- Yandong Guo, XPeng Motors
- Lei Zhang, Microsoft AI & Research
- Cheng Lu, XPeng Motors
- Additional lecturers: Tony Zhang, Tianpeng Feng
The recent advanced research in face recognition has boosted enormous industry applications, including biometric authentication, image search, surveillance, human-computer interaction, multimedia management, etc. Though the performance of face recognition on many public benchmarks is getting saturated, we have attempted to distill the research challenges and opportunities from the industry applications. We believe many subtopics in face recognition are still in their infancy and are excited to share them.
As a start of this tutorial, we will review the research interests and milestone works of face recognition in different periods, including the traditional solutions (e.g. handcrafted features), state of the art methods (e.g. deep learning) and present the future research directions in this field. More importantly, from the advances of face recognition in academia, the tutorial will focus more on the industrial progressions and the open questions of face recognition in industry.
Especially, we will introduce the following special topics.
- Modern face recognition pipeline
- Build cutting-edge face recognition engine using public datasets
- Make your face recognition practical: bias in face recognition & class-skewed/noisy data
- Make your face recognition practical: face recognition on the edge
- Make your face recognition practical: Imaging system for face recognition