Picture for Shaohua Dong

Shaohua Dong

LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking

Add code
May 27, 2024
Figure 1 for LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking
Figure 2 for LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking
Figure 3 for LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking
Figure 4 for LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking
Viaarxiv icon

Beyond MOT: Semantic Multi-Object Tracking

Add code
Mar 11, 2024
Viaarxiv icon

VastTrack: Vast Category Visual Object Tracking

Add code
Mar 06, 2024
Viaarxiv icon

Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning

Add code
Dec 04, 2023
Figure 1 for Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning
Figure 2 for Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning
Figure 3 for Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning
Figure 4 for Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning
Viaarxiv icon

Edge-aware Guidance Fusion Network for RGB Thermal Scene Parsing

Add code
Dec 09, 2021
Figure 1 for Edge-aware Guidance Fusion Network for RGB Thermal Scene Parsing
Figure 2 for Edge-aware Guidance Fusion Network for RGB Thermal Scene Parsing
Figure 3 for Edge-aware Guidance Fusion Network for RGB Thermal Scene Parsing
Figure 4 for Edge-aware Guidance Fusion Network for RGB Thermal Scene Parsing
Viaarxiv icon