Picture for Hong Zhang

Hong Zhang

TextInPlace: Indoor Visual Place Recognition in Repetitive Structures with Scene Text Spotting and Verification

Add code
Mar 09, 2025
Viaarxiv icon

ReJSHand: Efficient Real-Time Hand Pose Estimation and Mesh Reconstruction Using Refined Joint and Skeleton Features

Add code
Mar 08, 2025
Viaarxiv icon

Monocular Person Localization under Camera Ego-motion

Add code
Mar 04, 2025
Viaarxiv icon

FlowPlan: Zero-Shot Task Planning with LLM Flow Engineering for Robotic Instruction Following

Add code
Mar 04, 2025
Viaarxiv icon

RPF-Search: Field-based Search for Robot Person Following in Unknown Dynamic Environments

Add code
Mar 04, 2025
Viaarxiv icon

SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion

Add code
Mar 03, 2025
Viaarxiv icon

FUNCTO: Function-Centric One-Shot Imitation Learning for Tool Manipulation

Add code
Feb 17, 2025
Viaarxiv icon

fMoE: Fine-Grained Expert Offloading for Large Mixture-of-Experts Serving

Add code
Feb 07, 2025
Figure 1 for fMoE: Fine-Grained Expert Offloading for Large Mixture-of-Experts Serving
Figure 2 for fMoE: Fine-Grained Expert Offloading for Large Mixture-of-Experts Serving
Figure 3 for fMoE: Fine-Grained Expert Offloading for Large Mixture-of-Experts Serving
Figure 4 for fMoE: Fine-Grained Expert Offloading for Large Mixture-of-Experts Serving
Viaarxiv icon

Rethinking stance detection: A theoretically-informed research agenda for user-level inference using language models

Add code
Feb 04, 2025
Figure 1 for Rethinking stance detection: A theoretically-informed research agenda for user-level inference using language models
Viaarxiv icon

Superpixel Boundary Correction for Weakly-Supervised Semantic Segmentation on Histopathology Images

Add code
Jan 07, 2025
Viaarxiv icon