Hao Huang

papers

311

total citations

papers (12)

FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification

ECCV 2024arXiv

citations

OpenVIS: Open-vocabulary Video Instance Segmentation

AAAI 2025arXiv

citations

Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection

ECCV 2024arXiv

citations

Learning Diffusions under Uncertainty

AAAI 2024arXiv

citations

Manifold Adversarial Learning for Cross-Domain 3D Shape Representation

ECCV 2022

citations

Energy-Efficient Streaming Time Series Classification with Attentive Power Iteration

AAAI 2024

citations

Wavelet Policy: Lifting Scheme for Policy Learning in Long-Horizon Tasks

ICCV 2025arXiv

citations

QI-IRA: Quantum-Inspired Interactive Ranking Aggregation for Person Re-identification

AAAI 2024

citations

Hao Huang

papers (12)

T-SEA: Transfer-Based Self-Ensemble Attack on Object Detection

FairCLIP: Harnessing Fairness in Vision-Language Learning

Fine-Grained Predicates Learning for Scene Graph Generation

Efficient Decision-based Black-box Patch Attacks on Video Recognition

FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification

OpenVIS: Open-vocabulary Video Instance Segmentation

Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection

Learning Diffusions under Uncertainty

Manifold Adversarial Learning for Cross-Domain 3D Shape Representation

Energy-Efficient Streaming Time Series Classification with Attentive Power Iteration

Wavelet Policy: Lifting Scheme for Policy Learning in Long-Horizon Tasks

QI-IRA: Quantum-Inspired Interactive Ranking Aggregation for Person Re-identification

papers (12)

T-SEA: Transfer-Based Self-Ensemble Attack on Object Detection

FairCLIP: Harnessing Fairness in Vision-Language Learning

Fine-Grained Predicates Learning for Scene Graph Generation

Efficient Decision-based Black-box Patch Attacks on Video Recognition

FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification

OpenVIS: Open-vocabulary Video Instance Segmentation

Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection

Learning Diffusions under Uncertainty

Manifold Adversarial Learning for Cross-Domain 3D Shape Representation

Energy-Efficient Streaming Time Series Classification with Attentive Power Iteration

Wavelet Policy: Lifting Scheme for Policy Learning in Long-Horizon Tasks

QI-IRA: Quantum-Inspired Interactive Ranking Aggregation for Person Re-identification