1 citations · 2 across the 6 of their papers we have counts for
5 papers · 1 filter
Structural and Statistical Texture Knowledge Distillation and Learning for Segmentation
Deyi Ji, Feng Zhao, Hongtao Lu +2
Low-level texture feature/knowledge is also of vital importance for characterizing the local structural pattern and global statistical properties, such as boundary, smoothness, reg…
PPTFormer: Pseudo Multi-Perspective Transformer for UAV Segmentation
Deyi Ji, Wenwei Jin, Hongtao Lu +1
The ascension of Unmanned Aerial Vehicles (UAVs) in various fields necessitates effective UAV image segmentation, which faces challenges due to the dynamic perspectives of UAV-capt…
Discrete Latent Perspective Learning for Segmentation and Detection
Deyi Ji, Feng Zhao, Lanyun Zhu +3
In this paper, we address the challenge of Perspective-Invariant Learning in machine learning and computer vision, which involves enabling a network to understand images from varyi…
View-Centric Multi-Object Tracking with Homographic Matching in Moving UAV
Deyi Ji, Lanyun Zhu, Siqi Gao +8
In this paper, we address the challenge of Multi-Object Tracking (MOT) in moving Unmanned Aerial Vehicle (UAV) scenarios, where irregular flight trajectories, such as hovering, tur…
ChangeNet: Multi-Temporal Asymmetric Change Detection Dataset
Deyi Ji, Siqi Gao, Mingyuan Tao +2
Change Detection (CD) has been attracting extensive interests with the availability of bi-temporal datasets. However, due to the huge cost of multi-temporal images acquisition and…