Nannan Wang

42

Papers

96

Total Citations

Papers (42)

Disentangled Prompt Representation for Domain Generalization

Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model

Multi-Scene Generalized Trajectory Global Graph Solver with Composite Nodes for Multiple Object Tracking

Robust Training of Federated Models with Extremely Label Deficiency

Multi-Label Prototype Visual Spatial Search for Weakly Supervised Semantic Segmentation

DynPose: Largely Improving the Efficiency of Human Pose Estimation by a Simple Dynamic Framework

Dual Domain Control via Active Learning for Remote Sensing Domain Incremental Object Detection

Effective Diffusion Transformer Architecture for Image Super-Resolution

Thinking Racial Bias in Fair Forgery Detection: Models, Datasets and Evaluations

Motion Artifact Removal in Pixel-Frequency Domain via Alternate Masks and Diffusion Model

Mitigating Feature Gap for Adversarial Robustness by Feature Disentanglement

Optimizing Label Assignment for Weakly Supervised Person Search

QuARF: Quality-Adaptive Receptive Fields for Degraded Image Perception

Asymmetric Reinforcing Against Multi-Modal Representation Bias

Training Consistent Mixture-of-Experts-Based Prompt Generator for Continual Learning

Point Deformable Network with Enhanced Normal Embedding for Point Cloud Analysis

SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation

Generating Handwritten Mathematical Expressions From Symbol Graphs: An End-to-End Pipeline

Task-aware Orthogonal Sparse Network for Exploring Shared Knowledge in Continual Learning

Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer

Instance-Dependent Label-Noise Learning With Manifold-Regularized Transition Matrix Estimation

Towards Semi-Supervised Deep Facial Expression Recognition With an Adaptive Confidence Margin

Exploring Set Similarity for Dense Self-Supervised Representation Learning

Boosting Weakly-Supervised Temporal Action Localization With Text Information

Masked and Adaptive Transformer for Exemplar Based Image Translation

NAR-Former: Neural Architecture Representation Learning Towards Holistic Attributes Prediction

Removing Adversarial Noise in Class Activation Feature Space

Syncretic Modality Collaborative Learning for Visible Infrared Person Re-Identification

Hiding Visual Information via Obfuscating Adversarial Perturbations

Human-Inspired Facial Sketch Synthesis with Dynamic Adaptation

All-to-Key Attention for Arbitrary Style Transfer

Binarized Neural Network for Single Image Super Resolution

Support-Set Based Cross-Supervision for Video Grounding

Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization

ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning

Q-Norm: Robust Representation Learning via Quality-Adaptive Normalization

DIH-CLIP: Unleashing the Diversity of Multi-Head Self-Attention for Training-Free Open-Vocabulary Semantic Segmentation

3D Test-time Adaptation via Graph Spectral Driven Point Shift

Are Anchor Points Really Indispensable in Label-Noise Learning?

Part-dependent Label Noise: Towards Instance-dependent Label Noise

Class-Dependent Label-Noise Learning with Cycle-Consistency Regularization

NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning