Xiaobo Wang


Postdoctoral Scholar, CASIA
Previously Center for Biometrics and Security Research ( CBSR ), Institute of Automation, Chinese Academic of Sciences, Beijing, China

wangxiaobo2015cbsr@gmail.com, wangxiaobo2015@ia.ac.cn, xiaobo.wang@nlpr.ia.ac.cn


About Me


Currently I am a Postdoctoral Scholar in Institute of Automation, Chinese Academic of Sciences.
2018~2020, I was a Researcher in JD AI Research, working with Prof. Tao Mei.
Before that, I received the PhD degree in National Laboratory of Pattern Recognition of Institute of Automation, Chinese Academic of Sciences , supervised by Prof. Stan Z. Li . I received the B.S degree in Computational Mathematics , Tianjin University.

My research interest mainly lies in Face Recognition, Model Compression, Object Detection and Image Classification.

Pre-prints


  • [2021-1] Xiaobo Wang, Shuo Wang, Yanyan Liang, Liang Gu, Zhen Lei, RVFace: Reliable Vector Guided Softmax Loss for Face Recognition. Under Review. [paper] [code] [data[3hz7]] [trained models[ftw9]]

Publications


2021

  • [2021-1] Xiaobo Wang et al. Teacher Guided Neural Architecture Search for Face Recognition. Association for the Advancement of Artificial Intelligence, Online (AAAI2021). [paper] [code coming soon] [video]

2020

  • [2020-1] Xiaobo Wang, Tianyu Fu, Shengcai Liao, Shuo Wang, Zhen Lei, Tao Mei. Exclusivity-Consistency Regularized Knowledge Distillation for Face Recognition. European Conference on Computer Vision, Online (ECCV2020). [paper] [code cominig soon] [video]
  • [2020-2] Xiaobo Wang, Shuo Wang, Cheng Chi, Shifeng Zhang, Tao Mei. Loss Function Search for Face Recognition. International Conference on Machine Learning, Vienna, Austria (ICML2020). [paper] [data&code] [video]
  • [2020-3] Xiaobo Wang, Shifeng Zhang, Shuo Wang, Tianyu Fu, Tao Mei. Mis-classified Vector Guided Softmax Loss for Face Recognition. Association for the Advancement of Artificial Intelligence, New York, USA (AAAI2020, Oral). [paper] [data&code] [video]
  • [2020-4] Yinglu Liu, Hailin Shi, Hao Shen, Yue Si, Xiaobo Wang, Tao Mei. A New Dataset and Boundary-Attention Semantic Segmentation for Face Parsing. Association for the Advancement of Artificial Intelligence, New York, USA (AAAI2020). [paper]

2019

  • [2019-1] Xiaobo Wang, Shuo Wang, Jun Wang, Hailin Shi, Tao Mei. Co-Mining: Deep Face Recognition with Noisy Labels. IEEE International Conference on Computer Vision, Seoul, Korea (ICCV2019, Oral). [paper] [data&code coming soon!]
  • [2019-2] Shifeng Zhang, Xiaobo Wang, Zhen Lei, Stan Z. Li, FaceBoxes: A CPU Real-Time and Accurate Unconstrained Face Detector. Neurocomputing ( NC-19, SCI2 ). [paper]
  • [2019-3] Yinglu Liu, Hao Shen, Yue Si, Xiaobo Wang, Xiangyu Zhu, Hailin Shi, Grand Challenge of 106-Point Facial Landmark Localization. International Conference on Multimedia and Expo (ICME-19 Workshop, CCF-B). [paper] [Challenge]
  • [2019-4] Shifeng Zhang*, Rui Zhu*, Xiaobo Wang*, Hailin Shi, Tianyu Fu, Shuo Wang, Tao Mei, Stan Z. Li. Improved Selective Refinement Network for Face Detection. Technical report. (state-of-the-art performance on WIDER FACE). [paper]
  • [2019-5] Rui Zhu, Shifeng Zhang, Xiaobo Wang, Longyin Wen, Hailin Shi, Liefeng Bo, Tao Mei. ScratchDet: Training Single-Shot Object Detectors from Scratch. IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, USA. (CVPR2019 Oral). [paper] [code]
  • [2019-6] Shifeng Zhang*, Xiaobo Wang*, Ajian Liu, Chenxu Zhao, Jun Wan, Sergio Escalera, Hailin Shi, Zezheng Wang, Stan Z. Li. A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofing. IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, USA. (CVPR2019). [paper] [code]
  • [2019-7] Jinlin Wu, Shengcai Liao, Zhen Lei, Xiaobo Wang, Yang Yang, Stan Z. Li. Clustering and Dynamic Sampling Based Unsupervised Domain Adaption for Person Re-identification. IEEE International Conference on Multimedia and Expo, Shanghai, China. (ICME2019). [paper]
  • [2019-8] Xiaobo Wang, Zhen Lei, Xiaojie Guo, Changqing Zhang, Hailin Shi, Stan Z. Li, Multi-view subspace clustering with intactness-aware similarity. Pattern Recognition. (PR-19 SCI2 ). [paper] [code]

