Lei Fan

papers

127

total citations

papers (12)

GrainSpace: A Large-Scale Dataset for Fine-Grained and Domain-Adaptive Recognition of Cereal Grains

CVPR 2022arXiv

citations

MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objects

CVPR 2025arXiv

citations

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

CVPR 2024arXiv

citations

Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation

CVPR 2025arXiv

citations

Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detection

ICCV 2025arXiv

citations

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

CVPR 2024arXiv

citations

DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation

ICCV 2025arXiv

citations

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

ICCV 2021

citations

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

CVPR 2025

citations

Lei Fan

papers (12)

GrainSpace: A Large-Scale Dataset for Fine-Grained and Domain-Adaptive Recognition of Cereal Grains

MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objects

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

Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation

GRPose: Learning Graph Relations for Human Image Generation with Pose Priors

Interpretable Image Classification via Non-parametric Part Prototype Learning

Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance

Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detection

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

DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation

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

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

papers (12)

GrainSpace: A Large-Scale Dataset for Fine-Grained and Domain-Adaptive Recognition of Cereal Grains

MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objects

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

Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation

GRPose: Learning Graph Relations for Human Image Generation with Pose Priors

Interpretable Image Classification via Non-parametric Part Prototype Learning

Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance

Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detection

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

DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation

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

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