1 code implementation • 4 Nov 2021 • Peter Schaldenbrand, Zhixuan Liu, Jean Oh
Generating images that fit a given text description using machine learning has improved greatly with the release of technologies such as the CLIP image-text encoder model; however, current methods lack artistic control of the style of image to be generated.
1 code implementation • 24 Feb 2022 • Peter Schaldenbrand, Zhixuan Liu, Jean Oh
Generating images that fit a given text description using machine learning has improved greatly with the release of technologies such as the CLIP image-text encoder model; however, current methods lack artistic control of the style of image to be generated.
2 code implementations • 12 Oct 2017 • Anirudh Vemula, Katharina Muelling, Jean Oh
In this work, we propose Social Attention, a novel trajectory prediction model that captures the relative importance of each person when navigating in the crowd, irrespective of their proximity.
1 code implementation • ICCV 2023 • Inhwan Bae, Jean Oh, Hae-Gon Jeon
In this paper, we present EigenTrajectory ($\mathbb{ET}$), a trajectory prediction approach that uses a novel trajectory descriptor to form a compact space, known here as $\mathbb{ET}$ space, in place of Euclidean space, for representing pedestrian movements.
1 code implementation • 9 Feb 2023 • Vihaan Misra, Peter Schaldenbrand, Jean Oh
For speech, we decouple speech into its transcribed text and the tone of the speech.
1 code implementation • 30 Mar 2023 • Ukcheol Shin, Kyunghyun Lee, In So Kweon, Jean Oh
Also, the proposed self-distillation loss encourages the network to extract complementary and meaningful representations from a single modality or complementary masked modalities.
Ranked #2 on Thermal Image Segmentation on MFN Dataset
2 code implementations • 30 Nov 2020 • Manoj Bhat, Jonathan Francis, Jean Oh
Effective feature-extraction is critical to models' contextual understanding, particularly for applications to robotics and autonomous driving, such as multimodal trajectory prediction.
1 code implementation • 23 Oct 2022 • Peter Schaldenbrand, Zhixuan Liu, Jean Oh
We introduce an approach to generating videos based on a series of given language descriptions.
1 code implementation • 22 May 2016 • Anirudh Vemula, Katharina Muelling, Jean Oh
In this paper, we apply the idea of adaptive dimensionality to speed up path planning in dynamic environments for a robot with no assumptions on its dynamic model.
Robotics
1 code implementation • 18 Dec 2020 • Peter Schaldenbrand, Jean Oh
The objective of most Reinforcement Learning painting agents is to minimize the loss between a target image and the paint canvas.
1 code implementation • 22 Sep 2022 • Benjamin Stoler, Meghdeep Jana, Soonmin Hwang, Jean Oh
To support first-person view trajectory prediction research, we present T2FPV, a method for constructing high-fidelity first-person view (FPV) datasets given a real-world, top-down trajectory dataset; we showcase our approach on the ETH/UCY pedestrian dataset to generate the egocentric visual data of all interacting pedestrians, creating the T2FPV-ETH dataset.
1 code implementation • 7 Jul 2020 • Ardavan Bidgoli, Manuel Ladron De Guevara, Cinnie Hsiung, Jean Oh, Eunsu Kang
We propose a method to integrate an artistic style to the brushstrokes and the painting process through collaboration with a human artist.
1 code implementation • 28 Jan 2023 • Zhixuan Liu, Youeun Shin, Beverley-Claire Okogwu, Youngsik Yun, Lia Coleman, Peter Schaldenbrand, Jihie Kim, Jean Oh
It has been shown that accurate representation in media improves the well-being of the people who consume it.
