【Bio】Senior research scientist of the naverlab
【Research】instance-level and semantic visual search, representing the structure and geometry of object categories, and in reasoning at the scene-level with images and text
【Bio】Chief Scientist at Megvii (Face++), PhD from Xian Jiaotong Univ.
【Research】computational photography, face recognition, and deep learning based image understanding.
【Bio】leader of Learning & Perception Research team at Nvidia research, PhD from MPI
【Research】from low-level vision (denoising, super-resolution, computational photography), geometric vision (structure from motion, SLAM, optical flow) to high-level vision (detection, recognition, classification), as well as fundamental machine learning algorithms
【Bio】CEO of Prnscreen.
【Research】computer graphics,dynamic shape reconstruction and non-rigid registration, PhD from ETHZ
- 2017 PR HIGH-RESOLUTION IMAGE INPAINTING USING MULTI-SCALE NEURAL PATCH SYNTHESIS
- 2017 ARXIV ON THE EFFECTS OF BATCH AND WEIGHT NORMALIZATION IN GENERATIVE ADVER-SARIAL NETWORKS
【Bio】Principal scientist of TuSimple, PhD from HKUST.
【Research】vision based perception and localization part of autonomous driving
- 2018 ECCV Data-Driven Sparse Structure Selection for Deep Neural Networks
- 2018 CVPR Multi-shot Pedestrian Re-identification via Sequential Decision Making
- 2018 AAAI DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer
- 2017 ICCV Factorized Bilinear Models for Image Recognition
- 2017 IJCAI Demystifying Neural Style Transfer
- 2017 ICRA Self-paced Cross-modality Transfer Learning for Efficient Road Segmentation
【Bio】Researcher，executive director of Tencent AI Lab
【Research】Game AI, Social AI, Content AI, Cloud AI , Compute Vision, Speech recognition, NLP, ML; Projects on machine translation, voice chat, intelligent question answering, image understanding, go game, unmanned driving etc.