6 citations · 14 across the 4 of their papers we have counts for
4 papers
DualMamba: A Lightweight Spectral-Spatial Mamba-Convolution Network for Hyperspectral Image Classification
Jiamu Sheng, Jingyi Zhou, Jiong Wang +2
The effectiveness and efficiency of modeling complex spectral-spatial relations are both crucial for Hyperspectral image (HSI) classification. Most existing methods based on CNNs a…
DreamFrame: Enhancing Video Understanding via Automatically Generated QA and Style-Consistent Keyframes
Zhende Song, Chenchen Wang, Jiamu Sheng +4
Recent large vision-language models (LVLMs) for video understanding are primarily fine-tuned with various videos scraped from online platforms. Existing datasets, such as ActivityN…
Exploring Multi-Timestep Multi-Stage Diffusion Features for Hyperspectral Image Classification
Jingyi Zhou, Jiamu Sheng, Jiayuan Fan +4
The effectiveness of spectral-spatial feature learning is crucial for the hyperspectral image (HSI) classification task. Diffusion models, as a new class of groundbreaking generati…
JNDMix: JND-Based Data Augmentation for No-reference Image Quality Assessment
Jiamu Sheng, Jiayuan Fan, Peng Ye +1
Despite substantial progress in no-reference image quality assessment (NR-IQA), previous training models often suffer from over-fitting due to the limited scale of used datasets, r…