A paper of UNIST Vision & Learning Lab (UVLL) is accepted to IEEE International Conference on Computer Vision (ICCV) 2021, which is one of top conferences in computer vision field. We present a new algorithm that accurately estimates interacting hand poses in such a challenging scenario....
“Meta-Learning Sparse Implicit Neural Representations” by {Jaeho Lee*, Jihoon Tack*}, Namhoon Lee, Jinwoo Shin Abstract: Implicit neural representations are a promising new avenue of representing general signals by learning a continuous function that, parameterized as a neural network, maps the domain of a signal to its...
Visual Information Processing (VIP) lab’s paper has been presented at International Conference on Computer Vision (ICCV) 2021, one of the top conferences in computer vision. Person search suffers from the conflicting objectives of commonness and uniqueness between the two sub-tasks of person detection and re-identification that...
Statistical Decision Making (SDM) lab’s paper is accepted to 35th Conference on Neural Information Processing Systems (NeurIPS) 2021, one of the top-3 conferences for artificial intelligence and machine learning. A challenging aspect of the bandit problem is that a stochastic reward is observed only for the...
Learning Intelligent Machine (LIM) lab’s paper is accepted to 35th Conference on Neural Information Processing Systems (NeurIPS) 2021, one of the top-3 conferences for artificial intelligence and machine learning. Bootstrapping has been a primary tool for ensemble and uncertainty quantification in machine learning and statistics. However, due...
Published in: IEEE Transactions on Pattern Analysis and Machine Intelligence ( Early Access ) Date of Publication: 31 May 2021 ISSN Information: Print ISSN: 0162-8828 / CD: 2160-9292 / Electronic ISSN: 1939-3539 Abstract: Taking selfies has become one of the major photographic trends of our time. In this study, we focus on the selfie stick, on which a...
저 자 Jaesung Choe, Kyungdon Joo, Imtiaz Tooba, In So Kweon 학 회 IEEE Robotics and Automation Letters (RA-L) 논문일시(Year) 2021 논문일시(Month) 06 Abstract Stereo-LiDAR fusion is a promising task in that we can utilize two different types of 3D perceptions for practical usage -- dense 3D information (stereo cameras) and highly-accurate sparse point...
저 자 {Jaesung Choe, Kyungdon Joo}*, Francois Rameau, and In So Kweon 학 회 IEEE International Conference on Robotics and Automation (ICRA) 논문일시(Year) 2021 논문일시(Month) 06 Abstract This paper presents a stereo object matching method that exploits both 2D contextual information from images as well as 3D object-level information. Unlike existing stereo matching methods that...
ST-GRAT: A Novel Spatio-temporal Graph Attention Networks for Accurately Forecasting Dynamically Changing Road Speed Authors: Cheonbok Park, Cheonbok Park , Chunggi Lee , Hyojin Bahng, Hyojin Bahng , Yunwon Tae, Yunwon Tae , Seungmin Jin, Seungmin Jin , Kihwan Kim, Kihwan Kim , Sungahn Ko,...
SparTANN: sparse training accelerator for neural networks with threshold-based sparsification Authors: Hyeonuk Sim , Hyeonuk Sim , Jooyeon Cho, Jooyeon Choi , Jong-Eun Lee, Jongeun Lee Authors Info & Affiliations Publication:ISLPED '20: Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and DesignAugust 2020 Pages...
