Biography

I received my PhD degree from Institute of Computing Technology, Chinese Academy of Sciences in 2017, under the supervision of Prof. Shiguang Shan. I'm now an algorithm engineer at Alibaba Group. Before joining Alibaba, I was a researcher at Hulu.

Research Interest

Computer Vision, Deep Learning, Multimedia

Education Experience

2012.09-2017.06    PhD, Institute of Computing Technology, Chinese Academy of Sciences

2008.09-2012.06   BE, Computer School, Wuhan University

Research Experience

2018.06-current Senior Algorithm Engineer, R&D on multimodal video analysis and knowledge graph. Alibaba Group, Beijing, China.

2017.01-2018.06 Researcher, R&D on content-based multimedia video analysis. Hulu Research, Beijing, China.

2015.03-2016.02 Research Scholar, R&D on multimedia event detection and retrieval (supervised by Prof. Alexander Hauptmann), Language Technologies Institute, Carnegie Mellon University, U.S.A.

2014.07-2014.09 Research Scholar, R&D on human behavior recognition (supervised by Prof. Guoying Zhao and Prof. Matti Pietikainen), Center for Machine Vision Research, University of Oulu, Finland.

2012.09-2017.06 PhD, R&D on computer vision and pattern recognition (supervised by Prof. Shiguang Shan), Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China.

Honors & Awards

2016.01   Winner Award in Alibaba Large-Scale Image Search Challenge (rank: 1/860+) 

2015.12   Winner Award in ICCV ChaLearn LaP Challenge (Cultural Event Recognition) 2015 (rank: 1/100+)

2015.06   Travel Grant in IEEE CVPR WiCV Workshop 2015

2014.11   Winner Award in ACM Emotion Recognition in the Wild Challenge 2014 (rank: 1/50+)

2013.12   Second Runner-up Award in ACM Emotion Recognition in the Wild Challenge 2013 (rank: 3/40+)

2013.04   Travel Grant in IEEE FG Doctoral Consortium 2013

2011.09   Google Excellence Scholarship 2011

Research Papers (since 2012)

Journal papers:

[18] Mengyi Liu, Shuhui Wang, Yulan Guo, Yuan He, and Hui Xue. Pano-SfMLearner: Self-supervised Multi-task Learning of Depth and Semantics in Panoramic Videos. IEEE Signal Processing Letter (SPL), 2021.

[17] Hong-Xiang Chen, Kunhong Li, Zhiheng Fu, Mengyi Liu, Zonghao Chen, Yulan Guo. Distortion-aware Monocular Depth Estimation for Omnidirectional Images. IEEE Signal Processing Letter (SPL), 2021.

[16] Mengyi Liu, Shiguang Shan, Ruiping Wang, Xilin Chen. Learning Expressionlets via Universal Manifold Model for Dynamic Facial Expression Recognition. IEEE Transactions on Image Processing (IEEE T IP), 2016.

[15] Mengyi Liu, Ruiping Wang, Shiguang Shan, Xilin Chen. Learning Prototypes and Similes on Grassmann Manifold for Spontaneous Expression Recognition. Special Issue on Spontaneous Facial Behavior Analysis of Computer Vision and Image Understanding (CVIU), 2016. 

[14] Mengyi Liu, Ruiping Wang, Shaoxin Li, Zhiwu Huang, Shiguang Shan, Xilin Chen. Video Modeling and Learning on Riemannian Manifold for Emotion Recognition in the Wild.  Journal on Multimodal User Interfaces (JMUI), 2015.

[13] Mengyi Liu, Shaoxin Li, Shiguang Shan, Xilin Chen. AU-inspired Deep Networks for Facial Expression Feature Learning. Neurocomputing, 2015.

Conference papers:

[12] Mengyi Liu, Zhu Liu. Deep Reinforcement Learning Visual-Text Attention for Multimodal Video Classification. International Workshop on Multimodal Understanding and Learning for Embodied Applications in ACM Multimedia (MM) 2019. (Oral) 

[11] Mengyi Liu, Xiaohui Xie, Hanning Zhou. Content-based Video Relevance Prediction Challenge: Data, Protocol, and Baseline. arXiv 2018. (ACM Multimedia (MM) 2018 CBVRP Grand Challenge Benchmark) 

[10] Lingxun Meng, Yan Li, Mengyi Liu, Peng Shu. Skipping word: A character-sequential representation based framework for question answering. ACM International on Conference on Information and Knowledge Management (CIKM), 2016.

[9] Mengyi Liu*, Xin Liu*, Yan Li, Xilin Chen, Alexander Hauptmann, Shiguang Shan. Exploiting Feature Hierarchies with Convolutional Neural Networks for Cultural Event Recognition. International Conference on Computer Vision ChaLearn LaP Workshop (ICCVW), 2015. (ICCV ChaLearn LaP Challenge Winner Award)

[8]  Mengyi Liu, Ruiping Wang, Shaoxin Li, Shiguang Shan, Zhiwu Huang, Xilin Chen. Combining Multiple Kernel Methods on Riemannian Manifold for Emotion Recognition in the Wild. ACM International Conference on Multimodal Interaction (ACM ICMI), 2014. (ACM EmotiW Challenge Winner Award)

[7]  Mengyi Liu, Shaoxin Li, Shiguang Shan, Ruiping Wang, Xilin Chen. Deeply Learning Deformable Facial Action Parts Model for Dynamic Expression Analysis. Asian Conference on Computer Vision (ACCV), 2014.

[6]  Mengyi Liu, Shiguang Shan, Ruiping Wang, Xilin Chen. Learning Expressionlets on Spatio-Temporal Manifold for Dynamic Facial Expression Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2014.

[5] Mengyi Liu, Ruiping Wang, Zhiwu Huang, Shiguang Shan, Xilin Chen. Partial Least Squares Regression on Grassmannian Manifold for Emotion Recognition. ACM International Conference on Multimodal Interaction (ACM ICMI), 2013. (ACM EmotiW Challenge Second Runner-Up Award)

[4] Mengyi Liu, Shaoxin Li, Shiguang Shan, Xilin Chen. AU-aware Deep Networks for Expression Recognition. IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2013 .

[3] Mengyi Liu, Shaoxin Li, Shiguang Shan, Xilin Chen. Enhancing Expression Recognition in the Wild with Unlabeled Reference Data. Asian Conference on Computer Vision (ACCV), 2012.

Pre-print papers:

[2] Mengyi Liu, Lu Jiang, Shiguang Shan, Alexander Hauptmann. Self-paced Learning for Weakly Supervised Evidence Discovery in Multimedia Event Search. arXiv 2016.

[1] Mengyi Liu, Ruiping Wang, Shiguang Shan, Xilin Chen. Learning mid-level words on Riemannian manifold for action recognition. arXiv 2015.