Recommanded resources in Computer Vision and Deep Learning including advanced paper and issue-solutions in experiments.
- Vortex Pooling: Improving Context Representation in Semantic Segmentation(2018.4) [pdf]
- Pyramid Attention Network for Semantic Segmentation(2018.5) [pdf]
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention(2015) [pdf] [code_tensorflow] [code_PyTorch]
- Image Captioning with Semantic Attention(2016) [pdf] [code]
- Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering(2017) [pdf][code]
- Convolutional Image Captioning(2017) [pdf] [code]
- CNN+CNN: Convolutional Decoders for Image Captioning (2018) [pdf]
- Video-to-Video Synthesis(2018) [pdf] [code_PyTorch]
- Diverse Image-to-Image Translation via Disentangled Representations(2018.8) [pdf] [code_PyTorch] (Notes: maybe suitable for unpaired MR-CT synthesis for human body)
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention(2015) [pdf] [code_TensorFlow] [code_PyTorch]
- Image Captioning with Semantic Attention(2016) [pdf] [code]
- Attention Is All You Need(2017) [pdf] [code_PyTorch] [code_TensorFlow]
- Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering(2017) [pdf] [code]
- Attention U-Net:Learning Where to Look for the Pancreas(2018) [pdf] [code]
- Self-Attention Generative Adversarial Networks(2018.5) [pdf] [code_PyTorch] (Notes: 将自我注意机制引入到GAN的生成模型中，对于图像的纹理和几何上的联系提供全局的注意使得生成的图像更加的合理)
- Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction(2018) [pdf] [code]
- Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction(2018) [pdf] [code]