4 papers
SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention
Qi Zhao, Qirui Li, Hanlin Tang +10
Diffusion Transformers (DiTs) incur quadratic self-attention cost over spatiotemporal tokens. Existing training-free sparse attention methods often construct sparse masks from bloc…
MSCA-Net:Multi-Scale Context Aggregation Network for Infrared Small Target Detection
Xiaojin Lu, Taoran yue, Jiaxi cai +3
In complex environments, detecting tiny infrared targets has always been challenging because of the low contrast and high noise levels inherent in infrared images. These factors of…
SDS-Net: Shallow-Deep Synergism-detection Network for infrared small target detection
Taoran Yue, Xiaojin Lu, Jiaxi Cai +2
Current CNN-based infrared small target detection(IRSTD) methods generally overlook the heterogeneity between shallow and deep features, leading to inefficient collaboration betwee…
YOLO-MST: Multiscale deep learning method for infrared small target detection based on super-resolution and YOLO
Taoran Yue, Xiaojin Lu, Jiaxi Cai +2
With the advancement of aerospace technology and the increasing demands of military applications, the development of low false-alarm and high-precision infrared small target detect…