Publications
Only recent publications are listed here. The full list can be found in my Google Scholar Link.
2026
- GraspALL: Adaptive Structural Compensation from Luminance Variation for Robotic Garment Grasping in Any Low-Light ConditionsIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026
- Towards cost-effective and safe contact-rich robotic manipulation with reinforcement learning: A review of techniques for future industrial automationProceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering 2026
- SimForce: Force and Surface Electromyography from Full Body Video with Graph Neural NetsIn The IEEE/CVF Winter Conference on Applications of Computer Vision 2026
- Force-Aware 3D Contact Modeling for Stable Grasp GenerationIn Proceedings of the AAAI Conference on Artificial Intelligence 2026
2025
- A unified framework for unsupervised action learning via global-to-local motion transformerPattern Recognition 2025
- Collaborative Learning for 3D Hand-Object Reconstruction and Compositional Action Recognition from Egocentric RGB Videos Using SuperquadricsIn Proceedings of the AAAI Conference on Artificial Intelligence 2025
- PersonaBooth: Personalized Text-to-Motion GenerationIn Proceedings of the Computer Vision and Pattern Recognition Conference 2025
- 3D Prior is All You Need: Cross-Task Few-shot 2D Gaze EstimationIn Proceedings of the Computer Vision and Pattern Recognition Conference 2025
- AuGQ: Augmented quantization granularity to overcome accuracy degradation for sub-byte quantized deep neural networksApplied Intelligence 2025
- Single-view Image to Novel-view Generation for Hand-Object InteractionsIn Proceedings of the AAAI Conference on Artificial Intelligence 2025
- Behavior-aware Knowledge-embedded Model for Driver Attention PredictionIEEE Transactions on Circuits and Systems for Video Technology 2025
- Video-based human pose estimation via feature decoupling and multi-hypothesis calibrationPattern Recognition 2025
- PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose EstimationIn Proceedings of the Computer Vision and Pattern Recognition Conference 2025
- Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language ModelsIn Proceedings of the IEEE/CVF International Conference on Computer Vision 2025
- Roll Your Eyes: Gaze Redirection via Explicit 3D Eyeball RotationIn Proceedings of the 33rd ACM International Conference on Multimedia 2025
- DarkSeg: Infrared-Driven Semantic Segmentation for Garment Grasping Detection in Low-Light ConditionsIn 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025
- Multi-Hypothesis 3D Hand Mesh Recovering from a Single Blurry ImageIn IEEE International Conference on Multimedia and Expo 2025
- High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose EstimationIn Proceedings of the IEEE/CVF International Conference on Computer Vision 2025
- AMDANet: Attention-Driven Multi-Perspective Discrepancy Alignment for RGB-Infrared Image Fusion and SegmentationIn Proceedings of the IEEE/CVF International Conference on Computer Vision 2025
- The Third Visual Object Tracking Segmentation VOTS2025 Challenge ResultsIn Proceedings of the IEEE/CVF International Conference on Computer Vision 2025
2024
- Multi-modal gaze following in conversational scenariosIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision 2024
- NCRF: neural contact radiance fields for free-viewpoint rendering of hand-object interactionIn 2024 International Conference on 3D Vision (3DV) 2024
- What do you see in vehicle? comprehensive vision solution for in-vehicle gaze estimationIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024
- Benchmarks and challenges in pose estimation for egocentric hand interactions with objectsIn European Conference on Computer Vision 2024
- Georef: Geometric alignment across shape variation for category-level object pose refinementIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024
- Textgaze: Gaze-controllable face generation with natural languageIn Proceedings of the 32nd ACM International Conference on Multimedia 2024
- Few Exemplar-Based General Medical Image Segmentation via Domain-Aware Selective AdaptationIn Proceedings of the Asian Conference on Computer Vision 2024
- Most: Motion style transformer between diverse action contentsIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024
- Nl2contact: Natural language guided 3d hand-object contact modeling with diffusion modelIn European Conference on Computer Vision 2024
- Dual prototype-driven objectness decoupling for cross-domain object detection in urban sceneIn Proceedings of the Asian Conference on Computer Vision 2024
- GRF-MV: Ground Reaction Force Estimation from Monocular VideoIn BMVC 2024 Workshop on Advancing Non-invasive Human Motion Characterization (ANIMA 2024) 2024
- The second visual object tracking segmentation VOTS2024 challenge resultsIn European Conference on Computer Vision 2024
- Bidirectional Regression for Monocular 6DoF Head Pose Estimation and Reference System Alignment2024
2023
- Trans6D: Transformer-Based 6D Object Pose Estimation and RefinementIn European Conference on Computer Vision Workshop 2023
- Gazenerf: 3d-aware gaze redirection with neural radiance fieldsIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023
- Mutual information-based temporal difference learning for human pose estimation in videoIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023
