Tae-Kyun Kim

is this you? claim profile

∙ 0 followers
Imperial College London

Associate Professor (Senior Lecturer) and the leader of Computer Vision and Learning Lab at Imperial College London

Active Learning for Bayesian 3D Hand Pose Estimation

We propose a Bayesian approximation to a deep learning architecture for ...
10/01/2020 ∙ by Razvan Caramalau, et al. ∙ 59 ∙ share

read it
3D Dense Geometry-Guided Facial Expression Synthesis by Adversarial Learning

Manipulating facial expressions is a challenging task due to fine-graine...
09/30/2020 ∙ by Rumeysa Bodur, et al. ∙ 1 ∙ share

read it
Physics-Based Dexterous Manipulations with Estimated Hand Poses and Residual Reinforcement Learning

Dexterous manipulation of objects in virtual environments with our bare ...
08/07/2020 ∙ by Guillermo Garcia-Hernando, et al. ∙ 2 ∙ share

read it
Sequential Graph Convolutional Network for Active Learning

We propose a novel generic sequential Graph Convolution Network (GCN) tr...
06/18/2020 ∙ by Razvan Caramalau, et al. ∙ 26 ∙ share

read it
MatchGAN: A Self-Supervised Semi-Supervised Conditional Generative Adversarial Network

We propose a novel self-supervised semi-supervised learning approach for...
06/11/2020 ∙ by Jiaze Sun, et al. ∙ 17 ∙ share

read it
Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction

In this work, we study how well different type of approaches generalise ...
03/30/2020 ∙ by Anil Armagan, et al. ∙ 1 ∙ share

read it
Tackling Two Challenges of 6D Object Pose Estimation: Lack of Real Annotated RGB Images and Scalability to Number of Objects

State-of-the-art methods for 6D object pose estimation typically train a...
03/27/2020 ∙ by Juil Sock, et al. ∙ 0 ∙ share

read it
Additive Angular Margin for Few Shot Learning to Classify Clinical Endoscopy Images

Endoscopy is a widely used imaging modality to diagnose and treat diseas...
03/23/2020 ∙ by Sharib Ali, et al. ∙ 2 ∙ share

read it
EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learning

Event cameras sense intensity changes and have many advantages over conv...
03/17/2020 ∙ by Lin Wang, et al. ∙ 11 ∙ share

read it
Inducing Optimal Attribute Representations for Conditional GANs

Conditional GANs are widely used in translating an image from one catego...
03/13/2020 ∙ by Binod Bhattarai, et al. ∙ 6 ∙ share

read it
A Review on Object Pose Recovery: from 3D Bounding Box Detectors to Full 6D Pose Estimators

Object pose recovery has gained increasing attention in the computer vis...
01/28/2020 ∙ by Caner Sahin, et al. ∙ 18 ∙ share

read it
Accurate 6D Object Pose Estimation by Pose Conditioned Mesh Reconstruction

Current 6D object pose methods consist of deep CNN models fully optimize...
10/23/2019 ∙ by Pedro Castro, et al. ∙ 13 ∙ share

read it
Active 6D Multi-Object Pose Estimation in Cluttered Scenarios with Deep Reinforcement Learning

In this work, we explore how a strategic selection of camera movements c...
10/19/2019 ∙ by Juil Sock, et al. ∙ 25 ∙ share

read it
Sampling Strategies for GAN Synthetic Data

Generative Adversarial Networks (GANs) have been used widely to generate...
09/10/2019 ∙ by Binod Bhattarai, et al. ∙ 9 ∙ share

read it
Real-time Background-aware 3D Textureless Object Pose Estimation

In this work, we present a modified fuzzy decision forest for real-time ...
07/22/2019 ∙ by Mang Shao, et al. ∙ 5 ∙ share

read it
AugLabel: Exploiting Word Representations to Augment Labels for Face Attribute Classification

