A5022349020- Advanced Image and Video Retrieval Techniques
- Remote-Sensing Image Classification
- Image Retrieval and Classification Techniques
- Advanced Graph Theory Research
- Limits and Structures in Graph Theory
- Visual Attention and Saliency Detection
- Graph theory and applications
The University of Sydney
2024
Shanghai University
2024
In the field of Moving Infrared Small Target Detection (MIRSTD), current methods typically use sequential modeling with two individual modules for spatial and temporal processing. However, such a strategy lacks clear guidance on motion displacement difference between moving targets background noise, thereby limiting feature discriminability resulting in error-prone target localization. This paper addresses this issue from clip frame levels proposes novel architecture MOCID MIRSTD. For...
Obtaining image-level class labels for Remote Sensing (RS) images is a relatively straightforward process, sparking significant interest in Weakly Supervised Semantic Segmentation (WSSS). However, RS present challenges beyond those encountered generic WSSS, including complex backgrounds, densely distributed small objects, and considerable scale variations. To address above issues, we introduce COnsistency-COnstrained Multi-Class Attention model, noted as <italic...
Due to spatial redundancy in remote sensing images, sparse tokens containing rich information are usually involved self-attention (SA) reduce the overall token numbers within calculation, avoiding high computational cost issue Vision Transformers. However, such methods obtain by hand-crafted or parallel-unfriendly designs, posing a challenge reach better balance between efficiency and performance. Different from them, this paper proposes use learnable meta formulate tokens, which effectively...
Due to spatial redundancy in remote sensing images, sparse tokens containing rich information are usually involved self-attention (SA) reduce the overall token numbers within calculation, avoiding high computational cost issue Vision Transformers. However, such methods obtain by hand-crafted or parallel-unfriendly designs, posing a challenge reach better balance between efficiency and performance. Different from them, this paper proposes use learnable meta formulate tokens, which effectively...