Yaoyao Liu (PhD Student)

Yaoyao Liu

Adresse
Max-Planck-Institut für Informatik
Saarland Informatics Campus
Campus E1 4
66123 Saarbrücken
Standort
E1 4 - 624
Telefon
+49 681 9325 2024
Fax
+49 681 9325 2099

Personal Information

Research Interests

Computer Vision: image recognition, image generation, video captioning

Machine Learning: meta-learning, incremental learning, transfer learning

News

[Feb 2020] Our paper about incremental learning is accepted to CVPR 2020.

[Feb 2020] We will host the ACM Multimedia Asia 2020 conference in Singapore!

[Sep 2019] Our paper about few-shot learning is accepted to NeurIPS 2019.

[Mar 2019] Our paper about few-shot learning is accepted to CVPR 2019.

Publications

Mnemonics Training: Multi-Class Incremental Learning without Forgetting
Yaoyao LiuYuting SuAn-An LiuBernt SchieleQianru Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
[PDF] [Code] [ProjectOral Presentation

 

Learning to Self-Train for Semi-Supervised Few-Shot Classification
Xinzhe Li, Qianru SunYaoyao LiuShibao Zheng, Qin Zhou, Tat-Seng ChuaBernt Schiele
Thirty-third Conference on Neural Information Processing Systems (NeurIPS), 2019.
[PDF] [Code] [Poster]

 

Meta-Transfer Learning for Few-Shot Learning
Qianru Sun*, Yaoyao Liu*Tat-Seng ChuaBernt Schiele
(*=Equal contribution)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[PDF] [Code] [Project] [Poster]

 

An Ensemble of Epoch-Wise Empirical Bayes for Few-Shot Learning
Yaoyao LiuBernt SchieleQianru Sun
Under review. [PDF] [Code] [Project]

 

Meta-Transfer Learning through Hard Tasks
Qianru Sun*, Yaoyao Liu*Zhaozheng ChenTat-Seng ChuaBernt Schiele
(*=Equal contribution)
Under review. [PDF]

 

Generating Face Images with Attributes for Free
Yaoyao LiuXiangnan HeAn-An LiuYuting SuTat-Seng ChuaQianru Sun
Under review.

 

NUS-TJU @ The 2nd MSR Video to Language Challenge
An-An LiuNing Xu, Yurui Qiu, Xinhui Li, Mengjie Li, Yaoyao LiuYongkang WongWeizhi NieYuting SuMohan S. Kankanhalli
Technical Report for ACM MM 2017 Challenge. [PDF] [Link]

Selected Talks

Learning to Self-Train for Semi-Supervised Few-Shot Classification
NeurIPS Official Meetups
Beijing, China, December 2019 [Slides]

 

Multi-Class Incremental Learning
School of Computer Science and Engineering, Nanyang Technological University
Singapore, July 2019 [Slides]

 

Meta-Transfer Learning for Few-Shot Learning
School of Computing, National University of Singapore
Singapore, April 2019 [Slides]

Services