Augmenting data in image space (eg. flipping, cropping etc) and activati...
07/15/2019 ∙ by Binod Bhattarai, et al. ∙ 1 ∙ share

read it
Rethink Global Reward Game and Credit Assignment in Multi-agent Reinforcement Learning

Cooperative game is a critical research area in multi-agent reinforcemen...
07/11/2019 ∙ by Jianhong Wang, et al. ∙ 1 ∙ share

read it
Shapley Q-value: A Local Reward Approach to Solve Global Reward Games

Cooperative game is a critical research area in multi-agent reinforcemen...
07/11/2019 ∙ by Jianhong Wang, et al. ∙ 0 ∙ share

read it
Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Rendering

Estimating 3D hand meshes from single RGB images is challenging, due to ...
04/08/2019 ∙ by Seungryul Baek, et al. ∙ 6 ∙ share

read it
Instance- and Category-level 6D Object Pose Estimation

6D object pose estimation is an important task that determines the 3D po...
03/11/2019 ∙ by Caner Sahin, et al. ∙ 2 ∙ share

read it
RGB-based 3D Hand Pose Estimation via Privileged Learning with Depth Images

This paper proposes a method for hand pose estimation from RGB images th...
11/18/2018 ∙ by Shanxin Yuan, et al. ∙ 0 ∙ share

read it
HANDS18: Methods, Techniques and Applications for Hand Observation

This report outlines the proceedings of the Fourth International Worksho...
10/25/2018 ∙ by Iason Oikonomidis, et al. ∙ 0 ∙ share

read it
A Summary of the 4th International Workshop on Recovering 6D Object Pose

This document summarizes the 4th International Workshop on Recovering 6D...
10/09/2018 ∙ by Tomas Hodan, et al. ∙ 12 ∙ share

read it
Task-Oriented Hand Motion Retargeting for Dexterous Manipulation Imitation

Human hand actions are quite complex, especially when they involve objec...
10/03/2018 ∙ by Dafni Antotsiou, et al. ∙ 6 ∙ share

read it
BOP: Benchmark for 6D Object Pose Estimation

We propose a benchmark for 6D pose estimation of a rigid object from a s...
08/24/2018 ∙ by Tomas Hodan, et al. ∙ 0 ∙ share

read it
Category-level 6D Object Pose Recovery in Depth Images

Intra-class variations, distribution shifts among source and target doma...
08/01/2018 ∙ by Caner Sahin, et al. ∙ 2 ∙ share

read it
Multi-Task Deep Networks for Depth-Based 6D Object Pose and Joint Registration in Crowd Scenarios

In bin-picking scenarios, multiple instances of an object of interest ar...
06/11/2018 ∙ by Juil Sock, et al. ∙ 0 ∙ share

read it
Augmented Skeleton Space Transfer for Depth-based Hand Pose Estimation

Crucial to the success of training a depth-based 3D hand pose estimator ...
05/11/2018 ∙ by Seungryul Baek, et al. ∙ 0 ∙ share

read it
Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model

We propose a novel end-to-end semi-supervised adversarial framework to g...
04/10/2018 ∙ by Baris Gecer, et al. ∙ 0 ∙ share

read it
3D Hand Pose Estimation: From Current Achievements to Future Goals

In this paper, we strive to answer two questions: What is the current st...
12/11/2017 ∙ by Shanxin Yuan, et al. ∙ 0 ∙ share

read it
Occlusion-aware Hand Pose Estimation Using Hierarchical Mixture Density Network

Hand pose estimation is to predict the pose parameters representing a 3D...
11/29/2017 ∙ by Qi Ye, et al. ∙ 0 ∙ share

read it
Learning Deep Convolutional Embeddings for Face Representation Using Joint Sample- and Set-based Supervision

