Attention in CV
1. Attention in CV
1.1. CHAM:actionrecognition using convolutional hierarchical attention model.5
Cnn+多层LSTM,soft attention(指可导,hard attention使用强化学习,但是强化学习方差较大)
1.2. Recursiverecurrent nets with attention modeling for OCR in the wild.6
Recursive是结构上的循环(节省空间增加深度,类似与ISTN),recurrent是时间上的循环(多层使关注不同任务)。
1.3. Show,attend and tell: neural image caption generation with visual attention.7
Image caption任务。
1.4. Recurrentmodels of visual attention.8
鼻祖。
5. Yan,S., Smith, J. S., Lu, W. & Zhang, B. CHAM: action recognition usingconvolutional hierarchical attention model.ArXiv Prepr. ArXiv170503146(2017).
6. Lee,C.-Y. & Osindero, S. Recursive recurrent nets with attention modeling forOCR in the wild. inProceedings of the IEEE Conference on Computer Visionand Pattern Recognition 2231–2239 (2016).
7. Xu,K. et al. Show, Attend and Tell: Neural Image Caption Generation withVisual Attention. in14, 77–81 (2015).
8. Mnih,V., Heess, N., Graves, A. & others. Recurrent models of visual attention.inAdvances in neural information processing systems 2204–2212 (2014).