Lin Zhao

15

Papers

136

Total Citations

Papers (15)

Towards Learning a Generalist Model for Embodied Navigation

FD2-Net: Frequency-Driven Feature Decomposition Network for Infrared-Visible Object Detection

FED-PsyAU: Privacy-Preserving Micro-Expression Recognition via Psychological AU Coordination and Dynamic Facial Motion Modeling

DynPose: Largely Improving the Efficiency of Human Pose Estimation by a Simple Dynamic Framework

Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation

Label-Efficient Data Augmentation with Video Diffusion Models for Guidewire Segmentation in Cardiac Fluoroscopy

SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation

Prototype-based Contrastive Learning with Stage-wise Progressive Augmentation for Self-Supervised Fine-Grained Learning

Provable Discriminative Hyperspherical Embedding for Out-of-Distribution Detection

An Asymmetric Augmented Self-Supervised Learning Method for Unsupervised Fine-Grained Image Hashing

Deep Dive Into Gradients: Better Optimization for 3D Object Detection With Gradient-Corrected IoU Supervision

Deep Symmetric Network for Underexposed Image Enhancement With Recurrent Attentional Learning

Finite-Time Analysis for Double Q-learning

Faster Non-asymptotic Convergence for Double Q-learning

Finite-Time Analysis of Single-Timescale Actor-Critic