Picture for Xiangmin Xu

Xiangmin Xu

University of Glasgow, United Kingdom

SleepCoT: A Lightweight Personalized Sleep Health Model via Chain-of-Thought Distillation

Add code
Oct 22, 2024
Viaarxiv icon

Task-Oriented Edge-Assisted Cooperative Data Compression, Communications and Computing for UGV-Enhanced Warehouse Logistics

Add code
Oct 02, 2024
Viaarxiv icon

Multi-Scale Temporal Transformer For Speech Emotion Recognition

Add code
Oct 01, 2024
Viaarxiv icon

Online Multi-level Contrastive Representation Distillation for Cross-Subject fNIRS Emotion Recognition

Add code
Sep 24, 2024
Viaarxiv icon

AS-Speech: Adaptive Style For Speech Synthesis

Add code
Sep 09, 2024
Viaarxiv icon

Timeliness-Fidelity Tradeoff in 3D Scene Representations

Add code
Jul 23, 2024
Figure 1 for Timeliness-Fidelity Tradeoff in 3D Scene Representations
Figure 2 for Timeliness-Fidelity Tradeoff in 3D Scene Representations
Figure 3 for Timeliness-Fidelity Tradeoff in 3D Scene Representations
Figure 4 for Timeliness-Fidelity Tradeoff in 3D Scene Representations
Viaarxiv icon

Real-Time Interactions Between Human Controllers and Remote Devices in Metaverse

Add code
Jul 23, 2024
Viaarxiv icon

VideoCoT: A Video Chain-of-Thought Dataset with Active Annotation Tool

Add code
Jul 07, 2024
Viaarxiv icon

Disentangled Pre-training for Human-Object Interaction Detection

Add code
Apr 02, 2024
Figure 1 for Disentangled Pre-training for Human-Object Interaction Detection
Figure 2 for Disentangled Pre-training for Human-Object Interaction Detection
Figure 3 for Disentangled Pre-training for Human-Object Interaction Detection
Figure 4 for Disentangled Pre-training for Human-Object Interaction Detection
Viaarxiv icon

Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On

Add code
Apr 01, 2024
Viaarxiv icon