Wei Wang

98

Papers

296

Total Citations

Papers (98)

Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition

Correlation Matching Transformation Transformers for UHD Image Restoration

MathAttack: Attacking Large Language Models towards Math Solving Ability

AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis

Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World

Security Attacks on LLM-based Code Completion Tools

Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks

InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct

Within the Dynamic Context: Inertia-aware 3D Human Modeling with Pose Sequence

BearLLM: A Prior Knowledge-Enhanced Bearing Health Management Framework with Unified Vibration Signal Representation

Arbitrary Reading Order Scene Text Spotter with Local Semantics Guidance

Liberating Seen Classes: Boosting Few-Shot and Zero-Shot Text Classification via Anchor

S^3D-NeRF: Single-Shot Speech-Driven Neural Radiance Field for High Fidelity Talking Head Synthesis

Memorize and Rank: Elevating Large Language Models for Clinical Diagnosis Prediction

IDEA-Bench: How Far are Generative Models from Professional Designing?

Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Series

Promptable Representation Distribution Learning and Data Augmentation for Gigapixel Histopathology WSI Analysis

When to Grow? A Fitting Risk-Aware Policy for Layer Growing in Deep Neural Networks

ScaleOT: Privacy-utility-scalable Offsite-tuning with Dynamic LayerReplace and Selective Rank Compression

Multi-Label Few-Shot Image Classification via Pairwise Feature Augmentation and Flexible Prompt Learning

S$^3$E: Self-Supervised State Estimation for Radar-Inertial System

Unsupervised Region-Based Image Editing of Denoising Diffusion Models

Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical

Batch Singular Value Polarization and Weighted Semantic Augmentation for Universal Domain Adaptation

SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models

Hierarchical Recurrent Neural Network for Skeleton Based Action Recognition

Recurrent Face Aging

Instance-Aware Image and Sentence Matching With Selective Multimodal LSTM

See the Forest for the Trees: Joint Spatial and Temporal Recurrent Neural Networks for Video-Based Person Re-Identification

Multistage Adversarial Losses for Pose-Based Human Image Synthesis

Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation

Every Smile Is Unique: Landmark-Guided Diverse Smile Generation

M3: Multimodal Memory Modelling for Video Captioning

An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition

Single-Stage 6D Object Pose Estimation

Cross-Modal Cross-Domain Moment Alignment Network for Person Search

Exploring Adversarial Fake Images on Face Manifold

Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation

MUST-GAN: Multi-Level Statistics Transfer for Self-Driven Person Image Generation

Locate Then Segment: A Strong Pipeline for Referring Image Segmentation

Dynamically Instance-Guided Adaptation: A Backward-Free Approach for Test-Time Domain Adaptive Semantic Segmentation

Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation

Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers

Conditional High-Order Boltzmann Machine: A Supervised Learning Model for Relation Learning

FoveaNet: Perspective-Aware Urban Scene Parsing

Recurrent 3D-2D Dual Learning for Large-Pose Facial Landmark Detection

Recurrent U-Net for Resource-Constrained Segmentation

Enhancing Low Light Videos by Exploring High Sensitivity Camera Noise

CFSNet: Toward a Controllable Feature Space for Image Restoration

Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling?

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

Towards Robustness of Deep Neural Networks via Regularization

Bidirectional Alignment for Domain Adaptive Detection with Transformers

LEA2: A Lightweight Ensemble Adversarial Attack via Non-overlapping Vulnerable Frequency Regions

D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field

Householder Projector for Unsupervised Latent Semantics Discovery

Kinship Identification through Joint Learning using Kinship Verification Ensembles

3D-Aware Semantic-Guided Generative Model for Human Synthesis

Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations

Batch-Efficient EigenDecomposition for Small and Medium Matrices

Improving Covariance Conditioning of the SVD Meta-Layer by Orthogonality

A Cloud 3D Dataset and Application-Specific Learned Image Compression in Cloud 3D

Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution

HypLiLoc: Towards Effective LiDAR Pose Regression With Hyperbolic Fusion

Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Content

OVG-HQ: Online Video Grounding with Hybrid-modal Queries

Learning Robust Image Watermarking with Lossless Cover Recovery

Critical Forgetting-Based Multi-Scale Disentanglement for Deepfake Detection

Towards Better Robustness Against Natural Corruptions in Document Tampering Localization

Disentangle Nighttime Lens Flares: Self-supervised Generation-based Lens Flare Removal

Deep Hierarchies and Invariant Disease-Indicative Feature Learning for Computer Aided Diagnosis of Multiple Fundus Diseases

A Trusted Lesion-assessment Network for Interpretable Diagnosis of Coronary Artery Disease in Coronary CT Angiography

SdalsNet: Self-Distilled Attention Localization and Shift Network for Unsupervised Camouflaged Object Detection

Intra and Inter Parser-Prompted Transformers for Effective Image Restoration

A Lightweight Sparse Interaction Network for Time Series Forecasting

Multi-view Evidential Learning-based Medical Image Segmentation

Template-Driven LLM-Paraphrased Framework for Tabular Math Word Problem Generation

Federated Weakly Supervised Video Anomaly Detection with Multimodal Prompt

Generalizing across Temporal Domains with Koopman Operators

Deep Variational Incomplete Multi-View Clustering: Exploring Shared Clustering Structures

Learning Dense Correspondence for NeRF-Based Face Reenactment

STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models

No More Ambiguity in 360° Room Layout via Bi-Layout Estimation

VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context

Improved Bounds for Pure Private Agnostic Learning: Item-Level and User-Level Privacy

Backpropagation-Friendly Eigendecomposition

Semi-Supervised Partial Label Learning via Confidence-Rated Margin Maximization

Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations

KS-GNN: Keywords Search over Incomplete Graphs via Graphs Neural Network

Collaborative Learning by Detecting Collaboration Partners

RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection

CryptoGCN: Fast and Scalable Homomorphically Encrypted Graph Convolutional Network Inference

Binary Classification with Confidence Difference

PromptRestorer: A Prompting Image Restoration Method with Degradation Perception

RRHF: Rank Responses to Align Language Models with Human Feedback

Penguin: Parallel-Packed Homomorphic Encryption for Fast Graph Convolutional Network Inference

Semi-Supervised Domain Generalization with Known and Unknown Classes

Universality and Limitations of Prompt Tuning