Picture for Xiaotian Li

Xiaotian Li

GAFusion: Adaptive Fusing LiDAR and Camera with Multiple Guidance for 3D Object Detection

Add code
Nov 01, 2024
Viaarxiv icon

The Diversity Bonus: Learning from Dissimilar Distributed Clients in Personalized Federated Learning

Add code
Jul 22, 2024
Viaarxiv icon

MOFA: A Model Simplification Roadmap for Image Restoration on Mobile Devices

Add code
Aug 24, 2023
Viaarxiv icon

HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer

Add code
May 05, 2023
Viaarxiv icon

Weakly-Supervised Text-driven Contrastive Learning for Facial Behavior Understanding

Add code
Mar 31, 2023
Viaarxiv icon

Multimodal Learning with Channel-Mixing and Masked Autoencoder on Facial Action Unit Detection

Add code
Sep 25, 2022
Figure 1 for Multimodal Learning with Channel-Mixing and Masked Autoencoder on Facial Action Unit Detection
Figure 2 for Multimodal Learning with Channel-Mixing and Masked Autoencoder on Facial Action Unit Detection
Figure 3 for Multimodal Learning with Channel-Mixing and Masked Autoencoder on Facial Action Unit Detection
Figure 4 for Multimodal Learning with Channel-Mixing and Masked Autoencoder on Facial Action Unit Detection
Viaarxiv icon

Knowledge-Spreader: Learning Facial Action Unit Dynamics with Extremely Limited Labels

Add code
Mar 30, 2022
Figure 1 for Knowledge-Spreader: Learning Facial Action Unit Dynamics with Extremely Limited Labels
Figure 2 for Knowledge-Spreader: Learning Facial Action Unit Dynamics with Extremely Limited Labels
Figure 3 for Knowledge-Spreader: Learning Facial Action Unit Dynamics with Extremely Limited Labels
Figure 4 for Knowledge-Spreader: Learning Facial Action Unit Dynamics with Extremely Limited Labels
Viaarxiv icon

An EEG-Based Multi-Modal Emotion Database with Both Posed and Authentic Facial Actions for Emotion Analysis

Add code
Mar 29, 2022
Figure 1 for An EEG-Based Multi-Modal Emotion Database with Both Posed and Authentic Facial Actions for Emotion Analysis
Figure 2 for An EEG-Based Multi-Modal Emotion Database with Both Posed and Authentic Facial Actions for Emotion Analysis
Figure 3 for An EEG-Based Multi-Modal Emotion Database with Both Posed and Authentic Facial Actions for Emotion Analysis
Figure 4 for An EEG-Based Multi-Modal Emotion Database with Both Posed and Authentic Facial Actions for Emotion Analysis
Viaarxiv icon

Your "Attention" Deserves Attention: A Self-Diversified Multi-Channel Attention for Facial Action Analysis

Add code
Mar 23, 2022
Figure 1 for Your "Attention" Deserves Attention: A Self-Diversified Multi-Channel Attention for Facial Action Analysis
Figure 2 for Your "Attention" Deserves Attention: A Self-Diversified Multi-Channel Attention for Facial Action Analysis
Figure 3 for Your "Attention" Deserves Attention: A Self-Diversified Multi-Channel Attention for Facial Action Analysis
Figure 4 for Your "Attention" Deserves Attention: A Self-Diversified Multi-Channel Attention for Facial Action Analysis
Viaarxiv icon

Digging Into Self-Supervised Learning of Feature Descriptors

Add code
Oct 10, 2021
Figure 1 for Digging Into Self-Supervised Learning of Feature Descriptors
Figure 2 for Digging Into Self-Supervised Learning of Feature Descriptors
Figure 3 for Digging Into Self-Supervised Learning of Feature Descriptors
Figure 4 for Digging Into Self-Supervised Learning of Feature Descriptors
Viaarxiv icon