Jonghyun Choi

Affiliations

Seoul National University

papers

964

total citations

papers (26)

Online Continual Learning on a Contaminated Data Stream With Blurry Task Boundaries

CVPR 2022arXiv

citations

Learning Architectures for Binary Networks

ECCV 2020arXiv

citations

Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents

ICCV 2023arXiv

citations

Factorizing Perception and Policy for Interactive Instruction Following

ICCV 2021arXiv

citations

Ask4Help: Learning to Leverage an Expert for Embodied Tasks

NEURIPS 2022arXiv

citations

Learning Equi-angular Representations for Online Continual Learning

CVPR 2024arXiv

citations

Attentive Fine-Grained Structured Sparsity for Image Restoration

CVPR 2022arXiv

citations

ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments

ECCV 2024arXiv

citations

Online Continual Learning on Hierarchical Label Expansion

ICCV 2023arXiv

citations

Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling

ICLR 2025arXiv

citations

Story Visualization by Online Text Augmentation with Context Memory

ICCV 2023arXiv

citations

MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity

AAAI 2025arXiv

citations

Multi-Modal Grounded Planning and Efficient Replanning for Learning Embodied Agents with a Few Examples

AAAI 2025arXiv

citations

Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning

CVPR 2022arXiv

citations

PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images

ICLR 2024arXiv

citations

Operator-Learning-Inspired Modeling of Neural Ordinary Differential Equations

AAAI 2024arXiv

citations

ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO

AAAI 2025arXiv

citations

Online Generic Event Boundary Detection

ICCV 2025arXiv

citations

DataFreeShield: Defending Adversarial Attacks without Training Data

ICML 2024arXiv

citations

DialNav: Multi-turn Dialog Navigation with a Remote Guide

ICCV 2025arXiv

citations

Stereo Depth From Events Cameras: Concentrate and Focus on the Future

CVPR 2022

citations

Event-Intensity Stereo: Estimating Depth by the Best of Both Worlds

ICCV 2021

citations

Jonghyun Choi

Affiliations

papers (26)

Rainbow Memory: Continual Learning With a Memory of Diverse Samples

Learning to Super Resolve Intensity Images From Events

Rethinking Deep Image Prior for Denoising

Zero-Shot Natural Language Video Localization

Online Continual Learning on a Contaminated Data Stream With Blurry Task Boundaries

Learning Architectures for Binary Networks

Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents

Factorizing Perception and Policy for Interactive Instruction Following

Ask4Help: Learning to Leverage an Expert for Embodied Tasks

Learning Equi-angular Representations for Online Continual Learning

Attentive Fine-Grained Structured Sparsity for Image Restoration

ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments

Online Continual Learning on Hierarchical Label Expansion

Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling

Story Visualization by Online Text Augmentation with Context Memory

MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity

Multi-Modal Grounded Planning and Efficient Replanning for Learning Embodied Agents with a Few Examples

Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning

PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images

Operator-Learning-Inspired Modeling of Neural Ordinary Differential Equations

ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO

Online Generic Event Boundary Detection

DataFreeShield: Defending Adversarial Attacks without Training Data

DialNav: Multi-turn Dialog Navigation with a Remote Guide

Stereo Depth From Events Cameras: Concentrate and Focus on the Future

Event-Intensity Stereo: Estimating Depth by the Best of Both Worlds

papers (26)

Rainbow Memory: Continual Learning With a Memory of Diverse Samples

Learning to Super Resolve Intensity Images From Events

Rethinking Deep Image Prior for Denoising

Zero-Shot Natural Language Video Localization

Online Continual Learning on a Contaminated Data Stream With Blurry Task Boundaries

Learning Architectures for Binary Networks

Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents

Factorizing Perception and Policy for Interactive Instruction Following

Ask4Help: Learning to Leverage an Expert for Embodied Tasks

Learning Equi-angular Representations for Online Continual Learning

Attentive Fine-Grained Structured Sparsity for Image Restoration

ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments

Online Continual Learning on Hierarchical Label Expansion

Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling

Story Visualization by Online Text Augmentation with Context Memory

MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity

Multi-Modal Grounded Planning and Efficient Replanning for Learning Embodied Agents with a Few Examples

Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning

PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images

Operator-Learning-Inspired Modeling of Neural Ordinary Differential Equations

ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO

Online Generic Event Boundary Detection

DataFreeShield: Defending Adversarial Attacks without Training Data

DialNav: Multi-turn Dialog Navigation with a Remote Guide

Stereo Depth From Events Cameras: Concentrate and Focus on the Future

Event-Intensity Stereo: Estimating Depth by the Best of Both Worlds