Dr. Juil Sock, who holds both a Master's and a Ph.D. in Electrical Engineering from Imperial College London, UK, currently serves as the Lead Data Scientist within the AI Research division at BBC R&D. His research is primarily focused on AI Safety and the enhancement of visual data. Dr. Sock has an extensive publication history, including journal articles, conference papers, patents, and book chapters. Additionally, he has taken a leading role in organizing multiple workshops at Computer Vision conferences. Before joining BBC R&D, Dr. Sock contributed his expertise as a researcher at the Agency for Defense
Development(ADD) in South Korea, where he specialised in the development of autonomous surveillance vehicles. He also worked as a research engineer at a London-based startup that focused on 3D vision technology.
News
-
January 2024 - A journal paper accepted at IEEE Transactions on Circuits and Systems for Video Technology
-
May 2021 - PhD Thesis has been approved and the degree will be awarded in June 2021!
-
October 2020 - One paper accepted at International Conference on 3D Vision (3DV'20) as Oral.
-
July 2020 - One paper accepted at International Conference on Intelligent Robots and Systems (IROS'20)
-
December 2019 - I have co-authored a book chapter in "RGB-D Image Analysis and Processing"
-
October 2019 - I am co-organizing 5th International Workshop on Recovering 6D Object Pose at ICCV'19
-
July 2018 - One paper accepted at British Machine Vision Conference(BMVC'18)
-
December 2017 - One paper accepted for an oral presentation at Association for the Advancement of Artificial Intelligence(AAAI'18)
-
October 2017 - I will be a co-organiser of the 3rd International Workshop on Recovering 6D Object Pose at ICCV'17
-
September 2017 - One paper accepted for an oral presentation at the 3rd International Workshop on Recovering 6D Object Pose at ICCV'17
-
September 2017 - Student volunteer at BMVC 2017
-
July 2017 - One paper accepted to ICCV 2017
-
October 2016 - Started PhD. program at Imperial College
-
June 2016 - A journal paper published to Sensors
-
March 2016 - One paper accepted to ICRA 2016
Publications
-
J. Sock, G. Garcia-Hernando, A. Armagan, T-K. Kim, Introducing Pose Consistency and Warp-Alignment for Self-Supervised 6D Object Pose Estimation in Color Images, International Conference on 3D Vision (3DV), Fukuoka, Japan, Oct 2020, Oral [PDF]
-
J. Sock, G. Garcia-Hernando, T-K. Kim, Active 6D Multi-Object Pose Estimation in Cluttered Scenarios with Deep Reinforcement Learning, Proc. of International Conference on Intelligent Robots and Systems (IROS), Las Vegas, USA, Oct 2020 [PDF]
-
C. Sahin, G. Garcia-Hernando, J. Sock, T-K. Kim, Instance- and Category-level 6D Object Pose Estimation, book chapter in RGB-D Image Analysis and Processing, Springer, 2019
-
J. Sock, K.I. Kim, C. Sahin, T-K. Kim, Multi-Task Deep Networks for Depth-Based 6D Object Pose and Joint Registration in Crowd Scenarios, Proc. of British Machine Vision Conference (BMVC), Newcastle upon Tyne, UK, Sep 2018 [PDF]
-
Hamidreza Kasaei, Juil Sock, Luis Seabra Lopes, Ana Maria Tome, T-K Kim, Perceiving, Learning, and Recognizing 3D Objects : An Approach to Cognitive Service Robots, Proc. of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), New Orleans, USA, Feb 2018 [PDF]
-
Juil Sock, S.Hamidreza Kasaei, Luis Seabra Lopes, T-K Kim, Multi-view 6D Object Pose Estimation and Camera Motion Planning using RGBD Images, Proc. of Internation Conference on Computer Vision Workshop (ICCVW), Venice, Italy, Oct 2017 [PDF]
-
Vassileios Balntas, Andreas Doumanoglou, Caner Sahin, Juil Sock, Rigas Kouskouridas, T-K Kim, Pose Guided RGBD Feature Learning for 3D Object Pose Estimation, Proc. of International Conference on Computer Vision (ICCV), Venice, Italy, Oct 2017 [PDF]
-
Juil Sock, Jun Kim, Jihong Min, Kiho Kwak, Probabilistic traversability map generation using 3D-LIDAR and camera, Proc. of International Conference on Robotics and Automation (ICRA), Stockholm, Sweden, May 2016 [Link]
-
Sungdae Sim, Juil Sock, Kiho Kwak, Indirect Correspondence-Based Robust Extrinsic Calibration of LiDAR and Camera. IEEE Sensors Journal, 2016 [PDF]