Search Results for author: Hyung Jin Chang

Found 45 papers, 20 papers with code

RT-GENE: Real-Time Eye Gaze Estimation in Natural Environments

1 code implementation ECCV 2018 Tobias Fischer, Hyung Jin Chang, Yiannis Demiris

We first record a novel dataset of varied gaze and head pose images in a natural environment, addressing the issue of ground truth annotation by measuring head pose using a motion capture system and eye gaze using mobile eyetracking glasses.

Gaze Estimation Image Inpainting

G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features

1 code implementation CVPR 2020 Wei Chen, Xi Jia, Hyung Jin Chang, Jinming Duan, Ales Leonardis

Third, via the predicted segmentation and translation, we transfer the fine object point cloud into a local canonical coordinate, in which we train a rotation localization network to estimate initial object rotation.

6D Pose Estimation 6D Pose Estimation using RGB +2

BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimation

1 code implementation25 Sep 2023 Uyoung Jeong, Seungryul Baek, Hyung Jin Chang, Kwang In Kim

Our new instance embedding loss provides a learning signal on the entire area of the image with bounding box annotations, achieving globally consistent and disentangled instance representation.

Disentanglement Keypoint Estimation +2

FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation

1 code implementation CVPR 2021 Jaemin Na, Heechul Jung, Hyung Jin Chang, Wonjun Hwang

However, most of the studies were based on direct adaptation from the source domain to the target domain and have suffered from large domain discrepancies.

Unsupervised Domain Adaptation

Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning

1 code implementation ICCV 2019 Jiwoong Park, Minsik Lee, Hyung Jin Chang, Kyuewang Lee, Jin Young Choi

For the reconstruction of node features, the decoder is designed based on Laplacian sharpening as the counterpart of Laplacian smoothing of the encoder, which allows utilizing the graph structure in the whole processes of the proposed autoencoder architecture.

Clustering Graph Clustering +3

Unsupervised Hyperbolic Representation Learning via Message Passing Auto-Encoders

1 code implementation CVPR 2021 Jiwoong Park, Junho Cho, Hyung Jin Chang, Jin Young Choi

Most of the existing literature regarding hyperbolic embedding concentrate upon supervised learning, whereas the use of unsupervised hyperbolic embedding is less well explored.

Representation Learning

HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation

1 code implementation CVPR 2023 Linfang Zheng, Chen Wang, Yinghan Sun, Esha Dasgupta, Hua Chen, Ales Leonardis, Wei zhang, Hyung Jin Chang

In this paper, we focus on the problem of category-level object pose estimation, which is challenging due to the large intra-category shape variation.

Pose Estimation Translation

Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning

1 code implementation13 Jul 2022 Boeun Kim, Hyung Jin Chang, Jungho Kim, Jin Young Choi

To tackle the learning of whole-body motion, long-range temporal dynamics, and person-to-person interactions, we design a global and local attention mechanism, where, global body motions and local joint motions pay attention to each other.

Context-aware Deep Feature Compression for High-speed Visual Tracking

1 code implementation CVPR 2018 Jongwon Choi, Hyung Jin Chang, Tobias Fischer, Sangdoo Yun, Kyuewang Lee, Jiyeoup Jeong, Yiannis Demiris, Jin Young Choi

We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers.

Denoising Feature Compression +3

Contrastive Vicinal Space for Unsupervised Domain Adaptation

1 code implementation26 Nov 2021 Jaemin Na, Dongyoon Han, Hyung Jin Chang, Wonjun Hwang

In the contrastive space, inter-domain discrepancy is mitigated by constraining instances to have contrastive views and labels, and the consensus space reduces the confusion between intra-domain categories.

Unsupervised Domain Adaptation

MAGAN: Margin Adaptation for Generative Adversarial Networks

1 code implementation12 Apr 2017 Ruohan Wang, Antoine Cully, Hyung Jin Chang, Yiannis Demiris

We propose the Margin Adaptation for Generative Adversarial Networks (MAGANs) algorithm, a novel training procedure for GANs to improve stability and performance by using an adaptive hinge loss function.

Image Generation

Class-Attentive Diffusion Network for Semi-Supervised Classification

1 code implementation18 Jun 2020 Jongin Lim, Daeho Um, Hyung Jin Chang, Dae Ung Jo, Jin Young Choi

In contrast to the existing diffusion methods with a transition matrix determined solely by the graph structure, CAD considers both the node features and the graph structure with the design of our class-attentive transition matrix that utilizes a classifier.

