b'Donghyun Kim'

research

∙ 09/16/2023

Universal Metric Learning with Parameter-Efficient Transfer Learning

A common practice in metric learning is to train and test an embedding m...

0 Sungyeon Kim, et al. ∙

research

∙ 06/01/2023

Task Relation-aware Continual User Representation Learning

User modeling, which learns to represent users into a low-dimensional re...

0 Sein Kim, et al. ∙

research

∙ 05/31/2023

Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models

Vision and Language (VL) models offer an effective method for aligning r...

3 Sivan Doveh, et al. ∙

research

∙ 05/18/2023

Learning low-dimensional dynamics from whole-brain data improves task capture

The neural dynamics underlying brain activity are critical to understand...

0 Eloy Geenjaar, et al. ∙

research

∙ 05/15/2023

Event Camera-based Visual Odometry for Dynamic Motion Tracking of a Legged Robot Using Adaptive Time Surface

Our paper proposes a direct sparse visual odometry method that combines ...

0 Shifan Zhu, et al. ∙

research

∙ 03/30/2023

Going Beyond Nouns With Vision Language Models Using Synthetic Data

Large-scale pre-trained Vision Language (VL) models have shown remar...

0 Paola Cascante-Bonilla, et al. ∙

research

∙ 03/26/2023

VisDA 2022 Challenge: Domain Adaptation for Industrial Waste Sorting

Label-efficient and reliable semantic segmentation is essential for many...

0 Dina Bashkirova, et al. ∙

research

∙ 03/26/2023

Mind the Backbone: Minimizing Backbone Distortion for Robust Object Detection

Building object detectors that are robust to domain shifts is critical f...

0 Kuniaki Saito, et al. ∙

research

∙ 01/17/2023

YeLan: Event Camera-Based 3D Human Pose Estimation for Technology-Mediated Dancing in Challenging Environments with Comprehensive Motion-to-Event Simulator

As a beloved sport worldwide, dancing is getting integrated into traditi...

0 Zhongyang Zhang, et al. ∙

research

∙ 11/27/2022

Exploring Consistency in Cross-Domain Transformer for Domain Adaptive Semantic Segmentation

While transformers have greatly boosted performance in semantic segmenta...

0 Kaihong Wang, et al. ∙

research

∙ 11/23/2022

CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning

Computer vision models suffer from a phenomenon known as catastrophic fo...

0 James Seale Smith, et al. ∙

research

∙ 11/21/2022

Teaching Structured Vision Language Concepts to Vision Language Models

Vision and Language (VL) models have demonstrated remarkable zero-shot p...

11 Sivan Doveh, et al. ∙

research

∙ 11/17/2022

ConStruct-VL: Data-Free Continual Structured VL Concepts Learning

Recently, large-scale pre-trained Vision-and-Language (VL) foundation mo...

0 James Seale Smith, et al. ∙

research

∙ 11/07/2022

Technical Report on Web-based Visual Corpus Construction for Visual Document Understanding

We present a dataset generator engine named Web-based Visual Corpus Buil...

0 Donghyun Kim, et al. ∙

research

∙ 10/28/2022

Grafting Vision Transformers

Vision Transformers (ViTs) have recently become the state-of-the-art acr...

0 Jongwoo Park, et al. ∙

research

∙ 10/24/2022

System Configuration and Navigation of a Guide Dog Robot: Toward Animal Guide Dog-Level Guiding Work

A robot guide dog has compelling advantages over animal guide dogs for i...

0 Hochul Hwang, et al. ∙

research

∙ 10/07/2022

Integration of Riemannian Motion Policy and Whole-Body Control for Dynamic Legged Locomotion

In this paper, we present a novel Riemannian Motion Policy (RMP)flow-bas...

0 Daniel Marew, et al. ∙

research

∙ 05/06/2022

Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between Utterances

Each utterance in multi-turn empathetic dialogues has features such as e...

0 Wongyu Kim, et al. ∙

research

∙ 04/25/2022

Temporal Relevance Analysis for Video Action Models

In this paper, we provide a deep analysis of temporal modeling for actio...

0 Quanfu Fan, et al. ∙

research

∙ 04/01/2022

A Unified Framework for Domain Adaptive Pose Estimation

While pose estimation is an important computer vision task, it requires ...

0 Donghyun Kim, et al. ∙

research

∙ 03/22/2022

A Broad Study of Pre-training for Domain Generalization and Adaptation

Deep models must learn robust and transferable representations in order ...

0 Donghyun Kim, et al. ∙

research

∙ 12/28/2021

Robust Convergence in Federated Learning through Label-wise Clustering

Non-IID dataset and heterogeneous environment of the local clients are r...

1 Hunmin Lee, et al. ∙

research

∙ 10/28/2021

Learning to Jump from Pixels

Today's robotic quadruped systems can robustly walk over a diverse range...

15 Gabriel B. Margolis, et al. ∙

research

∙ 10/06/2021

Real-time Optimal Landing Control of the MIT Mini Cheetah

Quadrupedal landing is a complex process involving large impacts, elabor...

0 Se Hwan Jeon, et al. ∙

research

∙ 08/26/2021

Learning Cross-modal Contrastive Features for Video Domain Adaptation

Learning transferable and domain adaptive feature representations from v...

