Shuhui Wang

papers

1,893

total citations

papers (27)

Towards Discriminability and Diversity: Batch Nuclear-Norm Maximization Under Label Insufficient Situations

CVPR 2020arXiv

419

citations

Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection

CVPR 2023arXiv

102

citations

Hierarchical Modular Network for Video Captioning

CVPR 2022arXiv

citations

Greedy Gradient Ensemble for Robust Visual Question Answering

ICCV 2021arXiv

citations

Heuristic Domain Adaptation

NEURIPS 2020arXiv

citations

QAIR: Practical Query-Efficient Black-Box Attacks for Image Retrieval

CVPR 2021arXiv

citations

ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing

CVPR 2023arXiv

citations

Attribute Group Editing for Reliable Few-Shot Image Generation

CVPR 2022arXiv

citations

R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation

ICLR 2024arXiv

citations

The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image Generation

ICCV 2023arXiv

citations

Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video

AAAI 2024arXiv

citations

Confusing Pair Correction Based on Category Prototype for Domain Adaptation under Noisy Environments

AAAI 2024arXiv

citations

Video Language Model Pretraining with Spatio-temporal Masking

CVPR 2025

citations

Modeling Language Tokens as Functionals of Semantic Fields

ICML 2024

citations

Relieving the Over-Aggregating Effect in Graph Transformers

NEURIPS 2025arXiv

citations

Dis²Booth: Learning Image Distribution with Disentangled Features for Text-to-Image Diffusion Models

AAAI 2025

citations

MSR: A Multifaceted Self-Retrieval Framework for Microscopic Cascade Prediction

AAAI 2025

citations

DeeCap: Dynamic Early Exiting for Efficient Image Captioning

CVPR 2022

citations

Data-free Neural Representation Compression with Riemannian Neural Dynamics

ICML 2024

citations

Divide-and-Conquer: Tree-structured Strategy with Answer Distribution Estimator for Goal-Oriented Visual Dialogue

AAAI 2025arXiv

citations

Image-to-video Adaptation with Outlier Modeling and Robust Self-learning

AAAI 2025

citations

Interpretable Visual Reasoning via Probabilistic Formulation under Natural Supervision

ECCV 2020

citations

Learning Linguistic Association towards Efficient Text-Video Retrieval

ECCV 2022

citations

Shuhui Wang

papers (27)

Towards Discriminability and Diversity: Batch Nuclear-Norm Maximization Under Label Insufficient Situations

Label Decoupling Framework for Salient Object Detection

Gradually Vanishing Bridge for Adversarial Domain Adaptation

Parsing-Based View-Aware Embedding Network for Vehicle Re-Identification

State-Relabeling Adversarial Active Learning

Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection

Hierarchical Modular Network for Video Captioning

Greedy Gradient Ensemble for Robust Visual Question Answering

Heuristic Domain Adaptation

QAIR: Practical Query-Efficient Black-Box Attacks for Image Retrieval

ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing

Attribute Group Editing for Reliable Few-Shot Image Generation

R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation

The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image Generation

Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video

Confusing Pair Correction Based on Category Prototype for Domain Adaptation under Noisy Environments

Video Language Model Pretraining with Spatio-temporal Masking

Modeling Language Tokens as Functionals of Semantic Fields

Relieving the Over-Aggregating Effect in Graph Transformers

Dis²Booth: Learning Image Distribution with Disentangled Features for Text-to-Image Diffusion Models

MSR: A Multifaceted Self-Retrieval Framework for Microscopic Cascade Prediction

DeeCap: Dynamic Early Exiting for Efficient Image Captioning

Data-free Neural Representation Compression with Riemannian Neural Dynamics

Divide-and-Conquer: Tree-structured Strategy with Answer Distribution Estimator for Goal-Oriented Visual Dialogue

Image-to-video Adaptation with Outlier Modeling and Robust Self-learning

Interpretable Visual Reasoning via Probabilistic Formulation under Natural Supervision

Learning Linguistic Association towards Efficient Text-Video Retrieval

papers (27)

Towards Discriminability and Diversity: Batch Nuclear-Norm Maximization Under Label Insufficient Situations

Label Decoupling Framework for Salient Object Detection

Gradually Vanishing Bridge for Adversarial Domain Adaptation

Parsing-Based View-Aware Embedding Network for Vehicle Re-Identification

State-Relabeling Adversarial Active Learning

Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection

Hierarchical Modular Network for Video Captioning

Greedy Gradient Ensemble for Robust Visual Question Answering

Heuristic Domain Adaptation

QAIR: Practical Query-Efficient Black-Box Attacks for Image Retrieval

ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing

Attribute Group Editing for Reliable Few-Shot Image Generation

R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation

The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image Generation

Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video

Confusing Pair Correction Based on Category Prototype for Domain Adaptation under Noisy Environments

Video Language Model Pretraining with Spatio-temporal Masking

Modeling Language Tokens as Functionals of Semantic Fields

Relieving the Over-Aggregating Effect in Graph Transformers

Dis²Booth: Learning Image Distribution with Disentangled Features for Text-to-Image Diffusion Models

MSR: A Multifaceted Self-Retrieval Framework for Microscopic Cascade Prediction

DeeCap: Dynamic Early Exiting for Efficient Image Captioning

Data-free Neural Representation Compression with Riemannian Neural Dynamics

Divide-and-Conquer: Tree-structured Strategy with Answer Distribution Estimator for Goal-Oriented Visual Dialogue

Image-to-video Adaptation with Outlier Modeling and Robust Self-learning

Interpretable Visual Reasoning via Probabilistic Formulation under Natural Supervision

Learning Linguistic Association towards Efficient Text-Video Retrieval