Classification General Classification

Investigation of Architectures and Receptive Fields for Appearance-based Gaze Estimation

1 code implementation18 Aug 2023 Yunhan Wang, Xiangwei Shi, Shalini De Mello, Hyung Jin Chang, Xucong Zhang

With the rapid development of deep learning technology in the past decade, appearance-based gaze estimation has attracted great attention from both computer vision and human-computer interaction research communities.

Contrastive Learning Disentanglement +2

MoST: Motion Style Transformer between Diverse Action Contents

1 code implementation10 Mar 2024 Boeun Kim, Jungho Kim, Hyung Jin Chang, Jin Young Choi

While existing motion style transfer methods are effective between two motions with identical content, their performance significantly diminishes when transferring style between motions with different contents.

Disentanglement Motion Style Transfer +1

Multi-Modal Gaze Following in Conversational Scenarios

1 code implementation9 Nov 2023 Yuqi Hou, Zhongqun Zhang, Nora Horanyi, Jaewon Moon, Yihua Cheng, Hyung Jin Chang

We then use the identity information to enhance scene images and propose a gaze candidate estimation network.

Latent Regression Forest: Structured Estimation of 3D Articulated Hand Posture

no code implementations CVPR 2014 Danhang Tang, Hyung Jin Chang, Alykhan Tejani, Tae-Kyun Kim

In contrast to prior forest-based methods, which take dense pixels as input, classify them independently and then estimate joint positions afterwards; our method can be considered as a structured coarse-to-fine search, starting from the centre of mass of a point cloud until locating all the skeletal joints.

3D Hand Pose Estimation regression

Unsupervised Learning of Complex Articulated Kinematic Structures Combining Motion and Skeleton Information

no code implementations CVPR 2015 Hyung Jin Chang, Yiannis Demiris

The iterative merge process is guided by a skeleton distance function which is generated from a novel object boundary generation method from sparse points.

Motion Segmentation

Kinematic Structure Correspondences via Hypergraph Matching

no code implementations CVPR 2016 Hyung Jin Chang, Tobias Fischer, Maxime Petit, Martina Zambelli, Yiannis Demiris

In this paper, we present a novel framework for finding the kinematic structure correspondence between two objects in videos via hypergraph matching.

Hypergraph Matching

Visual Tracking Using Attention-Modulated Disintegration and Integration

no code implementations CVPR 2016 Jongwon Choi, Hyung Jin Chang, Jiyeoup Jeong, Yiannis Demiris, Jin Young Choi

In this paper, we present a novel attention-modulated visual tracking algorithm that decomposes an object into multiple cognitive units, and trains multiple elementary trackers in order to modulate the distribution of attention according to various feature and kernel types.

Object Visual Tracking

Joint Manifold Diffusion for Combining Predictions on Decoupled Observations

no code implementations CVPR 2019 Kwang In Kim, Hyung Jin Chang

We present a new predictor combination algorithm that improves a given task predictor based on potentially relevant reference predictors.

Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold

no code implementations CVPR 2017 YoungJoon Yoo, Sangdoo Yun, Hyung Jin Chang, Yiannis Demiris, Jin Young Choi

(iii) The proposed regression is embedded into a generative model, and the whole procedure is developed by the variational autoencoder framework.

regression

VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learning

no code implementations CVPR 2021 Jongwon Choi, Kwang Moo Yi, Ji-Hoon Kim, Jinho Choo, Byoungjip Kim, Jin-Yeop Chang, Youngjune Gwon, Hyung Jin Chang

We show that our method can be applied to classification tasks on multiple different datasets -- including one that is a real-world dataset with heavy data imbalance -- significantly outperforming the state of the art.

Active Learning

Implications of Human Irrationality for Reinforcement Learning

no code implementations7 Jun 2020 Haiyang Chen, Hyung Jin Chang, Andrew Howes

Recent work in the behavioural sciences has begun to overturn the long-held belief that human decision making is irrational, suboptimal and subject to biases.

BIG-bench Machine Learning Decision Making +2

SeqHAND:RGB-Sequence-Based 3D Hand Pose and Shape Estimation

no code implementations10 Jul 2020 John Yang, Hyung Jin Chang, Seungeui Lee, Nojun Kwak

In this paper, we attempt to not only consider the appearance of a hand but incorporate the temporal movement information of a hand in motion into the learning framework for better 3D hand pose estimation performance, which leads to the necessity of a large scale dataset with sequential RGB hand images.

