Ying Wu

30

Papers

17

Total Citations

Papers (30)

Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perception

AutoScape: Geometry-Consistent Long-Horizon Scene Generation

AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving

Active Open-Vocabulary Recognition: Let Intelligent Moving Mitigate CLIP Limitations

Heteroscedastic Max-Min Distance Analysis

Learning Reconstruction-Based Remote Gaze Estimation

Easy Identification From Better Constraints: Multi-Shot Person Re-Identification From Reference Constraints

Does Learning Specific Features for Related Parts Help Human Pose Estimation?

Semi-Supervised Transfer Learning for Image Rain Removal

Visual Query Answering by Entity-Attribute Graph Matching and Reasoning

Online Joint Multi-Metric Adaptation From Frequent Sharing-Subset Mining for Person Re-Identification

TA-Student VQA: Multi-Agents Training by Self-Questioning

Uncertainty-Aware Score Distribution Learning for Action Quality Assessment

Efficient Online Local Metric Adaptation via Negative Samples for Person Re-Identification

Towards a Unified Compositional Model for Visual Pattern Modeling

Learning Robust Facial Landmark Detection via Hierarchical Structured Ensemble

Recognizing Part Attributes With Insufficient Data

Order-Preserving Wasserstein Discriminant Analysis

Morphable Detector for Object Detection on Demand

Contrastive Learning for Label Efficient Semantic Segmentation

FLAR: A Unified Prototype Framework for Few-Sample Lifelong Active Recognition

Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance

Object Detection with a Unified Label Space from Multiple Datasets

Balancing between Forgetting and Acquisition in Incremental Subpopulation Learning

GPVK-VL: Geometry-Preserving Virtual Keyframes for Visual Localization under Large Viewpoint Changes

Incremental Object Keypoint Learning

SynMob: Creating High-Fidelity Synthetic GPS Trajectory Dataset for Urban Mobility Analysis

TOA: Task-oriented Active VQA

Learning Low-Dimensional Temporal Representations

Learning Distance for Sequences by Learning a Ground Metric