1 code implementation • RecSys 2016 • Donghyun Kim, Chanyoung Park, Jinoh Oh, Sungyoung Lee, Hwanjo Y
However, due to the inherent limitation of the bag-of-words model, they have difficulties in effectively utilizing contextual information of the documents, which leads to shallow understanding of the documents.
no code implementations • 30 Mar 2017 • Donghyun Kim, Matthias Hernandez, Jongmoo Choi, Gerard Medioni
We also propose a 3D face augmentation technique which synthesizes a number of different facial expressions from a single 3D face scan.
no code implementations • 21 Jun 2017 • Chanyoung Park, Donghyun Kim, Min-Chul Yang, Jung-Tae Lee, Hwanjo Yu
We begin by formulating various model assumptions, each one assuming a different order of user preferences among purchased, clicked-but-not-purchased, and non-clicked items, to study the usefulness of leveraging click records.
1 code implementation • CVPR 2018 • Sarah Adel Bargal, Andrea Zunino, Donghyun Kim, Jianming Zhang, Vittorio Murino, Stan Sclaroff
Models are trained to caption or classify activity in videos, but little is known about the evidence used to make such decisions.
no code implementations • ICLR 2018 • Heechang Ryu, Donghyun Kim, Hayong Shin
For example, job dispatching in the manufacturing factory is a typical "Learning to Select" problem.
no code implementations • NAACL 2019 • Sungjoon Park, Donghyun Kim, Alice Oh
A dataset of those interactions can be used to learn to automatically classify the client utterances into categories that help counselors in diagnosing client status and predicting counseling outcome.
3 code implementations • ICCV 2019 • Kuniaki Saito, Donghyun Kim, Stan Sclaroff, Trevor Darrell, Kate Saenko
Contemporary domain adaptation methods are very effective at aligning feature distributions of source and target domains without any target supervision.
no code implementations • ICLR 2019 • Donghyun Kim, Sarah Adel Bargal, Jianming Zhang, Stan Sclaroff
Deep models are state-of-the-art for many computer vision tasks including image classification and object detection.
1 code implementation • 4 Jun 2019 • Chanyoung Park, Donghyun Kim, Qi Zhu, Jiawei Han, Hwanjo Yu
In this paper, we propose a novel task-guided pair embedding framework in heterogeneous network, called TaPEm, that directly models the relationship between a pair of nodes that are related to a specific task (e. g., paper-author relationship in author identification).
1 code implementation • 4 Jun 2019 • Chanyoung Park, Donghyun Kim, Xing Xie, Hwanjo Yu
We also conduct extensive qualitative evaluations on the translation vectors learned by our proposed method to ascertain the benefit of adopting the translation mechanism for implicit feedback-based recommendations.
Ranked #1 on Recommendation Systems on Declicious
no code implementations • 5 Jun 2019 • Donghyun Kim, Sarah Adel Bargal, Jianming Zhang, Stan Sclaroff
However, it has been shown that deep models are vulnerable to adversarial examples.
no code implementations • 8 Sep 2019 • Donghyun Kim, Kuniaki Saito, Kate Saenko, Stan Sclaroff, Bryan A. Plummer
In this paper, we present a modular approach which can easily be incorporated into existing vision-language methods in order to support many languages.
2 code implementations • 15 Nov 2019 • Chanyoung Park, Donghyun Kim, Jiawei Han, Hwanjo Yu
Even for those that consider the multiplexity of a network, they overlook node attributes, resort to node labels for training, and fail to model the global properties of a graph.
no code implementations • 18 Feb 2020 • Donghyun Kim, Tian Lan, Chuhang Zou, Ning Xu, Bryan A. Plummer, Stan Sclaroff, Jayan Eledath, Gerard Medioni
We embed the attention module in a ``slow-fast'' architecture, where the slower network runs on sparsely sampled keyframes and the light-weight shallow network runs on non-keyframes at a high frame rate.
1 code implementation • NeurIPS 2020 • Kuniaki Saito, Donghyun Kim, Stan Sclaroff, Kate Saenko
While some methods address target settings with either partial or open-set categories, they assume that the particular setting is known a priori.
no code implementations • 18 Mar 2020 • Donghyun Kim, Kuniaki Saito, Tae-Hyun Oh, Bryan A. Plummer, Stan Sclaroff, Kate Saenko
We show that when labeled source examples are limited, existing methods often fail to learn discriminative features applicable for both source and target domains.
no code implementations • ECCV 2020 • Andrea Burns, Donghyun Kim, Derry Wijaya, Kate Saenko, Bryan A. Plummer
Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added.
