Dianbin Chen
Shanghai Jiao Tong University
14 Papers
4 Citations
Dianbin Chen is an academic researcher from Shanghai Jiao Tong University. The author has contributed to research in topics: Computer science & Pattern recognition (psychology). The author has an hindex of 2, co-authored 2 publications.
Chat about Author
Papers
A Multilevel Hybrid Transmission Network for Infrared and Visible Image Fusion
Qingqing Li,Guangliang Han,Peixun Liu,Hang Yang,Dianbin Chen,Xinglong Sun,Jiajia Wu,Dongxu Liu +7 more
TL;DR: Experimental results and analyses demonstrate that the proposed multilevel hybrid transmission network for infrared and visible image fusion not only can achieve high-quality image fusion, but also performs better than comparison methods in terms of qualitative and quantitative comparisons.
12
Slight Aware Enhancement Transformer and Multiple Matching Network for Real-Time UAV Tracking
TL;DR: SiamSTM as discussed by the authors proposes a novel siamese neural network tracker that is based on Slight Aware Enhancement Transformer and Multiple matching networks for real-time UAV tracking.
A Multiscale Cross Interaction Attention Network for Hyperspectral Image Classification
Dongxu Liu,Yirui Wang,Peixun Liu,Qingqing Li,Hang Yang,Dianbin Chen,Zhichao Liu,Guangliang Han +7 more
TL;DR: Wang et al. as mentioned in this paper proposed a multiscale cross interaction attention network (MCIANet) for hyperspectral image classification, where an interaction attention module (IAM) is designed to highlight the distinguishability of HSI and dispel redundant information.
5
CCC-SSA-UNet: U-Shaped Pansharpening Network with Channel Cross-Concatenation and Spatial–Spectral Attention Mechanism for Hyperspectral Image Super-Resolution
Zhichao Liu,Guangliang Han,Peixun Liu,Dianbin Chen,Dongxu Liu,Anping Deng +5 more
TL;DR: The experiment shows that the proposed CCC-SSA-UNet exhibits state-of-the-art performance and has a shorter inference runtime and lower GPU memory consumption than most of the existing hyperspectral pansharpening methods.
4
A Discriminative Spectral-Spatial-Semantic Feature Network Based on Shuffle and Frequency Attention Mechanisms for Hyperspectral Image Classification
TL;DR: This work proposes a discriminative spectral-spatial-semantic feature network based on shuffle and frequency attention mechanisms for HSI classification that can achieve satisfactory performance and is superior to other contrasting methods.