Mao Ye

10

Papers

144

Total Citations

Papers (10)

Source-Free Domain Adaptation with Frozen Multimodal Foundation Model

OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation

Motion Prior Knowledge Learning with Homogeneous Language Descriptions for Moving Infrared Small Target Detection

Bayesian Test-Time Adaptation for Vision-Language Models

Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification

Self-Prompting Analogical Reasoning for UAV Object Detection

FreeCap: Hybrid Calibration-Free Motion Capture in Open Environments

Pseudo Visible Feature Fine-Grained Fusion for Thermal Object Detection

High Dynamic Range Novel View Synthesis with Single Exposure

Domain Adaptive Diabetic Retinopathy Grading with Model Absence and Flowing Data