Closed ZHUXUHAN closed 5 years ago
Hi, I'm quite new to Image Captioning and computer vision in general, as my experience is mostly in NLP. In fact, one of the reasons I started doing these tutorials in computer vision is because it's a great way to learn. My academic background is in energy/environment, and not in machine/deep learning.
As you probably know, Show, Attend, and Tell is one of the older models, but it's a great place to start learning. If you want to learn newer, better image captioning models, you should definitely check out the following papers -
I hope to do tutorials on them later.
Hi, I'm quite new to Image Captioning and computer vision in general, as my experience is mostly in NLP. In fact, one of the reasons I started doing these tutorials in computer vision is because it's a great way to learn. My academic background is in energy/environment, and not in machine/deep learning.
As you probably know, Show, Attend, and Tell is one of the older models, but it's a great place to start learning. If you want to learn newer, better image captioning models, you should definitely check out the following papers -
- Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning
- Self-critical Sequence Training for Image Captioning
- Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
I hope to do tutorials on them later.
Thank you very much for your answers and have helped me a lot.
@ZHUXUHAN if you'd like to extend your knowledge, then I have extended this implementation to implement "Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning". You can find it here
Your project is very great, I will always study your latest projects,thank you very much for your guidance.
In this field, how long have you been studying, and what publications have been published? I just started researching, can you recommend some publications ?