no code implementations • 14 May 2024 • Yashuai Yan, Esteve Valls Mascaro, Tobias Egle, Dongheui Lee
This paper addresses the critical need for refining robot motions that, despite achieving a high visual similarity through human-to-humanoid retargeting methods, fall short of practical execution in the physical realm.
no code implementations • 7 Feb 2024 • Esteve Valls Mascaro, Yashuai Yan, Dongheui Lee
Integrating robots into populated environments is a complex challenge that requires an understanding of human social dynamics.
no code implementations • 28 Sep 2023 • Esteve Valls Mascaro, Daniel Sliwowski, Dongheui Lee
In this paper, we propose a Human-Object Interaction (HOI) anticipation framework for collaborative robots.
Ranked #1 on Human-Object Interaction Anticipation on VidHOI
Human-Object Interaction Anticipation Human-Object Interaction Detection
no code implementations • 11 Sep 2023 • Yashuai Yan, Esteve Valls Mascaro, Dongheui Lee
Additionally, we propose a consistency term to build a common latent space that captures the similarity of the poses with precision while allowing direct robot motion control from the latent space.
no code implementations • 14 Aug 2023 • Esteve Valls Mascaro, Hyemin Ahn, Dongheui Lee
Experimental results show that our model successfully forecasts human motion on the Human3. 6M dataset.
1 code implementation • 6 Jun 2023 • Zhifan Ni, Esteve Valls Mascaró, Hyemin Ahn, Dongheui Lee
Understanding the human-object interactions (HOIs) from a video is essential to fully comprehend a visual scene.
Ranked #2 on Human-Object Interaction Anticipation on VidHOI
Human-Object Interaction Anticipation Human-Object Interaction Detection +1
no code implementations • 3 May 2023 • Sang-ik An, Dongheui Lee, Gyunghoon Park
The key observation is that the usual input-output linearization problem can be interpreted as the problem of solving simultaneous linear equations associated with the input gain matrix: thus, even at points where the input gain matrix becomes singular, it is still possible to solve a part of linear equations, by which a subset of input-output relations is made linear or close to be linear.
no code implementations • 28 Feb 2023 • Hyemin Ahn, Esteve Valls Mascaro, Dongheui Lee
After many researchers observed fruitfulness from the recent diffusion probabilistic model, its effectiveness in image generation is actively studied these days.
1 code implementation • 22 Feb 2023 • Manuel Stoiber, Mariam Elsayed, Anne E. Reichert, Florian Steidle, Dongheui Lee, Rudolph Triebel
In this work, we develop a multi-modality tracker that fuses information from visual appearance and geometry to estimate object poses.
Ranked #1 on 6D Pose Estimation on YCB-Video
no code implementations • 16 Feb 2023 • Esteve Valls Mascaro, Shuo Ma, Hyemin Ahn, Dongheui Lee
In addition, our model is tested in conditions where the human motion is severely occluded, demonstrating its robustness in reconstructing and predicting 3D human motion in a highly noisy environment.
1 code implementation • 25 Jul 2022 • Esteve Valls Mascaro, Hyemin Ahn, Dongheui Lee
Our framework first extracts two level of human information over the N observed videos human actions through a Hierarchical Multi-task MLP Mixer (H3M).
Ranked #1 on Long Term Action Anticipation on Ego4D
no code implementations • 12 Jul 2022 • David Paulius, Alejandro Agostini, Dongheui Lee
We demonstrate our entire approach on long-horizon tasks in CoppeliaSim and show how learned action contexts can be extended to never-before-seen scenarios.
no code implementations • 1 Jun 2021 • David Paulius, Alejandro Agostini, Yu Sun, Dongheui Lee
Following work on joint object-action representations, the functional object-oriented network (FOON) was introduced as a knowledge graph representation for robots.
1 code implementation • ICCV 2021 • Hyemin Ahn, Dongheui Lee
In this paper, we propose Hierarchical Action Segmentation Refiner (HASR), which can refine temporal action segmentation results from various models by understanding the overall context of a given video in a hierarchical way.
Ranked #12 on Action Segmentation on 50 Salads
no code implementations • 16 Dec 2020 • Hyemin Ahn, Obin Kwon, Kyoungdo Kim, Jaeyeon Jeong, Howoong Jun, Hongjung Lee, Dongheui Lee, Songhwai Oh
We also suggest a relevant dataset and model which can be a baseline, and show that our model trained with the proposed dataset can also be applied to the real world based on the CycleGAN.
no code implementations • 16 Jul 2020 • Alejandro Agostini, Dongheui Lee
To tackle these limitations we propose an object-centered representation that permits characterizing a much wider set of possible changes in configuration spaces than the traditional observer perspective counterpart.
no code implementations • ECCV 2020 • 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, Yun-hui Liu, Adrian Spurr, Umar Iqbal, Pavlo Molchanov, Philippe Weinzaepfel, Romain Brégier, Grégory Rogez, Vincent Lepetit, Tae-Kyun Kim
To address these issues, we designed a public challenge (HANDS'19) to evaluate the abilities of current 3D hand pose estimators (HPEs) to interpolate and extrapolate the poses of a training set.
no code implementations • 21 Feb 2020 • Ziyuan Liu, Dongheui Lee, Wolfgang Sepp
In this paper, a motion capturing algorithm is proposed for upper body motion tracking.
no code implementations • 18 Jan 2020 • Pietro Falco, Shuang Lu, Ciro Natale, Salvatore Pirozzi, Dongheui Lee
In this work, we introduce the problem of cross-modal visuo-tactile object recognition with robotic active exploration.
no code implementations • 20 Nov 2019 • Pietro Falco, Abdallah Attawia, Matteo Saveriano, Dongheui Lee
This way, the occurrence of object slipping during the learning procedure, which we consider an irreversible event, is significantly reduced.
no code implementations • 20 Nov 2019 • Pietro Falco, Matteo Saveriano, Eka Gibran Hasany, Nicholas H. Kirk, Dongheui Lee
The second step enriches the descriptor considering minimum and maximum joint velocities and the correlations between the most informative joints.
no code implementations • CVPR 2019 • Shile Li, Dongheui Lee
In addition to the pose estimation task, the voting-based scheme can also provide point cloud segmentation result without ground-truth for segmentation.
no code implementations • 2 Jul 2018 • Jan Wöhlke, Shile Li, Dongheui Lee
In this work, we extend the kinematic layer to make the hand shape parameters learnable.
1 code implementation • CVPR 2018 • Shanxin Yuan, Guillermo Garcia-Hernando, Bjorn Stenger, Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee, Pavlo Molchanov, Jan Kautz, Sina Honari, Liuhao Ge, Junsong Yuan, Xinghao Chen, Guijin Wang, Fan Yang, Kai Akiyama, Yang Wu, Qingfu Wan, Meysam Madadi, Sergio Escalera, Shile Li, Dongheui Lee, Iason Oikonomidis, Antonis Argyros, Tae-Kyun Kim
Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018
Ranked #5 on Hand Pose Estimation on HANDS 2017
no code implementations • 28 Sep 2015 • Simon Kaltenbacher, Nicholas H. Kirk, Dongheui Lee
We prove the concept on human-written texts, and conjecture this work will reduce training data size of sequential instructions, while preserving semantic relations, when gathering information from large remote sources.