0 Donghyun Kim, et al. ∙

research

∙ 08/24/2021

Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density

Unsupervised domain adaptation (UDA) methods can dramatically improve ge...

0 Kuniaki Saito, et al. ∙

research

∙ 08/10/2021

BROS: A Layout-Aware Pre-trained Language Model for Understanding Documents

Understanding documents from their visual snapshots is an emerging probl...

0 Teakgyu Hong, et al. ∙

research

∙ 07/23/2021

VisDA-2021 Competition Universal Domain Adaptation to Improve Performance on Out-of-Distribution Data

Progress in machine learning is typically measured by training and testi...

0 Dina Bashkirova, et al. ∙

research

∙ 07/21/2021

CogME: A Novel Evaluation Metric for Video Understanding Intelligence

Developing video understanding intelligence is quite challenging because...

14 Minjung Shin, et al. ∙

research

∙ 05/28/2021

OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers

Semi-supervised learning (SSL) is an effective means to leverage unlabel...

0 Kuniaki Saito, et al. ∙

research

∙ 05/11/2021

Knowledge Transfer across Imaging Modalities Via Simultaneous Learning of Adaptive Autoencoders for High-Fidelity Mobile Robot Vision

Enabling mobile robots for solving challenging and diverse shape, textur...

0 Md Mahmudur Rahman, et al. ∙

research

∙ 04/19/2021

The MIT Humanoid Robot: Design, Motion Planning, and Control For Acrobatic Behaviors

Demonstrating acrobatic behavior of a humanoid robot such as flips and s...

0 Matthew Chignoli, et al. ∙

research

∙ 01/27/2021

Predicting Participation in Cancer Screening Programs with Machine Learning

In this paper, we present machine learning models based on random forest...

0 Donghyun Kim, et al. ∙

research

∙ 08/03/2020

Sharing Nim and Enumeration of Nim Characteristics

In this paper, we introduce and examine a variant of the game of Nim (Sh...

0 Donghyun Kim, et al. ∙

research

∙ 08/01/2020

Self-supervised Visual Attribute Learning for Fashion Compatibility

Many self-supervised learning (SSL) methods have been successful in lear...

6 Donghyun Kim, et al. ∙

research

∙ 06/07/2020

Unsupervised Differentiable Multi-aspect Network Embedding

Network embedding is an influential graph mining technique for represent...

2 Chanyoung Park, et al. ∙

research

∙ 04/09/2020

Learning to Scale Multilingual Representations for Vision-Language Tasks

Current multilingual vision-language models either require a large numbe...

7 Andrea Burns, et al. ∙

research

∙ 03/18/2020

Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labels

Existing unsupervised domain adaptation methods aim to transfer knowledg...

5 Donghyun Kim, et al. ∙

research

∙ 02/19/2020

Universal Domain Adaptation through Self Supervision

Unsupervised domain adaptation methods traditionally assume that all sou...

15 Kuniaki Saito, et al. ∙

research

∙ 02/18/2020

Multi-Task Learning from Videos via Efficient Inter-Frame Attention

Prior work in multi-task learning has mainly focused on predictions on a...

28 Donghyun Kim, et al. ∙

research

∙ 11/15/2019

Unsupervised Attributed Multiplex Network Embedding

Nodes in a multiplex network are connected by multiple types of relation...

0 Chanyoung Park, et al. ∙

research

∙ 09/14/2019

Highly Dynamic Quadruped Locomotion via Whole-Body Impulse Control and Model Predictive Control

Dynamic legged locomotion is a challenging topic because of the lack of ...

0 Donghyun Kim, et al. ∙

research

∙ 09/08/2019

MULE: Multimodal Universal Language Embedding

Existing vision-language methods typically support two languages at a ti...

4 Donghyun Kim, et al. ∙

research

∙ 06/10/2019

Control of A High Performance Bipedal Robot using Viscoelastic Liquid Cooled Actuators

This paper describes the control, and evaluation of a new human-scaled b...

0 Junhyeok Ahn, et al. ∙

research

∙ 06/05/2019

Multi-way Encoding for Robustness

Deep models are state-of-the-art for many computer vision tasks includin...

1 Donghyun Kim, et al. ∙

research

∙ 06/04/2019

Collaborative Translational Metric Learning

Recently, matrix factorization-based recommendation methods have been cr...

0 Chanyoung Park, et al. ∙

research

∙ 06/04/2019

Task-Guided Pair Embedding in Heterogeneous Network

Many real-world tasks solved by heterogeneous network embedding methods ...

0 Chanyoung Park, et al. ∙

research

∙ 04/13/2019

Semi-supervised Domain Adaptation via Minimax Entropy

Contemporary domain adaptation methods are very effective at aligning fe...

6 Kuniaki Saito, et al. ∙

research

∙ 03/31/2019

Conversation Model Fine-Tuning for Classifying Client Utterances in Counseling Dialogues

The recent surge of text-based online counseling applications enables us...

0 Sungjoon Park, et al. ∙

research

∙ 07/24/2018

A Hybrid of Deep Audio Feature and i-vector for Artist Recognition

Artist recognition is a task of modeling the artist's musical style. Thi...

0 Jiyoung Park, et al. ∙

Donghyun Kim

Featured Co-authors