SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning.
Computer Vision and Pattern Recognition（2016）
Key words
convolutional networks,structural prediction tasks,visual captioning,question answering,visual attention models,spatial probabilities,conv-layer feature map,CNN encoding,spatial attention,attention mechanism,dynamic feature extractor,CNN features,multilayer feature maps,attentive spatial locations,attentive channels,SCA-CNN architecture,image captioning methods,convolutional neural network,image captioning datasets,channel-wise attention,contextual fixations,Flickr30K,Flickr8K,MSCOCO
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined