image caption（二）代码_chinese-image-captioning

Basic:

Google<tensorflow> 

https://github.com/tensorflow/models/tree/master/im2txt

 

(Paper)Show,attend and tell:Neural Image Caption Generation with Visual Attention:<(soft attention) >

https://github.com/sgrvinod/a-PyTorch-Tutorial-to-Image-Captioning <Pytorch>1.1k

https://github.com/yunjey/show-attend-and-tell<tensorflow>834

https://github.com/DeepRNN/image_captioning<tensorflow>654

 

(Paper)Self-critical sequence training for image captioning(CVPR2017) <强化学习>

https://github.com/ruotianluo/self-critical.pytorch  <pytorch>1500

 

(Paper)Attention on Attention for Image Captioning". ICCV 2019

https://github.com/husthuaan/AoANet <Pytorch> 212

 

(Paper)Knowing When to Look: Adaptive Attention via a Visual Sentinal for Image Captioning(CVPR 2017): 

自适应的attention模型，该模型能够自己决定是否关注图片以及关注哪里

https://github.com/fawazsammani/knowing-when-to-look-adaptive-attention<Pytorch>55

 

(Paper)Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering: (CVPR 2018)

联合bottom-up 和top down的注意力机制，对目标物体和图像其它显著区域施加注意力权重

https://github.com/poojahira/image-captioning-bottom-up-top-down<Pytorch>108

https://github.com/peteanderson80/bottom-up-attention  Caffe   特征 

https://github.com/peteanderson80/Up-Down-Captioner 

 

(Paper)SCA-CNN: Spatial and Channel-wise Attention in Convolution Networks for Imgae Captioning  CVPR2017

https://github.com/zjuchenlong/sca-cnn.cvpr17  <Theno Caffe>192

 

 

New:

(Paper) Meshed-Memory Transformer for Image Captioning (CVPR 2020).

https://github.com/aimagelab/meshed-memory-transformer  <Pytorch>168

 

(Paper)X-Linear Attention Networks for Image Captioning (CVPR 2020)

https://github.com/JDAI-CV/image-captioning <Pytorch> 142

 

(Paper) Adaptively Aligned Image Captioning via Adaptive Attention Time 

https://github.com/husthuaan/AAT  <Pytorch> 36

 

 

Other:

(Paper)Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions(CVPR 2019): 

引入控制信号来控制image caption的结果，针对不同区域

https://github.com/aimagelab/show-control-and-tell< Pytorch>193

 

(Paper) Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner ICCV2017

The cross-domain captioning models

https://github.com/tsenghungchen/show-adapt-and-tell<Tensorflow>144

 

(Paper)    Attend to You: Personalized Image Captioning with Context Sequence Memory Networks. CVPR, 2017

https://github.com/cesc-park/attend2u  <tensorflow>195

 

 

Eval:

https://github.com/tylin/coco-caption   (python2)687

https://github.com/wangleihitcs/CaptionMetrics   (python2 3)40

 

(Paper)Learning to Evaluate Image Captioning  CVPR2018

https://github.com/richardaecn/cvpr18-caption-eval  <Pytorch Tensorflow> 69

 

 

Chinese:

https://github.com/ruotianluo/Image_Captioning_AI_Challenger   189

https://github.com/foamliu/Image-Captioning-PyTorch   <Pytorch>78

https://github.com/cai-lw/image-captioning-chinese  <Tensorflow>30

 

 

https://github.com/zhjohnchan/awesome-image-captioning