Cultural Vocal Bursts Intensity Prediction Image Generation +3
no code implementations • 8 Sep 2016 • Junjie Hu, Jean Oh, Anatole Gershman
Robotic commands in natural language usually contain various spatial descriptions that are semantically similar but syntactically different.
no code implementations • 15 Oct 2019 • Jean Oh, Martial Hebert, Hae-Gon Jeon, Xavier Perez, Chia Dai, Yeeho Song
One of the key challenges in the semantic mapping problem in postdisaster environments is how to analyze a large amount of data efficiently with minimal supervision.
no code implementations • 27 Nov 2019 • Xinjie Yao, Ji Zhang, Jean Oh
The underlying system incorporates a deep neural network to track social groups and join the flow of a social group in facilitating the navigation.
1 code implementation • LREC 2020 • Tzu-Hsiang Lin, Alexander Rudnicky, Trung Bui, Doo Soon Kim, Jean Oh
Our system grounds language on the level of edit operations, and suggests options for a user to choose from.
no code implementations • 16 Feb 2020 • Tzu-Hsiang Lin, Trung Bui, Doo Soon Kim, Jean Oh
In this paper, we present a multimodal dialogue system for Conversational Image Editing.
no code implementations • 2 Jul 2020 • Dapeng Zhao, Jean Oh
We propose a Convolutional Neural Network-based approach to learn, detect, and extract patterns in sequential trajectory data, known here as Social Pattern Extraction Convolution (Social-PEC).
no code implementations • 10 Jul 2020 • Junjiao Tian, Jean Oh
In image captioning where fluency is an important factor in evaluation, e. g., $n$-gram metrics, sequential models are commonly used; however, sequential models generally result in overgeneralized expressions that lack the details that may be present in an input image.
no code implementations • 25 Jan 2021 • Hyeonwoo Yu, Jean Oh
In this context, we propose a method for imputation of latent variables whose elements are partially lost.
no code implementations • 25 Jan 2021 • Hyeonwoo Yu, Jean Oh
Given a 2D Bounding Box (BBox) and object parameters, a 3D distance to the object can be calculated directly using 3D reprojection; however, such methods are prone to significant errors because an error from the 2D detection can be amplified in 3D.
no code implementations • 12 Apr 2021 • Fei Lu, Hyeonwoo Yu, Jean Oh
The advent of deep learning has brought an impressive advance to monocular depth estimation, e. g., supervised monocular depth estimation has been thoroughly investigated.
no code implementations • 14 Apr 2021 • Hyeonwoo Yu, Jean Oh
Therefore, we propose a strategy to exploit multipleobservations of the object in the image sequence in orderto surpass the self-performance: first, the landmarks for theglobal object map are estimated through network predic-tion and data association, and the corrected annotation fora single frame is obtained.
no code implementations • 21 May 2021 • Matthew R. Walter, Siddharth Patki, Andrea F. Daniele, Ethan Fahnestock, Felix Duvallet, Sachithra Hemachandra, Jean Oh, Anthony Stentz, Nicholas Roy, Thomas M. Howard
This progress now creates an opportunity for robots to operate not only in isolation, but also with and alongside humans in our complex environments.
no code implementations • 26 Jun 2021 • Jonathan Francis, Nariaki Kitamura, Felix Labelle, Xiaopeng Lu, Ingrid Navarro, Jean Oh
Recent advances in the areas of multimodal machine learning and artificial intelligence (AI) have led to the development of challenging tasks at the intersection of Computer Vision, Natural Language Processing, and Embodied AI.
no code implementations • 20 Aug 2021 • Xiaopeng Lu, Zhen Fan, Yansen Wang, Jean Oh, Carolyn P. Rose
LOGOS leverages two grounding tasks to better localize the key information of the image, utilizes scene text clustering to group individual OCR tokens, and learns to select the best answer from different sources of OCR (Optical Character Recognition) texts.
no code implementations • 29 Sep 2021 • Rajshekhar Das, Jonathan Francis, Sanket Vaibhav Mehta, Jean Oh, Emma Strubell, Jose Moura
Crucially, the objectness constraint is agnostic to the ground-truth semantic segmentation labels and, therefore, remains appropriate for unsupervised adaptation settings.