1 code implementation • 7 Jun 2020 • Chanyoung Park, Carl Yang, Qi Zhu, Donghyun Kim, Hwanjo Yu, Jiawei Han
To capture the multiple aspects of each node, existing studies mainly rely on offline graph clustering performed prior to the actual embedding, which results in the cluster membership of each node (i. e., node aspect distribution) fixed throughout training of the embedding model.
no code implementations • 1 Aug 2020 • Donghyun Kim, Kuniaki Saito, Samarth Mishra, Stan Sclaroff, Kate Saenko, Bryan A Plummer
Our approach consists of three self-supervised tasks designed to capture different concepts that are neglected in prior work that we can select from depending on the needs of our downstream tasks.
no code implementations • ICCV 2021 • Donghyun Kim, Kuniaki Saito, Tae-Hyun Oh, Bryan A. Plummer, Stan Sclaroff, Kate Saenko
We present a two-stage pre-training approach that improves the generalization ability of standard single-domain pre-training.
no code implementations • 1 Jan 2021 • Teakgyu Hong, Donghyun Kim, Mingi Ji, Wonseok Hwang, Daehyun Nam, Sungrae Park
Although the recent advance in OCR enables the accurate extraction of text segments, it is still challenging to extract key information from documents due to the diversity of layouts.
no code implementations • 27 Jan 2021 • Donghyun Kim
In this paper, we present machine learning models based on random forest classifiers, support vector machines, gradient boosted decision trees, and artificial neural networks to predict participation in cancer screening programs in South Korea.
1 code implementation • 28 May 2021 • Kuniaki Saito, Donghyun Kim, Kate Saenko
OpenMatch achieves state-of-the-art performance on three datasets, and even outperforms a fully supervised model in detecting outliers unseen in unlabeled data on CIFAR10.
no code implementations • 21 Jul 2021 • Minjung Shin, Jeonghoon Kim, SeongHo Choi, Yu-Jung Heo, Donghyun Kim, Minsu Lee, Byoung-Tak Zhang, Jeh-Kwang Ryu
Then we propose a top-down evaluation system for VideoQA, based on the cognitive process of humans and story elements: Cognitive Modules for Evaluation (CogME).
1 code implementation • 23 Jul 2021 • Dina Bashkirova, Dan Hendrycks, Donghyun Kim, Samarth Mishra, Kate Saenko, Kuniaki Saito, Piotr Teterwak, Ben Usman
Progress in machine learning is typically measured by training and testing a model on the same distribution of data, i. e., the same domain.
1 code implementation • 10 Aug 2021 • Teakgyu Hong, Donghyun Kim, Mingi Ji, Wonseok Hwang, Daehyun Nam, Sungrae Park
On the other hand, this paper tackles the problem by going back to the basic: effective combination of text and layout.
Ranked #5 on Relation Extraction on FUNSD
2 code implementations • ICCV 2021 • Kuniaki Saito, Donghyun Kim, Piotr Teterwak, Stan Sclaroff, Trevor Darrell, Kate Saenko
Unsupervised domain adaptation (UDA) methods can dramatically improve generalization on unlabeled target domains.
no code implementations • ICCV 2021 • Donghyun Kim, Yi-Hsuan Tsai, Bingbing Zhuang, Xiang Yu, Stan Sclaroff, Kate Saenko, Manmohan Chandraker
Learning transferable and domain adaptive feature representations from videos is important for video-relevant tasks such as action recognition.
1 code implementation • NeurIPS 2021 • Kuniaki Saito, Donghyun Kim, Kate Saenko
\ours achieves state-of-the-art performance on three datasets, and even outperforms a fully supervised model in detecting outliers unseen in unlabeled data on CIFAR10.
no code implementations • 28 Dec 2021 • Hunmin Lee, Yueyang Liu, Donghyun Kim, Yingshu Li
Non-IID dataset and heterogeneous environment of the local clients are regarded as a major issue in Federated Learning (FL), causing a downturn in the convergence without achieving satisfactory performance.
1 code implementation • 22 Mar 2022 • Donghyun Kim, Kaihong Wang, Stan Sclaroff, Kate Saenko
In this paper, we provide a broad study and in-depth analysis of pre-training for domain adaptation and generalization, namely: network architectures, size, pre-training loss, and datasets.
1 code implementation • 1 Apr 2022 • Donghyun Kim, Kaihong Wang, Kate Saenko, Margrit Betke, Stan Sclaroff
In this paper, we investigate the problem of domain adaptive 2D pose estimation that transfers knowledge learned on a synthetic source domain to a target domain without supervision.
no code implementations • 25 Apr 2022 • Quanfu Fan, Donghyun Kim, Chun-Fu, Chen, Stan Sclaroff, Kate Saenko, Sarah Adel Bargal
In this paper, we provide a deep analysis of temporal modeling for action recognition, an important but underexplored problem in the literature.
no code implementations • NAACL 2022 • Wongyu Kim, Youbin Ahn, Donghyun Kim, Kyong-Ho Lee
To solve the above issue, we propose a novel approach of recognizing feature transitions between utterances, which helps understand the dialogue flow and better grasp the features of utterance that needs attention.