- Hs-pose: Hybrid scope feature extraction for category-level object pose estimationIn Proceedings of the IEEE/CVF conference on computer vision and pattern recognition 2023
- G-DAIC: A gaze initialized framework for description and aesthetic-based image croppingProceedings of the ACM on Human-Computer Interaction 2023
- Where are they looking in the 3d space?In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023
- Gazecaps: Gaze estimation with self-attention-routed capsulesIn Proceedings of the IEEE/CVF conference on computer vision and pattern recognition 2023
- Diffpose: Spatiotemporal diffusion model for video-based human pose estimationIn Proceedings of the IEEE/CVF International Conference on Computer Vision 2023
- Spectral graphormer: Spectral graph-based transformer for egocentric two-hand reconstruction using multi-view color imagesIn Proceedings of the IEEE/CVF International Conference on Computer Vision 2023
- The first visual object tracking segmentation vots2023 challenge resultsIn Proceedings of the IEEE/CVF International Conference on Computer Vision 2023
- Switching temporary teachers for semi-supervised semantic segmentationAdvances in Neural Information Processing Systems 2023
2022
- Contrastive vicinal space for unsupervised domain adaptationIn European Conference on Computer Vision 2022
- Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph ConvolutionIn IEEE Computer Vision and Pattern Recognition (CVPR) 2022
- Self-attention with convolution and deconvolution for efficient eye gaze estimation from a full face imageIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022
- S^2 Contact: Graph-based Network for 3D Hand-Object Contact Estimation with Semi-Supervised LearningIn European Conference on Computer Vision 2022
- Cross-domain representation learning for clothes unfolding in robot-assisted dressingIn Tenth International Workshop on Assistive Computer Vision and Robotics 2022
- Towards Generic 3D Tracking in RGBD Videos: Benchmark and BaselineIn European Conference on Computer Vision 2022
- Global-local Motion Transformer for Unsupervised Skeleton-based Action LearningIn European conference on computer vision 2022
- The tenth visual object tracking vot2022 challenge resultsIn European Conference on Computer Vision 2022
2021
- Class-attentive diffusion network for semi-supervised classificationIn Proceedings of the AAAI conference on artificial intelligence 2021
- Fixbi: Bridging domain spaces for unsupervised domain adaptationIn Proceedings of the IEEE/CVF conference on computer vision and pattern recognition 2021
- Self-supervised spatio-temporal representation learning using variable playback speed predictionIEEE Access 2021
- Motion-aware ensemble of three-mode trackers for unmanned aerial vehiclesMachine Vision and Applications 2021
- Fs-net: Fast shape-based network for category-level 6d object pose estimation with decoupled rotation mechanismIn Proceedings of the IEEE/CVF conference on computer vision and pattern recognition 2021
- Unsupervised hyperbolic representation learning via message passing auto-encodersIn Proceedings of the IEEE/CVF conference on computer vision and pattern recognition 2021
- Apparently irrational choice as optimal sequential decision makingIn Proceedings of the AAAI Conference on Artificial Intelligence 2021
- Self-supervised visual learning by variable playback speeds prediction of a videoIEEE Access 2021
- Learning a model-driven variational network for deformable image registrationIEEE Transactions on Medical Imaging 2021
- Nesterov accelerated ADMM for fast diffeomorphic image registrationIn International Conference on Medical Image Computing and Computer-Assisted Intervention 2021
- The ninth visual object tracking vot2021 challenge resultsIn Proceedings of the IEEE/CVF international conference on computer vision 2021
2020
- Body pose sonification for a view-independent auditory aid to blind rock climbersIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision 2020
- PointPoseNet: Point pose network for robust 6D object pose estimationIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision 2020
- User modelling using multimodal information for personalised dressing assistanceIEEE Access 2020
- G2l-net: Global to local network for real-time 6d pose estimation with embedding vector featuresIn Proceedings of the IEEE/CVF conference on computer vision and pattern recognition 2020
- Combining task predictors via enhancing joint predictabilityIn European Conference on Computer Vision 2020
2019
- Symmetric graph convolutional autoencoder for unsupervised graph representation learningIn Proceedings of the IEEE/CVF international conference on computer vision 2019
- Joint manifold diffusion for combining predictions on decoupled observationsIn IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019
2018
- Highly articulated kinematic structure estimation combining motion and skeleton informationIEEE Transactions on Pattern Analysis and Machine Intelligence 2018
- Context-aware deep feature compression for high-speed visual trackingIn Proceedings of the IEEE conference on computer vision and pattern recognition 2018
- Transferring visuomotor learning from simulation to the real world for robotics manipulation tasksIn 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2018
2017
- Attentional correlation filter network for adaptive visual trackingIn Proceedings of the IEEE conference on computer vision and pattern recognition 2017
