Picture for Mengyuan Liu

Mengyuan Liu

Sharing Key Semantics in Transformer Makes Efficient Image Restoration

May 30, 2024
Viaarxiv icon

Prompt When the Animal is: Temporal Animal Behavior Grounding with Positional Recovery Training

Add code
May 09, 2024
Viaarxiv icon

A Survey on Backbones for Deep Video Action Recognition

May 09, 2024
Viaarxiv icon

SATO: Stable Text-to-Motion Framework

Add code
May 02, 2024
Viaarxiv icon

SemiPL: A Semi-supervised Method for Event Sound Source Localization

Add code
Apr 30, 2024
Figure 1 for SemiPL: A Semi-supervised Method for Event Sound Source Localization
Figure 2 for SemiPL: A Semi-supervised Method for Event Sound Source Localization
Figure 3 for SemiPL: A Semi-supervised Method for Event Sound Source Localization
Figure 4 for SemiPL: A Semi-supervised Method for Event Sound Source Localization
Viaarxiv icon

HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action Recognition

Add code
Apr 25, 2024
Figure 1 for HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action Recognition
Figure 2 for HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action Recognition
Figure 3 for HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action Recognition
Figure 4 for HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action Recognition
Viaarxiv icon

SFMViT: SlowFast Meet ViT in Chaotic World

Add code
Apr 25, 2024
Viaarxiv icon

MLP: Motion Label Prior for Temporal Sentence Localization in Untrimmed 3D Human Motions

Add code
Apr 21, 2024
Viaarxiv icon

Point-In-Context: Understanding Point Cloud via In-Context Learning

Add code
Apr 18, 2024
Figure 1 for Point-In-Context: Understanding Point Cloud via In-Context Learning
Figure 2 for Point-In-Context: Understanding Point Cloud via In-Context Learning
Figure 3 for Point-In-Context: Understanding Point Cloud via In-Context Learning
Figure 4 for Point-In-Context: Understanding Point Cloud via In-Context Learning
Viaarxiv icon

VG4D: Vision-Language Model Goes 4D Video Recognition

Add code
Apr 17, 2024
Viaarxiv icon