Ping Hu

21

Papers

66

Total Citations

Papers (21)

Koala: Key Frame-Conditioned Long Video-LLM

Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding

Boundary Probing for Input Privacy Protection When Using LMM Services

FineRS: Fine-grained Reasoning and Segmentation of Small Objects with Reinforcement Learning

Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters

Global Context-Aware Attention LSTM Networks for 3D Action Recognition

Deep Level Sets for Salient Object Detection

Motion-Guided Cascaded Refinement Network for Video Object Segmentation

Inverse Discriminative Networks for Handwritten Signature Verification

Temporally Distributed Networks for Fast Video Semantic Segmentation

ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenes

Many-to-Many Splatting for Efficient Video Frame Interpolation

Token Boosting for Robust Self-Supervised Visual Transformer Pre-Training

GAIT: Generating Aesthetic Indoor Tours with Deep Reinforcement Learning

Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation

Learning to Detect Every Thing in an Open World

Towards Explicit Geometry-Reflectance Collaboration for Generalized LiDAR Segmentation in Adverse Weather

JTD-UAV: MLLM-Enhanced Joint Tracking and Description Framework for Anti-UAV Systems

Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation

DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations

Joint Attribute and Model Generalization Learning for Privacy-Preserving Action Recognition