no code implementations • 24 Oct 2022 • Hochul Hwang, Tim Xia, Ibrahima Keita, Ken Suzuki, Joydeep Biswas, Sunghoon I. Lee, Donghyun Kim
A robot guide dog has compelling advantages over animal guide dogs for its cost-effectiveness, potential for mass production, and low maintenance burden.
no code implementations • 28 Oct 2022 • Jongwoo Park, Kumara Kahatapitiya, Donghyun Kim, Shivchander Sudalairaj, Quanfu Fan, Michael S. Ryoo
In this paper, we present a simple and efficient add-on component (termed GrafT) that considers global dependencies and multi-scale information throughout the network, in both high- and low-resolution features alike.
1 code implementation • 7 Nov 2022 • Donghyun Kim, Teakgyu Hong, Moonbin Yim, Yoonsik Kim, Geewook Kim
In recent years, research on visual document understanding (VDU) has grown significantly, with a particular emphasis on the development of self-supervised learning methods.
document understanding Optical Character Recognition (OCR) +1
1 code implementation • CVPR 2023 • James Seale Smith, Paola Cascante-Bonilla, Assaf Arbelle, Donghyun Kim, Rameswar Panda, David Cox, Diyi Yang, Zsolt Kira, Rogerio Feris, Leonid Karlinsky
This leads to reasoning mistakes, which need to be corrected as they occur by teaching VL models the missing SVLC skills; often this must be done using private data where the issue was found, which naturally leads to a data-free continual (no task-id) VL learning setting.
1 code implementation • 21 Nov 2022 • Sivan Doveh, Assaf Arbelle, Sivan Harary, Rameswar Panda, Roei Herzig, Eli Schwartz, Donghyun Kim, Raja Giryes, Rogerio Feris, Shimon Ullman, Leonid Karlinsky
Vision and Language (VL) models have demonstrated remarkable zero-shot performance in a variety of tasks.
1 code implementation • CVPR 2023 • James Seale Smith, Leonid Karlinsky, Vyshnavi Gutta, Paola Cascante-Bonilla, Donghyun Kim, Assaf Arbelle, Rameswar Panda, Rogerio Feris, Zsolt Kira
Our experiments show that we outperform the current SOTA method DualPrompt on established benchmarks by as much as 4. 5% in average final accuracy.
1 code implementation • 27 Nov 2022 • Kaihong Wang, Donghyun Kim, Rogerio Feris, Kate Saenko, Margrit Betke
We propose to perform adaptation on attention maps with cross-domain attention layers that share features between the source and the target domains.
1 code implementation • ICCV 2023 • Kaihong Wang, Donghyun Kim, Rogerio Feris, Margrit Betke
While transformers have greatly boosted performance in semantic segmentation, domain adaptive transformers are not yet well explored.
no code implementations • 17 Jan 2023 • Zhongyang Zhang, Kaidong Chai, Haowen Yu, Ramzi Majaj, Francesca Walsh, Edward Wang, Upal Mahbub, Hava Siegelmann, Donghyun Kim, Tauhidur Rahman
As a beloved sport worldwide, dancing is getting integrated into traditional and virtual reality-based gaming platforms nowadays.
1 code implementation • 26 Mar 2023 • Kuniaki Saito, Donghyun Kim, Piotr Teterwak, Rogerio Feris, Kate Saenko
We propose to use Relative Gradient Norm (RGN) as a way to measure the vulnerability of a backbone to feature distortion, and show that high RGN is indeed correlated with lower OOD performance.
1 code implementation • 26 Mar 2023 • Dina Bashkirova, Samarth Mishra, Diala Lteif, Piotr Teterwak, Donghyun Kim, Fadi Alladkani, James Akl, Berk Calli, Sarah Adel Bargal, Kate Saenko, Daehan Kim, Minseok Seo, YoungJin Jeon, Dong-Geol Choi, Shahaf Ettedgui, Raja Giryes, Shady Abu-Hussein, Binhui Xie, Shuang Li
To test the abilities of computer vision models on this task, we present the VisDA 2022 Challenge on Domain Adaptation for Industrial Waste Sorting.
1 code implementation • ICCV 2023 • Paola Cascante-Bonilla, Khaled Shehada, James Seale Smith, Sivan Doveh, Donghyun Kim, Rameswar Panda, Gül Varol, Aude Oliva, Vicente Ordonez, Rogerio Feris, Leonid Karlinsky
We contribute Synthetic Visual Concepts (SyViC) - a million-scale synthetic dataset and data generation codebase allowing to generate additional suitable data to improve VLC understanding and compositional reasoning of VL models.
