Yongqin Xian is currently a Postdoc at the Max Planck Institute for Informatics. He received his master degree in computer science with honors at Saarland University, Germany and bachelor degree in computer science at Beijing Institute of Technology, China. He was a research intern at Facebook AI with Lorenzo Torresani.
Zero-shot Learning - A Comprehensive Evaluation of the Good, the Bad and the Ugly Yongqin Xian, Christoph H. Lampert, Bernt Schiele and Zeynep Akata IEEE TPAMI link: https://arxiv.org/pdf/1703.04394.pdf
Latent Embeddings for Zero-shot Classification Yongqin Xian , Zeynep Akata , Gaurav Sharma,Quynh Nguyen, Matthias Hein and Bernt Schiele IEEE CVPR 2016 link: https://arxiv.org/pdf/1603.08895.pdf
Zero-shot learning - The Good, the Bad and the Ugly Yongqin Xian, Bernt Schiele, and Zeynep Akata. IEEE CVPR 2017 link: https://arxiv.org/pdf/1707.00600.pdf
Feature Generating Networks for Zero-Shot Learning. Yongqin Xian, Tobias Lorenz, Bernt Schiele, and Zeynep Akata. IEEE CVPR 2018 link: https://arxiv.org/pdf/1712.00981v2.pdf
f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning Yongqin Xian, Saurabh Sharma, Bernt Schiele, and Zeynep Akata. IEEE CVPR 2019 link: https://arxiv.org/pdf/1903.10132.pdf
SPNet: Semantic Projection Network for Zero- and Few-Label Semantic Segmentation Yongqin Xian*, Subhabrata Choudhury*, Yang He, Bernt Schiele, and Zeynep Akata. (*indicate equal contribution) IEEE CVPR 2019 link: https://pdfs.semanticscholar.org/ea8d/6c2de162e0f9ad89af7b950333cb29e94622.pdf
Yongqin Xian is mainly interested in solving computer vision tasks with limited supervision. For instance, zero-shot learning that learns to recognize unseen classes without any labeled data and few-shot learning that learns to recognize novel classes with only few labeled data. Besides, he is also interested in related topics on semi-supervised, unsupervised learning and self-supervised learning.