Qinghua Hu

23

Papers

174

Total Citations

Papers (23)

ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection

AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning

Hierarchical Classification Auxiliary Network for Time Series Forecasting

Visible and Clear: Finding Tiny Objects in Difference Map

Exploring Diverse Representations for Open Set Recognition

Every Node Is Different: Dynamically Fusing Self-Supervised Tasks for Attributed Graph Clustering

Patch-wise Structural Loss for Time Series Forecasting

Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning

Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model

Ahpatron: A New Budgeted Online Kernel Learning Machine with Tighter Mistake Bound

TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition

CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification

Public Opinion Field Effect and Hawkes Process Join Hands for Information Popularity Prediction

DALIP: Distribution Alignment-based Language-Image Pre-Training for Domain-Specific Data

Bi-directional Adapter for Multimodal Tracking

Decoupled Multi-Predictor Optimization for Inference-Efficient Model Tuning

Unknown Text Learning for CLIP-based Few-Shot Open-set Recognition

Task-Customized Mixture of Adapters for General Image Fusion

Online Clustering of Dueling Bandits

Reducing Class-wise Confusion for Incremental Learning with Disentangled Manifolds

Predictive Dynamic Fusion

Asymmetric Reinforcing Against Multi-Modal Representation Bias

Socialized Learning: Making Each Other Better Through Multi-Agent Collaboration