仅作学术交流，如有侵权，请联系删除
我其实有个不错的想法：
40篇比较新的oral paper，最好是开源的、你能看懂的、尽可能时髦的、大佬点赞的。
然后画一个40*40的矩阵，对角线上的元素不看，还剩下1560个元素。
每个元素看看A+B是不是靠谱，虽然可能99%都不靠谱。
但是还是有可能筛出来15篇左右的idea，如果考虑交换性可能只有7篇也够了。
或者你找40篇比较新的不是你发的oral paper，再找K篇自己的paper，也可以做这个事情。这样就不用排除对角元素了。
个人的publication水平还不高，不过很多其实也不是A+B产生的。
比如CNN之前的话，有一些是发数据集的
Pixel-Level Hand Detection in Ego-centric Videos
https://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Li_Pixel-Level_Hand_Detection_2013_CVPR_paper.pdf
有一些其实是一个经典pipeline里面有A+B+C很多步。
别人讨论B，C等步骤比较多，但是A步骤也很重要。想出一个A的trick最后发展出一篇文章
Face alignment by coarse-to-fine shape searching
http://openaccess.thecvf.com/content_cvpr_2015/papers/Zhu_Face_Alignment_by_2015_CVPR_paper.pdf
A+B也可以有一些跨度大的时候，也能产生一些还比较有趣的想法，并不是简简单单的incremental work。
比如把推荐系统用在分类器推荐（CNN时代之前）
Model recommendation with virtual probes for egocentric hand detection
http://openaccess.thecvf.com/content_iccv_2013/html/Li_Model_Recommendation_with_2013_ICCV_paper.html
分而治之也是常见思路，任何topic都可以加（CNN时代之前）
Unconstrained face alignment via cascaded compositional learning
http://openaccess.thecvf.com/content_cvpr_2016/html/Zhu_Unconstrained_Face_Alignment_CVPR_2016_paper.html
还有有的时候看到别人RL+tracking的文章，想到手里的聚类也可以这么做，就搞了一个A+B（不过步子扯有点大老是被拒后来就投了AAAI）
Merge or not? learning to group faces via imitation learning
https://arxiv.org/abs/1707.03986
今年还看到有人用GCN聚类所以结合GCN重新投了一篇。（还没release）
还有有时候可以做一些哲学讨论，就不是简单的A+B了
The devil of face recognition is in the noise
http://arxiv.org/abs/1807.11649
----------补充说明----------
4）做一个传统的小猫识别，还是使用YOLO3，用大量实验证明其有效性
<pre style="max-width: 100%;box-sizing: border-box !important;overflow-wrap: break-word !important;"><p style="max-width: 100%;letter-spacing: 0.544px;white-space: normal;color: rgb(0, 0, 0);font-family: -apple-system-font, system-ui, "Helvetica Neue", "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei UI", "Microsoft YaHei", Arial, sans-serif;widows: 1;line-height: 1.75em;margin-left: 0px;margin-right: 0px;padding-left: 0em;padding-right: 0em;box-sizing: border-box !important;overflow-wrap: break-word !important;"><strong style="max-width: 100%;box-sizing: border-box !important;overflow-wrap: break-word !important;"><span style="max-width: 100%;letter-spacing: 0.5px;font-size: 14px;box-sizing: border-box !important;overflow-wrap: break-word !important;"><strong style="max-width: 100%;font-size: 16px;letter-spacing: 0.544px;box-sizing: border-box !important;overflow-wrap: break-word !important;"><span style="max-width: 100%;letter-spacing: 0.5px;box-sizing: border-box !important;overflow-wrap: break-word !important;">—</span></strong>完<strong style="max-width: 100%;font-size: 16px;letter-spacing: 0.544px;box-sizing: border-box !important;overflow-wrap: break-word !important;"><span style="max-width: 100%;letter-spacing: 0.5px;font-size: 14px;box-sizing: border-box !important;overflow-wrap: break-word !important;"><strong style="max-width: 100%;font-size: 16px;letter-spacing: 0.544px;box-sizing: border-box !important;overflow-wrap: break-word !important;"><span style="max-width: 100%;letter-spacing: 0.5px;box-sizing: border-box !important;overflow-wrap: break-word !important;">—</span></strong></span></strong></span></strong></p><section style="max-width: 100%;letter-spacing: 0.544px;white-space: normal;font-family: -apple-system-font, system-ui, "Helvetica Neue", "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei UI", "Microsoft YaHei", Arial, sans-serif;widows: 1;box-sizing: border-box !important;overflow-wrap: break-word !important;padding-left: 0em;padding-right: 0em;"><section powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box !important;overflow-wrap: break-word !important;"><section style="margin-top: 15px;margin-bottom: 25px;max-width: 