T
Tae-Kyun Kim
Researcher at Imperial College London
Publications - 308
Citations - 11653
Tae-Kyun Kim is an academic researcher from Imperial College London. The author has contributed to research in topics: Pose & Facial recognition system. The author has an hindex of 51, co-authored 295 publications receiving 9522 citations. Previous affiliations of Tae-Kyun Kim include KAIST & University of Cambridge.
Papers
More filters
Proceedings ArticleDOI
Sequential Graph Convolutional Network for Active Learning
TL;DR: In this article, a pool-based active learning framework constructed on a sequential graph convolutional network (GCN) is proposed, where each image feature from a pool of data represents a node in the graph and the edges encode their similarities.
Book ChapterDOI
Instance- and Category-level 6D Object Pose Estimation.
TL;DR: In this chapter, the 6D object pose estimation problem at the levels of both instances and categories is presented, discussed, and analysed by following the available literature on the topic.
Posted Content
Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Rendering
TL;DR: In this paper, a hand mesh estimator (HME) is implemented by a neural network and a differentiable renderer, supervised by 2D segmentation masks and 3D skeletons.
Posted Content
Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction
Anil Armagan,Guillermo Garcia-Hernando,Seungryul Baek,Shreyas Hampali,Mahdi Rad,Zhaohui Zhang,Shipeng Xie,Mingxiu Chen,Boshen Zhang,Fu Xiong,Yang Xiao,Zhiguo Cao,Junsong Yuan,Pengfei Ren,Weiting Huang,Haifeng Sun,Marek Hrúz,Jakub Kanis,Zdeněk Krňoul,Qingfu Wan,Shile Li,Linlin Yang,Dongheui Lee,Angela Yao,Weiguo Zhou,Sijia Mei,Yunhui Liu,Adrian Spurr,Umar Iqbal,Pavlo Molchanov,Philippe Weinzaepfel,Romain Brégier,Grégory Rogez,Vincent Lepetit,Tae-Kyun Kim +34 more
TL;DR: The recent HANDS'19 challenge as mentioned in this paper evaluated the abilities of current 3D hand pose estimators (HPEs) to interpolate and extrapolate the poses of a training set.
Posted Content
RGB-based 3D Hand Pose Estimation via Privileged Learning with Depth Images.
TL;DR: The method outperforms the state-of-the-art methods for hand pose estimation using RGB image input and uses both external large-scale depth image datasets and paired depth and RGB images as privileged information at training time.