S
Sanghyun Woo
Researcher at KAIST
Publications - 56
Citations - 12917
Sanghyun Woo is an academic researcher from KAIST. The author has contributed to research in topics: Computer science & Inpainting. The author has an hindex of 14, co-authored 43 publications receiving 4809 citations.
Papers
More filters
Posted Content
CBAM: Convolutional Block Attention Module
TL;DR: The proposed Convolutional Block Attention Module (CBAM), a simple yet effective attention module for feed-forward convolutional neural networks, can be integrated into any CNN architectures seamlessly with negligible overheads and is end-to-end trainable along with base CNNs.
Book ChapterDOI
CBAM: Convolutional Block Attention Module
TL;DR: Convolutional Block Attention Module (CBAM) as discussed by the authors is a simple yet effective attention module for feed-forward convolutional neural networks, given an intermediate feature map, the module sequentially infers attention maps along two separate dimensions, channel and spatial, then the attention maps are multiplied to the input feature map for adaptive feature refinement.
Proceedings Article
BAM: Bottleneck Attention Module
TL;DR: Bottleneck Attention Module (BAM) as discussed by the authors infers an attention map along two separate pathways, channel and spatial, and constructs a hierarchical attention at bottlenecks with a number of parameters and it is trainable in an end-to-end manner jointly with any feed-forward models.
Posted Content
BAM: Bottleneck Attention Module.
TL;DR: Bottleneck Attention Module (BAM) as discussed by the authors infers an attention map along two separate pathways, channel and spatial, and constructs a hierarchical attention at bottlenecks with a number of parameters and it is trainable in an end-to-end manner jointly with any feed-forward models.
Proceedings ArticleDOI
Deep Video Inpainting
TL;DR: This work proposes a novel deep network architecture for fast video inpainting built upon an image-based encoder-decoder model that is designed to collect and refine information from neighbor frames and synthesize still-unknown regions.