给大家推荐几个AI、CV方向优秀公众号

3 月 1 日 计算机视觉life

大家好!今天给大家推荐几个精心挑选的AI」和计算机视觉」相关方向的 公众号,看看优秀的你关注了几个?

智 车 科 技

智车科技是一个专注于自动驾驶与ADAS技术的公众号。分享的内容包括自动驾驶的视觉感知、运动决策、规划控制等知识点,以及自动驾驶汽车的产业趋势,国家政策,会议资讯,专家访谈等内容。

▲识别二维码关注

我爱计算机视觉


一个华为人的技术提升之路,关注计算机视觉、机器学习、深度学习技术的最前沿,技术方向包括:OCR、SLAM、GAN、目标检测、语义分割、姿态估计、目标跟踪、人脸识别、医学影像处理与识别、遥感与航空影像处理识别、计算机视觉竞赛等。欢迎关注!

网站主页:www.52cv.net

▲识别二维码关注


OpenCV学堂


一个致力于计算机视觉OpenCV原创技术传播的公众号!OpenCV计算机视觉与tensorflow深度学习相关算法原创文章分享、函数使用技巧、源码分析与讨论,计算机视觉前沿技术介绍,技术专家经验分享,人才交流,学习交流。是学习计算机视觉与深度学习在计算机视觉方向应用,OpenCV框架的最好平台。

▲识别二维码关注

计算机视觉战队

计算机视觉专业领域的团队,专注于机器学习、深度学习知识领域,主要在人脸检测、人脸识别,多目标检测、目标跟踪、行人检测及跟踪等研究方向。本团队想通过计算机视觉战队平台”打造属于自己的品牌,让更多相关领域的人了解本团队,加入我们一起来学习,共同进步!

▲识别二维码关注

磐 创 AI


磐创AI,聚焦传递AI行业最新动态,出品机器学习干货文章、深度学习实战项目、Tensorflow与Keras中文原创教程、国内外最新论文翻译。撰有《TensorFlow 从零开始学》一书。另外还会定期送些小福利。欢迎关注。


▲识别二维码关注

极 市 平 台

极市平台为开发者提供行业真实场景集,在线训练系统,多行业项目需求,开发者技术社区,公众号分享技术论文干货、每月业内大咖直播分享、专业技术讨论等,分享内容涉及目标检测、语义分割、人脸识别、目标跟踪、工业检测等,期待您的关注~

▲识别二维码关注

End

登录查看更多
点赞 0

Being accurate, efficient, and compact is essential to a facial landmark detector for practical use. To simultaneously consider the three concerns, this paper investigates a neat model with promising detection accuracy under wild environments e.g., unconstrained pose, expression, lighting, and occlusion conditions) and super real-time speed on a mobile device. More concretely, we customize an end-to-end single stage network associated with acceleration techniques. During the training phase, for each sample, rotation information is estimated for geometrically regularizing landmark localization, which is then NOT involved in the testing phase. A novel loss is designed to, besides considering the geometrical regularization, mitigate the issue of data imbalance by adjusting weights of samples to different states, such as large pose, extreme lighting, and occlusion, in the training set. Extensive experiments are conducted to demonstrate the efficacy of our design and reveal its superior performance over state-of-the-art alternatives on widely-adopted challenging benchmarks, i.e., 300W (including iBUG, LFPW, AFW, HELEN, and XM2VTS) and AFLW. Our model can be merely 2.1Mb of size and reach over 140 fps per face on a mobile phone (Qualcomm ARM 845 processor) with high precision, making it attractive for large-scale or real-time applications. We have made our practical system based on PFLD 0.25X model publicly available at \url{http://sites.google.com/view/xjguo/fld} for encouraging comparisons and improvements from the community.

点赞 0
阅读1+
Top