K
Kai Li
Researcher at Northeastern University
Publications - 46
Citations - 6024
Kai Li is an academic researcher from Northeastern University. The author has contributed to research in topics: Line segment & Computer science. The author has an hindex of 17, co-authored 44 publications receiving 3362 citations. Previous affiliations of Kai Li include Wuhan University & NEC.
Papers
More filters
Posted Content
Image Super-Resolution Using Very Deep Residual Channel Attention Networks
TL;DR: This work proposes a residual in residual (RIR) structure to form very deep network, which consists of several residual groups with long skip connections, and proposes a channel attention mechanism to adaptively rescale channel-wise features by considering interdependencies among channels.
Book ChapterDOI
Image Super-Resolution Using Very Deep Residual Channel Attention Networks
TL;DR: Very deep residual channel attention networks (RCAN) as mentioned in this paper proposes a residual in residual (RIR) structure to form very deep network, which consists of several residual groups with long skip connections Each residual group contains some residual blocks with short skip connections.
Proceedings ArticleDOI
Visual Semantic Reasoning for Image-Text Matching
TL;DR: A simple and interpretable reasoning model to generate visual representation that captures key objects and semantic concepts of a scene that outperforms the current best method for image retrieval and caption retrieval on MS-COCO and Flickr30K datasets.
Posted Content
Residual Non-local Attention Networks for Image Restoration.
TL;DR: The proposed residual local and non-local attention learning to train the very deep network is generalized for various image restoration applications, such as image denoising, demosaicing, compression artifacts reduction, and super-resolution.
Proceedings Article
Residual Non-local Attention Networks for Image Restoration
TL;DR: Zhang et al. as discussed by the authors proposed a residual non-local attention network for high-quality image restoration, which designed a trunk branch and (non-) local mask branch in each attention block.