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