2018

  • [2018-1] Xiaobo Wang, Shifeng Zhang, Zhen Lei, Si Liu, Xiaojie Guo, Stan Z. Li, Ensemble Soft-Margin Softmax Loss for Image Classification. the 27th International Joint Conference on Artificial Intelligence, Stockholm, Sweden. (IJCAI-18, Oral, CCF-A). [paper] [code]
  • [2018-2] Xiaobo Wang, Zhen Lei, Hailin Shi, Xiaojie Guo, Xiangyu Zhu, Stan Z. Li, Co-Referenced Subspace Clustering. IEEE International Conference on Multimedia and Expo, San Diego, USA. (ICME-18/Oral, Best Student Paper Runner Up, CCF-B). [paper] [code]
  • [2018-3] Xiaobo Wang, Zhen Lei, Shengcai Liao, Xiaojie Guo, Yang Yang, Stan Z. Li, Dependence-Aware Feature Coding for Person Re-Identification. IEEE Signal Processing Letters (SPL-18 SCI3 ). [paper] [code]
  • [2018-4] Xuezhi Liang, Shengcai Liao, Xiaobo Wang, Wei Liu, Yuxuan Chen, Stan Z. Li, Deep Background Subtraction with Guided Learning. IEEE International Conference on Multimedia and Expo, San Diego, USA. (ICME-18 CCF-B). [paper]
  • [2018-5] Changqing Zhang, Ziwei Yu, Qinghua Hu*, Pengfei Zhu, Xinwang Liu, Xiaobo Wang, Latent Semantic Aware Multi-view Multi-label Classification. the 32th AAAI Conference on Artificial Intelligence, New Orleans, Louisiana (AAAI-18/Oral CCF-A). [paper]

2017

  • [2017-1] Xiaobo Wang, Xiaojie Guo, Zhen Lei, Changqing Zhang, Stan Z. Li, Exclusivity-Consistency Regularized Multi-view Subspace CLustering. IEEE Conference on Computer Vision and Pattern Recognition, Hawaii, USA (CVPR-17/Spotlight CCF-A). [paper] [code]
  • [2017-2] Liang Xuezhi, Xiaobo Wang, Zhen Lei, Shengcai Liao, Stan Z. Li, Soft-Margin Softmax for Deep Classification. IEEE International Conference on Neural Information Processing, Guangzhou, China. (ICONIP-17/Oral CCF-C). [paper]
  • [2017-3] Haibo Jin, Xiaobo Wang, Shengcai Liao, Stan Z. Li, Deep Person Re-Identification with Improved Embedding and Efficient Training. International Joint Conference on Biometrics, Denver, USA. (IJCB-17/Spotlight CCF-C). [paper]
  • [2017-4] Xiaojie Guo, Xiaobo Wang, Haibin Ling, Exclusivity Regularized Machine: A new Ensemble SVM Classifier. the 26th International Joint Conference on Artificial Intelligence, Melbourne, Australia. (IJCAI-17 CCF-A). [paper]
  • [2017-5] Hailin Shi, Xiaobo Wang, Dong Yi, Zhen Lei, Xiangyu Zhu, Stan Z. Li, Cross-Modality Face Recognition via Heterogeneous Joint Bayesian. IEEE Signal Processing Letters (SPL-17, SCI3 ). [paper]
  • [2017-6] Shifeng Zhang, Xiangyu Zhu, Zhen Lei, Hailin Shi, Xiaobo Wang, Stan Z. Li, S3FD: Single Shot Scale-invariant Face Detector. IEEE International Conference on Computer Vision, Venice, Italy. (ICCV-17, CCF-A). [paper]
  • [2017-7] Shifeng Zhang, Xiangyu Zhu, Zhen Lei, Hailin Shi, Xiaobo Wang, Stan Z. Li, Detecting Face with Densely Connected Face Proposal Network. Neurocomputing (NC-17, SCI2 ). [paper]
  • [2017-8] Shifeng Zhang, Xiangyu Zhu, Zhen Lei, Hailin Shi, Xiaobo Wang, Stan Z. Li, FaceBoxes: A CPU Real-time Face Detector with High Accuracy. International Joint Conference on Biometrics, Denver, USA. (IJCB-17/Spotlight, CCF-C). [paper] [code]
  • [2017-9] Shifeng Zhang, Xiangyu Zhu, Zhen Lei, Hailin Shi, Xiaobo Wang, Stan Z. Li, Detecting Face with Densely Connected Face Proposal Network. Chinese Conference Biometric Recognition, Shenzhen, China. (CCBR-17, Best Student Paper). [paper]

Before 2017

  • [2015-1] Xiaobo Wang, Xiaojie Guo, Stan Z. Li, Adaptively Unified Semi-Supervised Dictionary Learning with Active Points. IEEE International Conference on Computer Vision, Santiago, Chile. (ICCV-15, CCF-A). [paper] [code]
  • [2014-1] Xiaobo Wang, Xiaochun Cao, Xiaojie Guo, Zhenjie Song, Beautifying Fisheye Images using Orientation and Shape Cues. ACM Multimedia Conference, Brisbane, Australia. (ACMMM-14, CCF-A). [paper] [code]

Awards


Academic Activities


Presentation

Reviewer

Friends


Zhen Lei (CBSR), Xiaojie Guo (Tianjin University), Si Liu (IIE, CAS), Changqing Zhang (Tianjin University), Shengcai Liao (CBSR), Jun Wan (CBSR), Shifeng Zhang (CBSR),