Anbang Yao got his Ph.D. degree from Tsinghua University in Jan. 2010. He is currently a Senior Staff Research Scientist at Intel Labs China where he leads the research efforts on 2D/3D scene understanding, multi-modal emotion analysis, deep neural network design and compression, etc. He has 60+ PCT/US patent applications got granted/filed, which are widely used in Intel AI related HW designs (such as Intel® Movidius™ Neural Compute Sticks and Intel® Arria® 10 SoC FPGAs) and SW applications (such as Intel® RealSense™ SDK and Intel® Distribution of OpenVINO™ Toolkit). As the first/corresponding author, he has published 20+ top-tier research papers in NeurIPS, ICLR, CVPR, ICCV, ECCV, IJCV, TIP, PR and etc. He has been recognized with numerous Awards at Intel, including 1 Intel Global Inventor (2018), 3 Intel Labs Gordy Awards (2014/2015/2016), 1 Intel Labs Top-1 Inventor of the Year (2017), 2 Intel China Awards (2016/2017), 1 Intel China Employee of the Year Award (2017) and 1 i360 Design Hero Award of Intel IOTG Asian Region (2017). He also led the team and won the Winner of the prestigious EmotiW Challenges (held by ACM ICMI) in 2015/2017, beating out 74/100+ teams.News：
- July 23rd, 2019. Three papers accepted to ICCV 2019.
- February 25th, 2019. Our DKS (Deeply-supervised Knowledge Synergy) work is accepted by CVPR 2019.
- December 20th, 2018. Delivered an invited talk at Tsinghua University.
- December 7th, 2018. Delivered an invited talk “Deep neural network compression and acceleration” at NeurIPS 2018, CDNNRIA Workshop.
- July 5th, 2018. Our SGC (Spatial Group Convolution) work is accepted as a full oral paper by ECCV 2018.
- February 22nd, 2018. Our ELQ (Explicit Loss-error-aware Quantization) work is accepted by CVPR 2018.
- July 17th, 2017. One paper accepted to ICCV 2017.
- March 18th, 2017. Three papers accepted to CVPR 2017.
- February 6th, 2017. Our INQ (Incremental Network Quantization) work is accepted by ICLR 2017.
- August 12th, 2016. Our DNS (Dynamic Network Surgery) work is accepted by NIPS 2016.
- March 1st, 2016. Our HyperNet work is accepted as a spotlight oral paper by CVPR 2016.
(* Interns mentored by me, + Corresponding author)
- HBONet: Harmonious Bottleneck on Two Orthogonal Dimensions. Duo Li*, Aojun Zhou* and Anbang Yao+. To appear in ICCV 2019.
- Learning Two-View Correspondences and Geometry Using Order-Aware Network. Jiahui Zhang*, Dawei Sun*, Zixin Luo, Anbang Yao+, Lei Zhou, Tianwei Shen, Yurong Chen, Hongen Liao and Long Quan. To appear in ICCV 2019.
- A Closed-form Solution to Universal Style Transfer. Ming Lu*, Hao Zhao*, Anbang Yao+, Yurong Chen, Feng Xu and Li Zhang. To appear in ICCV 2019.
- Deeply-Supervised Knowledge Synergy. Dawei Sun*, Anbang Yao+, Aojun Zhou* and Hao Zhao*. CVPR 2019.
- Efficient Semantic Scene Completion Network with Spatial Group Convolution. Jiahui Zhang*, Hao Zhao*, Anbang Yao+, Yurong Chen, Li Zhang and Hongen Liao. ECCV 2018, (Oral).
- Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks. Aojun Zhou*, Anbang Yao+, Kuan Wang* and Yurong Chen. CVPR 2018.
- Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights. Aojun Zhou*, Anbang Yao+, Yiwen Guo, Lin Xu and Yurong Chen. ICLR 2017.
- Decoder Network over Lightweight Reconstructed Feature for Fast Semantic Style Transfer. Ming Lu*, Hao Zhao*, Anbang Yao+, Feng Xu, Yurong Chen and Li Zhang. ICCV 2017.
- RON: Reverse Connection with Objectness Prior Networks for Object Detection. Tao Kong*, Fuchun Sun, Anbang Yao+, Huaping Liu, Ming Lu* and Yurong Chen. CVPR 2017.
- Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation. Hao Zhao*, Ming Lu*, Anbang Yao+, Yurong Chen and Li Zhang. CVPR 2017.
- Network Sketching: Exploiting Binary Structure in Deep CNNs. Yiwen Guo, Anbang Yao, Hao Zhao* and Yurong Chen. CVPR 2017.
- Learning Supervised Scoring Ensemble for Emotion Recognition in the Wild. Ping Hu, Dongqi Cai, Shandong Wang, Anbang Yao+ (project leader) and Yurong Chen. ACM ICMI 2017, (Oral, Winner of EmotiW-AFEW 2017 out of 100+ Teams).
- Dynamic Network Surgery for Efficient DNNs. Yiwen Guo*, Anbang Yao+ and Yurong Chen. NeurIPS 2016.
- HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection. Tao Kong*, Anbang Yao+, Yurong Chen and Fuchun Sun. CVPR 2016, (Spotlight).
- HoloNet: Towards Robust Emotion Recognition in the Wild. Anbang Yao+, Dongqi Cai, Ping Hu, Shandong Wang, Liang Sha and Yurong Chen. ACM ICMI 2016, (Oral, 1-st Runner-up of EmotiW-AFEW 2016 out of ~100 Teams).
2015 and before
- Capturing AU-Aware Facial Features and Their Latent Relations for Emotion Recognition in the Wild. Anbang Yao+, Junchao Shao*, Ningning Ma* and Yurong Chen. ACM ICMI 2015, (Oral, Winner of EmotiW-AFEW 2015 out of 75 Teams).
- Robust Face Representation Using Hybrid Spatial Feature Interdependence Matrix. Anbang Yao+ and Shan Yu. IEEE Trans. Image Processing, 2013.
- A Compact Association of Particle Filtering and Kernel Based Object Tracking. Anbang Yao+, Xinggang Lin, Guijin Wang and Shan Yu. Pattern Recognition, 2012.
- An Incremental Bhattacharyya Dissimilarity Measure for Particle Filtering. Anbang Yao+, Guijin Wang, Xinggang Lin and Xiujuan Chai. Pattern Recognition, 2010.
- Kernel Based Articulated Object Tracking with Scale Adaptation and Model Update. Anbang Yao+, Guijin Wang, Xinggang Lin and Hao Wang. ICASSP 2008.
- Intel Global Inventor 2018, 1 out of ~10000 Employees of Intel China
- Intel China Employee of the Year Award 2017
- Intel China Award 2017, Highest Team Award of Intel China
- Top Inventor of 2017, 1 out of over 700 Research Scientists across Intel Labs Globally
- Intel i360 Design Hero Award 2017, Highest Business Award of Intel IOTG Asian Region
- Intel China Award 2016, Highest Team Award of Intel China
- Intel Labs Academy Award 2016 (a.k.a Gordy Award,戈登·摩尔奖), Highest Annual Research Award across Intel Labs Globally
- Intel Labs Academy Award 2015 (a.k.a Gordy Award,戈登·摩尔奖), Highest Annual Research Award across Intel Labs Globally
- Intel Labs Academy Award 2014 (a.k.a Gordy Award,戈登·摩尔奖), Highest Annual Research Award across Intel Labs Globally
- Tsinghua-JiangZhen Scholarship 2009, Highest Scholarship of School of Information Science and Technology, Tsinghua University
- Tsinghua-Toshiba Scholarship 2008, First Class.
- Tsinghua-AHaiFa Scholarship 2005, First Class
Current and Past Interns
I am really fortunate to be working with these amazingly talented students
- Dawei Sun (Tsinghua University)
- Duo Li (Tsinghua University)
- Aojun Zhou(CASIA)
- Ming Lu (Tsinghua University)
- Hao Zhao (Tsinghua University)
- Jiahui Zhang (Tsinghua University)
- Kuan Wang(Tsinghua University)
- Tao Kong (Tsinghua University)
- Wenbing Huang (Tsinghua University)
- Yun Ren (Beihang University)
- Yao Cheng (Peking University)
- Peixian Hu (Tsinghua University)
- Ruoyan Wang (Dalian University of Technology)
- Yuhang Wang (CASIA)
- Yunlong Bian (Beijing University of Posts and Telecommunications)
- Ningning Ma (Tsinghua University)
- Junchao Shao (Beihang University)
- Yiwen Guo (Tsinghua University)