks With Grouped Bilinear Attentional Transforms

Improving Convolutional Networks With Self-Calibrated Convolutions

Is normalization indispensable for training deep neural network?

Unsupervised Real-World Super-Resolution: A Domain Adaptation Perspective

Directed Graph Contrastive Learning

Domain-Invariant Disentangled Network for Generalizable Object Detection

DREAM: Decoupled Discriminative Learning with Bigraph-aware Alignment for Semi-supervised 2D-3D Cross-modal Retrieval

papers (22)

Sparse R-CNN: End-to-End Object Detection With Learnable Proposals

Involution: Inverting the Inherence of Convolution for Visual Recognition

Learning the Best Pooling Strategy for Visual Semantic Embedding

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

Mining Contextual Information Beyond Image for Semantic Segmentation

Cross-Category Video Highlight Detection via Set-Based Learning

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

TrackGo: A Flexible and Efficient Method for Controllable Video Generation

Weakly Supervised Person Search With Region Siamese Networks

Unifying Nonlocal Blocks for Neural Networks

LaVin-DiT: Large Vision Diffusion Transformer

Contextual Text Block Detection towards Scene Text Understanding

MT-ORL: Multi-Task Occlusion Relationship Learning

Adaptive Data Augmentation on Temporal Graphs

TRACI: A Data-centric Approach for Multi-Domain Generalization on Graphs

Non-Local Neural Networks With Grouped Bilinear Attentional Transforms

Improving Convolutional Networks With Self-Calibrated Convolutions

Is normalization indispensable for training deep neural network?

Unsupervised Real-World Super-Resolution: A Domain Adaptation Perspective

Directed Graph Contrastive Learning

Domain-Invariant Disentangled Network for Generalizable Object Detection

DREAM: Decoupled Discriminative Learning with Bigraph-aware Alignment for Semi-supervised 2D-3D Cross-modal Retrieval