Transfer Learning via Unsupervised Task Discovery for Visual Question Answering论文解读
这篇文章虽然也是VQA的，但和之前看的类型完全不一样，文章研究的问题也几乎没有被探索过，所以还是有很多地方看不太明白，在这里仅发表自己的看法，若有不对的地方，还望多多指教！ 引入 人类看到和理解的视觉场景是基于不同视觉概念。例如，从一张椅子的单一图像中，人类毫不费力地识别出不同的视觉概念，如它的颜色、材料等。 风格、用途等。这种不同的视觉概念可能与自然语言中定义每个视觉概念的识别任务的不同问题有关
相关文章
- 1. 粗读CVPR2019 论文 Transfer Learning via Unsupervised Task Discovery for Visual Question Answering
- 2. Learning Conditioned Graph Structures for Interpretable Visual Question Answering论文解读
- 3. 论文解读：Hierarchical Question-Image Co-Attention for Visual Question Answering
- 4. 论文笔记：Visual Question Answering as a Meta Learning Task
- 5. 论文解读：From Pixels to Objects: Cubic Visual Attention for Visual Question Answering
- 6. 论文阅读:Unsupervised Deep Learning by Neighbourhood Discovery
- 7. Learning to Paraphrase for Question Answering 论文笔记
- 8. 论文阅读：FVQA: Fact-based Visual Question Answering
- 9. nips 208 visual question answering 导读
- 10. 《Visual Question Generation as Dual Task of Visual Question Answering》阅读笔记
- 更多相关文章...
- • C# 文本文件的读写 - C#教程
- • ASP Transfer 方法 - ASP 教程
- • JDK13 GA发布：5大特性解读
- • Scala 中文乱码解决
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 粗读CVPR2019 论文 Transfer Learning via Unsupervised Task Discovery for Visual Question Answering
- 2. Learning Conditioned Graph Structures for Interpretable Visual Question Answering论文解读
- 3. 论文解读：Hierarchical Question-Image Co-Attention for Visual Question Answering
- 4. 论文笔记：Visual Question Answering as a Meta Learning Task
- 5. 论文解读：From Pixels to Objects: Cubic Visual Attention for Visual Question Answering
- 6. 论文阅读:Unsupervised Deep Learning by Neighbourhood Discovery
- 7. Learning to Paraphrase for Question Answering 论文笔记
- 8. 论文阅读：FVQA: Fact-based Visual Question Answering
- 9. nips 208 visual question answering 导读
- 10. 《Visual Question Generation as Dual Task of Visual Question Answering》阅读笔记