Ranked #68 on Visual Reasoning on Winoground
no code implementations • 15 May 2023 • Shifan Zhu, Zhipeng Tang, Michael Yang, Erik Learned-Miller, Donghyun Kim
Our paper proposes a direct sparse visual odometry method that combines event and RGB-D data to estimate the pose of agile-legged robots during dynamic locomotion and acrobatic behaviors.
no code implementations • 18 May 2023 • Eloy Geenjaar, Donghyun Kim, Riyasat Ohib, Marlena Duda, Amrit Kashyap, Sergey Plis, Vince Calhoun
We evaluate our approach on various task-fMRI datasets, including motor, working memory, and relational processing tasks, and demonstrate that it outperforms widely used dimensionality reduction techniques in how well the latent timeseries relates to behavioral sub-tasks, such as left-hand or right-hand tapping.
1 code implementation • 1 Jun 2023 • Sein Kim, Namkyeong Lee, Donghyun Kim, MinChul Yang, Chanyoung Park
However, since learning task-specific user representations for every task is infeasible, recent studies introduce the concept of universal user representation, which is a more generalized representation of a user that is relevant to a variety of tasks.
no code implementations • 16 Sep 2023 • Sungyeon Kim, Donghyun Kim, Suha Kwak
In this regard, we introduce a novel metric learning paradigm, called Universal Metric Learning (UML), which learns a unified distance metric capable of capturing relations across multiple data distributions.
no code implementations • ICCV 2023 • Daehee Kim, Yoonsik Kim, Donghyun Kim, Yumin Lim, Geewook Kim, Taeho Kil
In this paper, we investigate effective pre-training tasks in the broader domains and also propose a novel pre-training method called SCOB that leverages character-wise supervised contrastive learning with online text rendering to effectively pre-train document and scene text domains by bridging the domain gap.
1 code implementation • 16 Oct 2023 • Kibum Kim, Kanghoon Yoon, Jaehyeong Jeon, Yeonjun In, Jinyoung Moon, Donghyun Kim, Chanyoung Park
Weakly-Supervised Scene Graph Generation (WSSGG) research has recently emerged as an alternative to the fully-supervised approach that heavily relies on costly annotations.
1 code implementation • NeurIPS 2023 • Howard Zhong, Samarth Mishra, Donghyun Kim, SouYoung Jin, Rameswar Panda, Hilde Kuehne, Leonid Karlinsky, Venkatesh Saligrama, Aude Oliva, Rogerio Feris
To this end, we present, for the first time, a benchmark that leverages real-world videos with humans removed and synthetic data containing virtual humans to pre-train a model.
no code implementations • 12 Dec 2023 • Jayeon Yoo, Dongkwan Lee, Inseop Chung, Donghyun Kim, Nojun Kwak
It is a well-known fact that the performance of deep learning models deteriorates when they encounter a distribution shift at test time.
no code implementations • 13 Dec 2023 • Divyanshu Saxena, Nihal Sharma, Donghyun Kim, Rohit Dwivedula, Jiayi Chen, Chenxi Yang, Sriram Ravula, Zichao Hu, Aditya Akella, Sebastian Angel, Joydeep Biswas, Swarat Chaudhuri, Isil Dillig, Alex Dimakis, P. Brighten Godfrey, Daehyeok Kim, Chris Rossbach, Gang Wang
This paper lays down the research agenda for a domain-specific foundation model for operating systems (OSes).
1 code implementation • 18 Jan 2024 • Kibum Kim, Kanghoon Yoon, Yeonjun In, Jinyoung Moon, Donghyun Kim, Chanyoung Park
To this end, we introduce a Self-Training framework for SGG (ST-SGG) that assigns pseudo-labels for unannotated triplets based on which the SGG models are trained.
no code implementations • 9 Feb 2024 • Hochul Hwang, Sunjae Kwon, Yekyung Kim, Donghyun Kim
Safely navigating street intersections is a complex challenge for blind and low-vision individuals, as it requires a nuanced understanding of the surrounding context - a task heavily reliant on visual cues.
no code implementations • 21 Feb 2024 • Zexue He, Leonid Karlinsky, Donghyun Kim, Julian McAuley, Dmitry Krotov, Rogerio Feris
Large Language Models (LLMs) struggle to handle long input sequences due to high memory and runtime costs.
no code implementations • 29 Feb 2024 • Young-Jin Park, Donghyun Kim, Frédéric Odermatt, Juho Lee, Kyung-Min Kim
Time series forecasting is one of the most essential and ubiquitous tasks in many business problems, including demand forecasting and logistics optimization.
no code implementations • 19 Mar 2024 • Seil Kang, Donghyun Kim, Junhyeok Kim, Hyo Kyung Lee, Seong Jae Hwang
(1) Previous methods solely use CXR reports, which are insufficient for comprehensive Visual Question Answering (VQA), especially when additional health-related data like medication history and prior diagnoses are needed.