no code implementations • 29 Sep 2021 • Tanmay Shankar, Yixin Lin, Aravind Rajeswaran, Vikash Kumar, Stuart Anderson, Jean Oh
In this paper, we explore how we can endow robots with the ability to learn correspondences between their own skills, and those of morphologically different robots in different domains, in an entirely unsupervised manner.
no code implementations • 14 Oct 2021 • Bingqing Chen, Jonathan Francis, Jean Oh, Eric Nyberg, Sylvia L. Herbert
Given the nature of the task, autonomous agents need to be able to 1) identify and avoid unsafe scenarios under the complex vehicle dynamics, and 2) make sub-second decision in a fast-changing environment.
no code implementations • 5 May 2022 • Jonathan Francis, Bingqing Chen, Siddha Ganju, Sidharth Kathpal, Jyotish Poonganam, Ayush Shivani, Vrushank Vyas, Sahika Genc, Ivan Zhukov, Max Kumskoy, Anirudh Koul, Jean Oh, Eric Nyberg
In the first stage of the challenge, we evaluate an autonomous agent's ability to drive as fast as possible, while adhering to safety constraints.
no code implementations • 29 Jul 2022 • Xinjie Yao, Ji Zhang, Jean Oh
Under shared autonomy, wheelchair users expect vehicles to provide safe and comfortable rides while following users high-level navigation plans.
no code implementations • 16 Dec 2022 • Jonathan Francis, Bingqing Chen, Weiran Yao, Eric Nyberg, Jean Oh
The feasibility of collecting a large amount of expert demonstrations has inspired growing research interests in learning-to-drive settings, where models learn by imitating the driving behaviour from experts.
no code implementations • 21 Dec 2022 • Gyan Tatiya, Jonathan Francis, Luca Bondi, Ingrid Navarro, Eric Nyberg, Jivko Sinapov, Jean Oh
We also define a new audio-visual navigation sub-task, where agents are evaluated on novel sounding objects, as opposed to unheard clips of known objects.
no code implementations • 4 Apr 2023 • Ingrid Navarro, Jay Patrikar, Joao P. A. Dantas, Rohan Baijal, Ian Higgins, Sebastian Scherer, Jean Oh
In this work, we propose Social Robot Tree Search (SoRTS), an algorithm for the safe navigation of mobile robots in social domains.
no code implementations • 5 Apr 2023 • Jonathan Francis, Nariaki Kitamura, Felix Labelle, Xiaopeng Lu, Ingrid Navarro, Jean Oh
Recent advances in the areas of Multimodal Machine Learning and Artificial Intelligence (AI) have led to the development of challenging tasks at the intersection of Computer Vision, Natural Language Processing, and Robotics.
no code implementations • 29 Apr 2023 • Rajshekhar Das, Jonathan Francis, Sanket Vaibhav Mehta, Jean Oh, Emma Strubell, Jose Moura
Self-training based on pseudo-labels has emerged as a dominant approach for addressing conditional distribution shifts in unsupervised domain adaptation (UDA) for semantic segmentation problems.
no code implementations • 9 May 2023 • Xin Shen, Kyungdon Joo, Jean Oh
We propose an end-to-end deep learning approach to rectify fisheye images and simultaneously calibrate camera intrinsic and distortion parameters.
no code implementations • 16 Jan 2024 • Zhixuan Liu, Peter Schaldenbrand, Beverley-Claire Okogwu, Wenxuan Peng, Youngsik Yun, Andrew Hundt, Jihie Kim, Jean Oh
Accurate representation in media is known to improve the well-being of the people who consume it.
no code implementations • 27 Mar 2024 • Yuning Wu, Jiaying Wei, Jean Oh, Daniel Cardoso Llach
In the dynamic construction industry, traditional robotic integration has primarily focused on automating specific tasks, often overlooking the complexity and variability of human aspects in construction workflows.