视觉问答精华 - 专知

会员服务 ·

视觉问答

视觉问答（Visual Question Answering，VQA），是一种涉及计算机视觉和自然语言处理的学习任务。这一任务的定义如下： A VQA system takes as input an image and a free-form, open-ended, natural-language question about the image and produces a natural-language answer as the output[1]。翻译为中文：一个VQA系统以一张图片和一个关于这张图片形式自由、开放式的自然语言问题作为输入，以生成一条自然语言答案作为输出。简单来说，VQA就是给定的图片进行问答。

Avi Singh's blog
- http://avisingh599.github.io/deeplearning/visual-qa/
Visual Question Generation as Dual Task of Visual...
- https://amds123.github.io/2017/09/21/Visual-Question-Generation-as-Dual-Task-of-Visual-Question-Answering/
Visual Question Answering with Memory-Augmented...
- https://amds123.github.io/2017/07/17/Visual-Question-Answering-with-Memory-Augmented-Networks/
Speech-Based Visual Question Answering
- https://amds123.github.io/2017/09/16/Speech-Based-Visual-Question-Answering/
Visual Question Answering Demo in Python Notebook
- http://iamaaditya.github.io/2016/04/visual_question_answering_demo_notebook
The Color of the Cat is Gray: 1 Million Full-Sentences Visual...
- https://amds123.github.io/2016/09/21/The-Color-of-the-Cat-is-Gray-1-Million-Full-Sentences-Visual-Question-Answering/
zhihu.com/lives
- https://www.zhihu.com/lives
Visual Question Answering – Aaditya Prakash...
- http://iamaaditya.github.io/notes/research/vqa/
CVPR 2016 有什么值得关注的亮点？ - 知乎
- https://www.zhihu.com/question/47385572/answer/108519485
如何评价 Visual Studio Code？ - 知乎
- https://www.zhihu.com/question/29984607
将错误的版本（有大量的 commits） push 到 Git...
- https://www.zhihu.com/question/19996736/answer/30883413
Python出现ValueError: need more than 1 value to unpack...
- https://www.zhihu.com/question/19932406/answer/13391058
zhihu.com/question/36701137
- https://www.zhihu.com/question/36701137
阅读笔记（Multimodal Compact Bilinear Pooling for Visual...
- https://zhuanlan.zhihu.com/p/22704349
Visual Studio 2017 如何编译 Visual Studio 2015 的项目？ - 知乎
- https://www.zhihu.com/question/62353187/answer/199095596
Exploring Human-like Attention Supervision in Visual...
- https://amds123.github.io/2017/09/19/Exploring-Human-like-Attention-Supervision-in-Visual-Question-Answering/
Don't Just Assume; Look and Answer: Overcoming Priors for...
- https://amds123.github.io/2017/12/01/Dont-Just-Assume;-Look-and-Answer-Overcoming-Priors-for-Visual-Question-Answering/
Visual Question Answering - handong1587
- https://handong1587.github.io/deep_learning/2015/10/09/vqa.html
知乎 - 发现更大的世界
- https://www.zhihu.com/question/50282387
怎么能下载到visual modelq？ - 知乎
- https://www.zhihu.com/question/63079248

展开全文

参考链接

父主题

计算机视觉

微信扫码咨询专知VIP会员