General Information

Req #
WD00028145
Career area:
Artificial Intelligence
Country/Region:
China
State:
Beijing
City:
北京(Beijing)
Date:
Monday, April 25, 2022
Working time:
Full-time
Additional Locations: 
* 北京(Beijing) - Beijing - China

Why Work at Lenovo

Here at Lenovo, we believe in smarter technology for all, so we spend our time building a society that’s brighter and more inclusive. And we go big. No, not big—huge. 

We’re a US$60 billion revenue Fortune Global 500 company serving customers in 180 markets around the world. Focused on a bold vision to deliver smarter technology for all, we are developing world-changing technologies that power (through devices and infrastructure) and empower (through solutions, services and software) millions of customers every day and together create a more inclusive, trustworthy and sustainable digital society for everyone, everywhere. 

The one thing that’s missing? Well… you...

Description and Requirements

岗位职责
1. 计算机视觉领域人体姿态估计相关算法和模型研发,包括但不限于:单摄像机/多摄像机下的单人/多人2D/3D姿态估计,人体行为理解,基于文本/语音驱动人体姿势生成以及语音驱动人脸视频生成等前沿研究方向;
2. 面向智能教育行业的工程化落地实现,基于机器学习、CV、CG等技术实现数字人的虚拟形象和AR特效,参与人体姿态估计和数字人动作驱动算法的设计与实现,包括但不限于嘴唇运动驱动、面部表情运动驱动、身体姿势驱动等;
3.与其它高校、内部团队合作,将概念和技术转化和实现为完整的原型或产品;

岗位要求
1. 计算机视觉,图像处理,机器学习,模式识别等相关专业硕士或博士学历; 
2. 在计算机视觉、深度学习、机器学习等人工智能领域有丰富经验和突出成果,发表过计算机视觉相关领域国际顶级会议/期刊(如CVPR, ICCV, ECCV, PAMI, IJCV等)论文者优先考虑;
3. 具备扎实的姿态估计相关技术的理论基础,了解最前沿的学术界和工业界的姿态检测技术现状和发展趋势,对相关计算机视觉算法有深入理解,对主流的人体姿态估计模型如OpenPose、AlphaPose、HRNet、HMOR等有着很深入的研究;
4. 在多摄像机三维建模、多摄像机标定、虚拟数字人形象建模及动作驱动方向有丰富经验者优先;
5. 熟练掌握各种深度学习模型的训练和推理原理,熟悉深度学习模型压缩技术,如紧凑化模型,模型量化,知识蒸馏, NAS等, 有实际应用项目研发经验者优先;
6. 具备很好的数学功底,熟悉机器学习的数学推理,精通求解优化算法;
7. 具有良好的编程基础,掌握C/C++/Python等编程开发和常用数据结构、算法;并且熟练使用主流深度学习框架,如PyTorch ,TensorFlow等;
8. 具备良好的创新和合作精神,较强的进取心和流利的英语能力;

* 北京(Beijing) - Beijing - China