In this work, we investigate several methods and strategies to learn dee...
08/01/2017 ∙ by Baris Gecer, et al. ∙ 0 ∙ share

read it
The 2017 Hands in the Million Challenge on 3D Hand Pose Estimation

We present the 2017 Hands in the Million Challenge, a public competition...
07/07/2017 ∙ by Shanxin Yuan, et al. ∙ 0 ∙ share

read it
Recovering 6D Object Pose: Multi-modal Analyses on Challenges

A large number of studies analyse object detection and pose estimation a...
06/10/2017 ∙ by Caner Sahin, et al. ∙ 0 ∙ share

read it
Deep Convolutional Decision Jungle for Image Classification

We propose a novel method called deep convolutional decision jungle (CDJ...
06/06/2017 ∙ by Seungryul Baek, et al. ∙ 0 ∙ share

read it
BigHand2.2M Benchmark: Hand Pose Dataset and State of the Art Analysis

In this paper we introduce a large-scale hand pose dataset, collected us...
04/09/2017 ∙ by Shanxin Yuan, et al. ∙ 0 ∙ share

read it
First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations

In this work we study the use of 3D hand poses to recognize first-person...
04/08/2017 ∙ by Guillermo Garcia-Hernando, et al. ∙ 0 ∙ share

read it
Learning and Refining of Privileged Information-based RNNs for Action Recognition from Depth Sequences

Existing RNN-based approaches for action recognition from depth sequence...
03/28/2017 ∙ by Zhiyuan Shi, et al. ∙ 0 ∙ share

read it
A Learning-based Variable Size Part Extraction Architecture for 6D Object Pose Recovery in Depth

State-of-the-art techniques for 6D object pose recovery depend on occlus...
01/09/2017 ∙ by Caner Sahin, et al. ∙ 0 ∙ share

read it
Real-time Online Action Detection Forests using Spatio-temporal Contexts

Online action detection (OAD) is challenging since 1) robust yet computa...
10/28/2016 ∙ by Seungryul Baek, et al. ∙ 0 ∙ share

read it
Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection

A human action can be seen as transitions between one's body poses over ...
07/10/2016 ∙ by Guillermo Garcia-Hernando, et al. ∙ 0 ∙ share

read it
Siamese Regression Networks with Efficient mid-level Feature Extraction for 3D Object Pose Estimation

In this paper we tackle the problem of estimating the 3D pose of object ...
07/08/2016 ∙ by Andreas Doumanoglou, et al. ∙ 0 ∙ share

read it
Latent Bi-constraint SVM for Video-based Object Recognition

We address the task of recognizing objects from video input. This import...
05/31/2016 ∙ by Yang Liu, et al. ∙ 0 ∙ share

read it
Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation

Discriminative methods often generate hand poses kinematically implausib...
04/12/2016 ∙ by Qi Ye, et al. ∙ 0 ∙ share

read it
Iterative Hough Forest with Histogram of Control Points for 6 DoF Object Registration from Depth Images

State-of-the-art techniques proposed for 6D object pose recovery depend ...
03/08/2016 ∙ by Caner Sahin, et al. ∙ 0 ∙ share

read it
Latent-Class Hough Forests for 6 DoF Object Pose Estimation

In this paper we present Latent-Class Hough Forests, a method for object...
02/03/2016 ∙ by Rigas Kouskouridas, et al. ∙ 0 ∙ share

read it
Recovering 6D Object Pose and Predicting Next-Best-View in the Crowd

Object detection and 6D pose estimation in the crowd (scenes with multip...
12/23/2015 ∙ by Andreas Doumanoglou, et al. ∙ 0 ∙ share

read it
Enhanced Random Forest with Image/Patch-Level Learning for Image Understanding

Image understanding is an important research domain in the computer visi...
10/14/2014 ∙ by Wai Lam Hoo, et al. ∙ 0 ∙ share

read it
Multiple Object Tracking: A Literature Review

Multiple Object Tracking (MOT) is an important computer vision problem w...
09/26/2014 ∙ by Wenhan Luo, et al. ∙ 0 ∙ share

read it

Tae-Kyun Kim

Featured Co-authors