3D Hand Pose Estimation

Combining Task Predictors via Enhancing Joint Predictability

no code implementations ECCV 2020 Kwang In Kim, Christian Richardt, Hyung Jin Chang

Predictor combination aims to improve a (target) predictor of a learning task based on the (reference) predictors of potentially relevant tasks, without having access to the internals of individual predictors.

Attribute Multi-class Classification

SeqHAND: RGB-Sequence-Based 3D Hand Pose and Shape Estimation

no code implementations ECCV 2020 John Yang, Hyung Jin Chang, Seungeui Lee, Nojun Kwak

In this paper, we attempt to not only consider the appearance of a hand but incorporate the temporal movement information of a hand in motion into the learning framework for better 3D hand pose estimation performance, which leads to the necessity of a large scale dataset with sequential RGB hand images.

3D Hand Pose Estimation

Learning a Model-Driven Variational Network for Deformable Image Registration

no code implementations25 May 2021 Xi Jia, Alexander Thorley, Wei Chen, Huaqi Qiu, Linlin Shen, Iain B Styles, Hyung Jin Chang, Ales Leonardis, Antonio de Marvao, Declan P. O'Regan, Daniel Rueckert, Jinming Duan

We then propose two neural layers (i. e. warping layer and intensity consistency layer) to model the analytical solution and a residual U-Net to formulate the denoising problem (i. e. generalized denoising layer).

Denoising Image Registration

Nesterov Accelerated ADMM for Fast Diffeomorphic Image Registration

no code implementations26 Sep 2021 Alexander Thorley, Xi Jia, Hyung Jin Chang, Boyang Liu, Karina Bunting, Victoria Stoll, Antonio de Marvao, Declan P. O'Regan, Georgios Gkoutos, Dipak Kotecha, Jinming Duan

Recent developments in stochastic approaches based on deep learning have achieved sub-second runtimes for DiffIR with competitive registration accuracy, offering a fast alternative to conventional iterative methods.

Image Registration

Category-Level 6D Object Pose Estimation with Flexible Vector-Based Rotation Representation

no code implementations9 Dec 2022 Wei Chen, Xi Jia, Zhongqun Zhang, Hyung Jin Chang, Linlin Shen, Jinming Duan, Ales Leonardis

The proposed rotation representation has two major advantages: 1) decoupled characteristic that makes the rotation estimation easier; 2) flexible length and rotated angle of the vectors allow us to find a more suitable vector representation for specific pose estimation task.

6D Pose Estimation using RGB Data Augmentation

Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video

no code implementations CVPR 2023 Runyang Feng, Yixing Gao, Xueqing Ma, Tze Ho Elden Tse, Hyung Jin Chang

On the other hand, the temporal difference has the ability to encode representative motion information which can potentially be valuable for pose estimation but has not been fully exploited.

Disentanglement Optical Flow Estimation +1

Clothes Grasping and Unfolding Based on RGB-D Semantic Segmentation

no code implementations5 May 2023 Xingyu Zhu, Xin Wang, Jonathan Freer, Hyung Jin Chang, Yixing Gao

These methods often utilize physics engines to synthesize depth images to reduce the cost of real labeled data collection.

Data Augmentation Semantic Segmentation

DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation

no code implementations ICCV 2023 Runyang Feng, Yixing Gao, Tze Ho Elden Tse, Xueqing Ma, Hyung Jin Chang

However, extending such models to multi-frame human pose estimation is non-trivial due to the presence of the additional temporal dimension in videos.

Denoising Image Generation +5

High-Fidelity Eye Animatable Neural Radiance Fields for Human Face

no code implementations1 Aug 2023 Hengfei Wang, Zhongqun Zhang, Yihua Cheng, Hyung Jin Chang

In this paper, we aim to learn a face NeRF model that is sensitive to eye movements from multi-view images.

Face Model Gaze Estimation

NCRF: Neural Contact Radiance Fields for Free-Viewpoint Rendering of Hand-Object Interaction

no code implementations8 Feb 2024 Zhongqun Zhang, Jifei Song, Eduardo Pérez-Pellitero, Yiren Zhou, Hyung Jin Chang, Aleš Leonardis

Despite remarkable progress that has been achieved in this field, existing methods still fail to synthesize the hand-object interaction photo-realistically, suffering from degraded rendering quality caused by the heavy mutual occlusions between the hand and the object, and inaccurate hand-object pose estimation.

hand-object pose Novel View Synthesis +3

Cannot find the paper you are looking for? You can Submit a new open access paper.