Picture for Honghai Liu

Honghai Liu

Language-Assisted Human Part Motion Learning for Skeleton-Based Temporal Action Segmentation

Add code
Oct 08, 2024
Figure 1 for Language-Assisted Human Part Motion Learning for Skeleton-Based Temporal Action Segmentation
Figure 2 for Language-Assisted Human Part Motion Learning for Skeleton-Based Temporal Action Segmentation
Figure 3 for Language-Assisted Human Part Motion Learning for Skeleton-Based Temporal Action Segmentation
Figure 4 for Language-Assisted Human Part Motion Learning for Skeleton-Based Temporal Action Segmentation
Viaarxiv icon

Online 4D Ultrasound-Guided Robotic Tracking Enables 3D Ultrasound Localisation Microscopy with Large Tissue Displacements

Add code
Sep 17, 2024
Figure 1 for Online 4D Ultrasound-Guided Robotic Tracking Enables 3D Ultrasound Localisation Microscopy with Large Tissue Displacements
Figure 2 for Online 4D Ultrasound-Guided Robotic Tracking Enables 3D Ultrasound Localisation Microscopy with Large Tissue Displacements
Figure 3 for Online 4D Ultrasound-Guided Robotic Tracking Enables 3D Ultrasound Localisation Microscopy with Large Tissue Displacements
Figure 4 for Online 4D Ultrasound-Guided Robotic Tracking Enables 3D Ultrasound Localisation Microscopy with Large Tissue Displacements
Viaarxiv icon

The Unified Balance Theory of Second-Moment Exponential Scaling Optimizers in Visual Tasks

Add code
May 28, 2024
Viaarxiv icon

Exploring Self- and Cross-Triplet Correlations for Human-Object Interaction Detection

Add code
Jan 11, 2024
Viaarxiv icon

A Simple Asymmetric Momentum Make SGD Greatest Again

Add code
Sep 05, 2023
Viaarxiv icon

Full Resolution Repetition Counting

Add code
May 24, 2023
Figure 1 for Full Resolution Repetition Counting
Figure 2 for Full Resolution Repetition Counting
Figure 3 for Full Resolution Repetition Counting
Figure 4 for Full Resolution Repetition Counting
Viaarxiv icon

Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimation

Add code
Mar 09, 2023
Figure 1 for Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimation
Figure 2 for Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimation
Figure 3 for Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimation
Figure 4 for Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimation
Viaarxiv icon

CountingMOT: Joint Counting, Detection and Re-Identification for Multiple Object Tracking

Add code
Dec 12, 2022
Figure 1 for CountingMOT: Joint Counting, Detection and Re-Identification for Multiple Object Tracking
Figure 2 for CountingMOT: Joint Counting, Detection and Re-Identification for Multiple Object Tracking
Figure 3 for CountingMOT: Joint Counting, Detection and Re-Identification for Multiple Object Tracking
Figure 4 for CountingMOT: Joint Counting, Detection and Re-Identification for Multiple Object Tracking
Viaarxiv icon

Deep Depth Completion: A Survey

Add code
May 17, 2022
Figure 1 for Deep Depth Completion: A Survey
Figure 2 for Deep Depth Completion: A Survey
Figure 3 for Deep Depth Completion: A Survey
Figure 4 for Deep Depth Completion: A Survey
Viaarxiv icon

Dense 3D Facial Reconstruction from a Single Depth Image in Unconstrained Environment

Add code
Apr 24, 2017
Figure 1 for Dense 3D Facial Reconstruction from a Single Depth Image in Unconstrained Environment
Figure 2 for Dense 3D Facial Reconstruction from a Single Depth Image in Unconstrained Environment
Figure 3 for Dense 3D Facial Reconstruction from a Single Depth Image in Unconstrained Environment
Figure 4 for Dense 3D Facial Reconstruction from a Single Depth Image in Unconstrained Environment
Viaarxiv icon