- DAC-h3: a proactive robot cognitive architecture to acquire and express knowledge about the world and the selfIEEE Transactions on Cognitive and Developmental Systems 2017
- Learning kinematic structure correspondences using multi-order similaritiesIEEE transactions on pattern analysis and machine intelligence 2017
2016
- Blockwise collaborative representation-based classification via L2-norm of query data for accurate face recognitionElectronics Letters 2016
- Transition hough forest for trajectory-based action recognitionIn 2016 IEEE Winter Conference on Applications of Computer Vision (WACV) 2016
- Spatio-temporal hough forest for efficient detection–localisation–recognition of fingerwriting in egocentric cameraComputer Vision and Image Understanding 2016
- Kinematic structure correspondences via hypergraph matchingIn Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016
- Visual tracking using attention-modulated disintegration and integrationIn Proceedings of the IEEE conference on computer vision and pattern recognition 2016
- Towards anchoring self-learned representations to those of other agentsIn Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems Workshop on Bio-inspired Social Robot Learning in Home Scenarios 2016 2016
- Personalised assistive dressing by humanoid robots using multi-modal informationIn IEEE ICRA Workshop on Human-Robot Interfaces for Enhanced Physical Interactions 2016
- Latent regression forest: structured estimation of 3d hand posesIEEE Transactions on Pattern Analysis and Machine Intelligence 2016
2015
- Unsupervised learning of complex articulated kinematic structures combining motion and skeleton informationIn Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2015
- 3D finger cape: Clicking action and position estimation under self-occlusions in egocentric viewpointIEEE Transactions on Visualization and Computer Graphics 2015
- Stare: Spatio-temporal attention relocation for multiple structured activities detectionIEEE Transactions on Image Processing 2015
2014
- Latent regression forest: Structured estimation of 3d articulated hand postureIn Proceedings of the IEEE conference on computer vision and pattern recognition 2014
2013
- Action Chart: A Representation for Efficient Recognition of Complex ActivityIn Proceedings of the British Machine Vision Conference 2013
- Abstracted radon profiles for fingerprint recognitionIn 2013 IEEE International Conference on Image Processing 2013
2012
- Robust moving object detection against fast illumination changeComputer Vision and Image Understanding 2012
- Hierarchical feature grouping for multiple object segmentation and trackingIn Proceedings of the 27th Conference on Image and Vision Computing New Zealand 2012
2011
- Pil-eye: Integrated system for sustainable development of intelligent visual surveillance algorithmsIn 2011 International Conference on Digital Image Computing: Techniques and Applications 2011
- Tracking failure detection by imitating human visual perceptionIn 2011 18th IEEE International Conference on Image Processing 2011
- Spatiotemporal pattern modeling for fault detection and classification in semiconductor manufacturingIEEE Transactions on Semiconductor Manufacturing 2011
- Modeling of moving object trajectory by spatio-temporal learning for abnormal behavior detectionIn 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) 2011
- Unsupervised motion learning for abnormal behavior detection in visual surveillanceJournal of the Institute of Electronics Engineers of Korea SC 2011
2010
2009
- Optical image stabilizing system using multirate fuzzy PID controller for mobile device cameraIEEE Transactions on Consumer Electronics 2009
- Detection of suspicious activity using incremental outlier detection algorithmsIn Signal and Data Processing of Small Targets 2009 2009
2008
- Fast incremental learning for one-class support vector classifier using sample margin informationIn 2008 19th International Conference on Pattern Recognition 2008
- SVDD based Scene Understanding using Color Space InformationIn Proceedings of the KIEE Conference 2008
- Moving Object Detection Robust to Sudden illumination Change using Modified Texture InformationIn Proceedings of the KIEE Conference 2008
2007
- Fast support vector data description using k-means clusteringIn International Symposium on Neural Networks 2007
- Emotional head robot with behavior decision model and face recognitionIn 2007 International Conference on Control, Automation and Systems 2007
- Support Vector Data Description Using Clustering MethodIn ITC-CSCC: International Technical Conference on Circuits Systems, Computers and Communications 2007
- K-means Support Vector Data Description concerning Negative dataIn Proceedings of the KIEE Conference 2007
- Support Vector Data Description using Mean Shift ClusteringIn Proceedings of the KIEE Conference 2007
- Shamyl Bin Mansoor, Woo-Sung Kang, Seok Min Yoon, Jin Hee Na, Young Min Baek, Hyung Jin Chang, Dong Sung Song, Jin Young Choi and Hyeong-Seok Ko,“Emotional Head Robot with Behavior Decision Model and Face Recognition”In International Conference on Control, Automation and Systems Oct 2007
2006
- Face Recognition Based on PCA and LDA Combining ClusteringIn Proceedings of the IEEK Conference 2006
- KMSVOD: Support Vector Data Description using K-means ClusteringIn Proceedings of the KIEE Conference 2006