|
I am a postdoctoral research fellow at VGG @ Oxford working with Prof. Andrew Zisserman. My research interests are Egocentric Vision, Action Recognition, Contextual AI, Hand-object Interaction, Video Understanding, AR/VR, Multi-modal Learning, Visual-language Models and Self-supervised Learning. Previously, I did my PhD under the supervision of Prof. Marc Pollefeys at ETH Zurich and I earned my Master's degree from UCLA. I received my Bachelor's in Electrical Engineering from Yonsei University, Seoul, Korea If you are interested in semester projects (ETHZ), master's theses (ETHZ), 4YP (Oxford), or personal projects related to action recognition, egocentric vision, video understanding, and hand-object interaction that could lead to publications, feel free to email me. We can discuss potential exciting projects. |
|
|
|
- 03/2025 Our paper JEGAL is accepted to ICCV 2025.
- 03/2025 Our paper EgoPressure is accepted to CVPR 2025.
- 09/2024 I will start my postdoc fellow position at VGG, Oxford.
- 07/2024 I successfully defended my PhD.
- 07/2023 Our paper HoloAssist is accepted to ICCV 2023.
- 12/2022 I will start my research internship at Meta Reality Labs Research.
- 06/2022 Our paper Egobody is accepted to ECCV 2022.
- 06/2022 I will start my research internship at Microsoft Research.
- 05/2022 I will co-organize Human Body, Hands, and Activities from Egocentric and Multi-view Cameras @ ECCV 2022.
- 03/2022 Our paper CASA is accepted to CVPR 2022 (oral).
- 03/2021 Our paper H2O is accepted to ICCV 2021.
|
|
|
Junho Park, Andrew Sangwoo Ye, Taein Kwon arXiv, 2025 project page / paper We introduce EgoWorld, a novel two-stage framework that reconstructs egocentric view from rich exocentric observations, including depth maps, 3D hand poses, and textual descriptions. |
|
Sindhu Hggde*, K R Prajwal*, Taein Kwon, Andrew Zisserman ICCV, 2025 project page / paper / code We introduce JEGAL, a Joint Embedding space for Gestures, Audio and Language. Our semantic gesture representations can be used to perform multiple downstream tasks such as cross-modal retrieval, spotting gestured words, and identifying who is speaking solely using gestures. * co-first authors |
|
Yiming Zhao*, Taein Kwon*, Paul Streli*, Marc Pollefeys, Christian Holz CVPR, 2025 project page / paper We introduce EgoPressure, a novel dataset of touch contact and pressure interaction from an egocentric perspective, complemented with hand pose meshes and fine-grained pressure intensities for each contact. * co-first authors |
|
Taein Kwon, Zador Pataki, Mahdi Rad, Marc Pollefeys arXiv, 2025 paper We propose a novel framework that overcomes these limitations using sequence alignment via implicit clustering. Specifically, our key idea is to perform implicit clip-level clustering while aligning frames in sequences. This coupled with our proposed dual augmentation technique enhances the network's ability to learn generalizable and discriminative representations. |
|
Xin Wang*, Taein Kwon*, Mahdi Rad, Bowen Pan, Ishani Chakraborty, Sean Andrist, Ashley Fanello, Bugra Tekin, Felipe Vieira Frujeri, Neel Joshi, Marc Pollefeys ICCV, 2023 project page / paper / supp HoloAssist is a large-scale egocentric human interaction dataset, where two people collaboratively complete physical manipulation tasks. By augmenting the data with action and conversational annotations and observing the rich behaviors of various participants, we present key insights into how human assistants correct mistakes, intervene in the task completion procedure, and ground their instructions to the environment. * co-first authors |
|
Junan Lin*, Zhichao Sun*, Enjie Cao*, Taein Kwon, Mahdi Rad, Marc Pollefeys arXiv, 2023 paper Contact-aware Skeletal Action Recognition (CaSAR) uses novel representations of hand-object interaction that encompass spatial information: 1) contact points where the hand joints meet the objects, 2) distant points where the hand joints are far away from the object and nearly not involved in the current action. Our framework is able to learn how the hands touch or stay away from the objects for each frame of the action sequence, and use this information to predict the action class. * co-first authors |
|
Siwei Zhang, Qianli Ma, Yan Zhang, Zhiyin Qian, Taein Kwon, Marc Pollefeys, Federica Bogo, Siyu Tang ECCV, 2022 project page / paper / code EgoBody is a large-scale dataset of accurate 3D human body shape, pose and motion of humans interacting in 3D scenes, with multi-modal streams from third-person and egocentric views, captured by Azure Kinects and a HoloLens2. Given two interacting subjects, we leverage a lightweight multi-camera rig to reconstruct their 3D shape and pose over time. |
|
Taein Kwon, Bugra Tekin, Siyu Tang, Marc Pollefeys CVPR, 2022 (Oral Presentation) project page / paper / video / code We propose a skeletal self-supervised learning approach that uses alignment as a pretext task. Our approach to alignment relies on a context-aware attention model that incorporates spatial and temporal context within and across sequences and a contrastive learning formulation that relies on 4D skeletal augmentations. Pose data provides a valuable cue for alignment and downstream tasks, such as phase classification and phase progression, as it is robust to different camera angles and changes in the background, while being efficient for real-time processing. |
|
Taein Kwon, Bugra Tekin, Jan Stuhmer, Federica Bogo, Marc Pollefeys ICCV, 2021 project page / paper / video In this paper, we propose a method to collect a dataset of two hands manipulating objects for first person interaction recognition. We provide a rich set of annotations including action labels, object classes, 3D left & right hand poses, 6D object poses, camera poses and scene point clouds. We further propose the first method to jointly recognize the 3D poses of two hands manipulating objects and a novel topology-aware graph convolutional network for recognizing hand-object interactions. |
|
Taein Kwon, Eunjeong Park, Hyukjae Chang ACM BCB, 2016 We propose a sensor-equipped food container, Smart Refrigerator, which recognizes foods and monitors their status. We demonstrated the performance in detection of food and suggested that automatic monitoring of food intake can provide intuitive feedback to users. |
|
|
Teaching Assistant
|
|
|
Awards
|
Talks
|
|
|
|
Organizer: Human Body, Hands, and Activities from Egocentric and Multi-view Cameras @ ECCV'22, KSAE Open Seminar @ ETH Zurich Reviwer: CVPR, ICCV, ECCV, CHI, SIGGRAPH |
|
|
|
|
|
|
Dept. of Computer Science
ETH Zurich CNB G 85.2 Universitatstrasse 6 CH-8092 Zurich, Switzerland Tel: +41 (0)44 63 26 360 taein.kwon@inf (dot) ethz (dot) ch |
|
Website template from Jon Barron. |