Visual Information Processing and Learning
Visual Information Processing and Learning


News / Events

【Conference visiting】Prof. Shiguang Shan et al. visited Inria and attended FG2019

Date of publication:2019-05-30      Number of clicks: 79

IEEE International Conference on Automatic Face and Gesture Recognition (IEEE FG) 2019 was held in Lille, France on May 14th-18th, 2019. IEEE FG is the premier forum for the presentation of new advances and research results in the fields of face and gesture recognition. Forty-two long and short oral presentations and 45 poster presentations shared their latest findings at FG2019, including researches in automated face, gesture, and body analysis, recognition, and synthesis, psychological and behavioral domains, and newest technologies and applications. Over the course of five full days, there were rich offerings of keynote sessions, workshops, tutorials, special sessions, and challenges, oral presentations, posters, and demos. Three keynote speakers presented their researches and reflected the interdisciplinary vigor of the community. Prof. Marian Bartlett, Research Scientist at Apple, presented on spontaneous facial expression recognition: insights for reinforcement learning. Hatice Gunes, Associate Professor in the Department of Computer Science and Technology, University of Cambridge, presented on creating technology with socio-emotional intelligence, and Rachael Jack, Associate Professor at the Institute of Neuroscience & Psychology, University of Glasgow presented on equipping Artificial Agents with Culturally-Sensitive Facial Expressions Using Data-Driven Methods.

Six papers from VIPL group have been accepted by FG2019, including 4 oral papers and 2 poster paper. Prof. Shiguang Shan, A/Prof. Hu Han, Dr. Jiabei Zeng, Dr Shuang Yang and Mingjie He attended FG2019.  At the conference, Prof. Shiguang Shan presented the VIPL’s last research of end-to-end learning for joint face completion and super-resolution. A/Prof. Hu Han presented the VIPL’s research on face sketch recognition via adversarial sketch-photo transformation. Dr. Shuang Yang gave the presentation of VIPL’s last research on lip reading. Mingjie He presented the VIPL’s last research on pose invariant face recognition. Dr. Jiabei Zeng gave a spotlight presentation of VIPL’s last research on video prediction. At the same time, the VIPL group has given poster presentations for all the accepted papers.

At the banquet of FG2019, the Program Chairs announced the Best Paper Award, Best Student Paper Award, Test of Time Award (Highest Impact Paper from FG 1999-2004), Best Posters Presentation Award and Best Demo Award. VIPL’s paperRobust Remote Heart Rate Estimation from Face Utilizing Spatial-temporal Attention.”(Authors: Xuesong Niu*, Xingyuan Zhao*, Hu Han, Abhijit Das, Antitza Dantcheva, Shiguang Shan and Xilin Chen) was awarded as one of the best poster presentation papers. This is the first time that the VIPL group has won the IEEE FG Best Paper/Poster Paper Award.  At the same time, another paper“FCSR-GAN: End-to-end Learning for Joint Face Completion and Super-resolution”(Authors: Jiancheng Cai, Hu Han, Shiguang Shan, and Xilin Chen) was selected as one of the IEEE FG Best Reviewed Papers, and the authors were invited to submit a journal to IEEE Trans BIOM.


Figure 1Oral presentation of Prof. Shiguang Shan;Figure 2: Oral presentation of A/Prof. Hu HanFigure 3: Oral presentation of Dr. Shuang YangFigure 4: Spotlight presentation of Dr. Jiabei ZengFigure 5: Oral presentation of Mingjie He;Figure 6: Award certificate of FG2019 Bset Poster Presentation。


Before attending FG2019, Prof. Shiguang Shan, A/Prof. Hu Han, Dr. Jiabei Zeng, Dr Shuang Yang and Mingjie He visited the French National Research Institute for the Digital Sciences, Inria in Sophia Antipolis, France on 12th-13th, May. During the visiting, Prof. Shiguang Shan introduced the researches and team members of VIPL. A/Prof. Hu Han, the head of the CAS-Inria Cooperation Project, presented the last research progress of Institute of Computing Technology. Dr. Jiabei Zeng, Dr. Shuang Yang and Mingjie He gave presentations on emotion recognition, lip reading and pose-invariant face recognition, respectively. After the visiting of Inria to ICT, both the Inria and the VIPL group will strengthen the cooperation with each other and continue to focus on the research of vision-based health monitor.


Figure 1Prof. Shiguang Shan introduced VIPL group;Figure 2: A/Prof. Hu Han introduced the research progresses of ICTFigure 3: Dr. Jiabei Zeng presented the research on emotion recognitionFigure 4: Dr. Jiabei Zeng presented the research on lip readingFigure 5: Mingjie He presented the research on face recognition;Figure 6: All the attending members.


[1] Xuesong Niu, Xingyuan Zhao, Hu Han, Abhijit Das, Antitza Dantcheva, Shiguang Shan, Xilin Chen,"Robust Remote Heart Rate Estimation from Face Utilizing Spatial-temporal Attention," 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019), pp. 1-8, Lille,  France, May 14-18, 2019. (Best Poster Presentation Award)

[2] Jiancheng Cai, Hu Han, Shiguang Shan, and Xilin Chen, "FCSR-GAN: End-to-end Learning for Joint Face Completion and Super-resolution,"  14th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019), pp. 1-8, Lille, France, May 14-18, 2019. (Oral, Best Reviewed Papers)

[3] Shikang Yu, Hu Han, Shiguang Shan, Antitza Dantcheva, and Xilin Chen, "Improving Face Sketch Recognition via Adversarial Sketch-Photo Transformation," 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019), pp. 1-8, Lille, France, May 14-18, 2019. (Oral)

[4] Ruibing Hou, Hong Chang, Bingpeng Ma and Xilin Chen, "Video Prediction with Bidirectional Constraint Network," 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019), Lille, France, May 14-18, 2019. (Poster)

[5] Shuang Yang, Yuanhang Zhang, Dalu Feng, Mingmin Yang, Chenhao Wang, Jingyun Xiao, Keyu Long, Shiguang Shan, Xilin Chen, "LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild," 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019), Lille, France, May 14-18, 2019. (Oral)

[6] Mingjie He, Jie Zhang, Shiguang Shan, Meina Kan, Xilin Chen, "Deformable Face Net: Learning Pose Invariant Feature with Pose Aware Feature Alignment for Face Recognition," 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019), Lille, France, May 14-18, 2019. (Oral)


Visual Information Processing and Learning
  • Address :No.6 Kexueyuan South Road
  • Zhongguancun,Haidian District
  • Beijing,China
  • Postcode :100190
  • Tel : (8610)62600514
  • Email:yi.cheng@vipl.ict.ac.cn
  • Valse

  • Big Lecture of DL

Copyright @ Visual Information Processing and Learning 京ICP备05002829号 京公网安备1101080060