100%;opacity: 0.8;box-sizing: border-box !important;overflow-wrap: break-word !important;"><section style="max-width: 100%;box-sizing: border-box !important;overflow-wrap: break-word !important;"><section style="max-width: 100%;letter-spacing: 0.544px;box-sizing: border-box !important;overflow-wrap: break-word !important;"><section powered-by="xiumi.us" style="max-width: 100%;box-sizing: border-box !important;overflow-wrap: break-word !important;"><section style="margin-top: 15px;margin-bottom: 25px;max-width: 100%;opacity: 0.8;box-sizing: border-box !important;overflow-wrap: break-word !important;"><section style="max-width: 100%;box-sizing: border-box !important;overflow-wrap: break-word !important;"><p style="margin-bottom: 15px;padding-right: 0em;padding-left: 0em;max-width: 100%;color: rgb(127, 127, 127);font-size: 12px;font-family: sans-serif;line-height: 25.5938px;letter-spacing: 3px;margin-left: 0px;margin-right: 0px;box-sizing: border-box !important;overflow-wrap: break-word !important;"><span style="max-width: 100%;color: rgb(0, 0, 0);box-sizing: border-box !important;overflow-wrap: break-word !important;"><strong style="max-width: 100%;box-sizing: border-box !important;overflow-wrap: break-word !important;"><span style="max-width: 100%;font-size: 16px;font-family: 微软雅黑;caret-color: red;box-sizing: border-box !important;overflow-wrap: break-word !important;">为您推荐</span></strong></span></p><p style="margin: 5px 0px;padding-right: 0em;padding-left: 0em;max-width: 100%;min-height: 1em;font-family: sans-serif;letter-spacing: 0px;opacity: 0.8;line-height: normal;box-sizing: border-box !important;overflow-wrap: break-word !important;"><span style="max-width: 100%;color: rgb(87, 107, 149);font-size: 14px;box-sizing: border-box !important;overflow-wrap: break-word !important;">人工智能领域最具影响力的十大女科学家</span><br style="max-width: 100%;box-sizing: border-box !important;overflow-wrap: break-word !important;" /></p><p style="margin: 5px 0px;padding-right: 0em;padding-left: 0em;max-width: 100%;min-height: 1em;font-family: sans-serif;letter-spacing: 0px;opacity: 0.8;line-height: normal;box-sizing: border-box !important;overflow-wrap: break-word !important;"><span style="max-width: 100%;color: rgb(87, 107, 149);font-size: 14px;box-sizing: border-box !important;overflow-wrap: break-word !important;">MIT最新深度学习入门课，安排起来！</span></p><p style="margin: 5px 0px;padding-right: 0em;padding-left: 0em;max-width: 100%;min-height: 1em;font-family: sans-serif;letter-spacing: 0px;opacity: 0.8;line-height: normal;box-sizing: border-box !important;overflow-wrap: break-word !important;"><span style="max-width: 100%;color: rgb(87, 107, 149);font-size: 14px;box-sizing: border-box !important;overflow-wrap: break-word !important;">有了这个神器，轻松用 Python 写个 App</span></p><p style="margin: 5px 0px;padding-right: 0em;padding-left: 0em;max-width: 100%;min-height: 1em;font-family: sans-serif;letter-spacing: 0px;opacity: 0.8;line-height: normal;box-sizing: border-box !important;overflow-wrap: break-word !important;"><span style="max-width: 100%;color: rgb(87, 107, 149);font-size: 14px;box-sizing: border-box !important;overflow-wrap: break-word !important;">「最全」实至名归，NumPy 官方早有中文教程</span><br style="max-width: 100%;box-sizing: border-box !important;overflow-wrap: break-word !important;" /></p><p style="margin: 5px 0px;padding-right: 0em;padding-left: 0em;max-width: 100%;min-height: 1em;font-family: sans-serif;letter-spacing: 0px;opacity: 0.8;line-height: normal;box-sizing: border-box !important;overflow-wrap: break-word !important;">漫画版 Linux 内核的世界<br /></p></section></section></section></section></section></section></section></section>
本篇文章来源于: 深度学习这件小事
本文为原创文章，版权归知行编程网所有，欢迎分享本文，转载请保留出处！
内容反馈