前言
最近进入瓶颈？
改论文，改到有些抑郁了
总是不对，总是被打回
好的写作，让人一看就清楚明白非常重要
郁闷时候看看大佬们怎么说的 沈向洋、华刚：读科研论文的三个层次、四个阶段与十个问题
十问
- What is the problem addressed in the paper? 这篇文章究竟讲了什么问题？
The answer shall address:
1) what are the input X (e.g., a single RGB image, an image sequence, or an RGBD image) 输入是什么（RGB图像还是图像序列还是RGBD图像，ps:D是图像深度，每个像素的位数，也就是色彩分辨率）
2) what are the Y (e.g., pose of the human in the image) 输出是什么（图像中人类姿势）
3) what are the constraints on X and/or Y, if any. X和Y的约束/联系是什么 - Is this a new problem? 是一个新的问题嘛？
If it is a new problem, why does it matter?如果是一个新问题，它的重要性在哪？
A new, meaningful, and yet challenging research problem needs a keen eye to spot, and if it is big/important enough, it may draw many people to work on it. So in a sense, it is a kind of highest innovation. 发现新的有意义、又挑战性的问题需要一双敏锐的眼睛，重要的问题将吸引更多的科研人去研究，这是一种最大的创新 - What is the scientific hypothesis that the paper is trying to verify? 这篇文章致力于证明什么假设？
Answer to this question is to address what new knowledge is advanced in the paper. A scientific hypothesis sounds like:“If we did abc in our algorithm/dnn architecture, 90% of case we can guarantee results cde.” A contrete example,"In ResNet, if we do the Residue block, we expect to be able to learn much deeper networks, which leads to much higher recognition accuracy."研究是从科学假设开始的，提出假说并通过实验去验证 - What are the key related works and who are the key people working on this topic? 与这篇论文十分相关的研究有哪些 ？这一领域的关键人物有那些？
It is important to indentify the most relavant work that inspired the work in this paper.Grouping them helps with a taxonomy helps you to build a systematic view about the research problem addressed. And finally, please memorize the name of the authors and affiliations of these related works, as they will be key people who will appreciate or criticize this work.了解方向的重要工作，对相关研究分类建立系统认识，记住作者以及他们关系，他们是会欣赏和批判你的工作的人。/对你工作最感兴趣的人 - What is the key of the proposed solution in the paper?这篇文章提出的问题解决方案中，核心贡献是什么？
Please summarize the key differentiation of the paper when compared with
the previous related works. 简要介绍本文和其他之前文章之间的不同之处 - How are the experiments designed? 实验是如何设计的？
Experiments design is very important. A good experiments design shall validate all claims made in the paper. Indeed, experiments should be designed around this validation. 关键是通过实验来支撑验证每个假说 - Waht datasets are build/used for the quantitative evaluation? Is the code open sourced? 实验的数据集是如何构建和使用的，代码是开源的吗？
Dataset is an important factor in scientific research. And code helps for readers to reproduce the results. 科学研究应当是可量化、可浮现的，读文章的人是否可以接触文中所用数据集？ - Is the scientific hypothesis well supported by evidence in the experiments? 实验结果是否有力地支持假设？
Are the claims in the paper well supported by the experimental result? - What are the contributions of the paper? 这篇文章的贡献是什么？
Up to this point, it should be clear if the paper made one or some solid contributions, which really refers to what knowledge is advanced. 到第九个问题，如果文中有好的贡献并且先进，这个答案非常清楚 - What should/could be done next？下一步可以做什么？
This shall summarize your understanding of the limitations of the proposed method in the paper. Addressing these limitations are naturally future research, both from the problem definition itself and/or technical improvement. Or it could be linked to some other abstract knowledge in your cognitive model and stimulate new directions to go. This final question is the creativity part. 总结你对于本文提出的方法的局限性的理解，并在未来研究解决这些局限性，或者它可以与当前的认知模型中的其他抽象指示联系起来，并激发性的方法。最后一个问题是创造力。
