Donghyun Kim

Orcid: 0000-0002-7132-4454

Affiliations:

MIT-IBM Watson AI Lab
Boston University, USA (PhD 2022)

According to our database¹, Donghyun Kim authored at least 41 papers between 2016 and 2024.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Bibliography

2024

Too Many Frames, not all Useful: Efficient Strategies for Long-Form Video QA.

[BibT_eX]

[DOI]

CoRR, 2024

CAMELoT: Towards Large Language Models with Training-Free Consolidated Associative Memory.

[BibT_eX]

[DOI]

CoRR, 2024

Grafting Vision Transformers.

[BibT_eX]

[DOI]

Jongwoo Park

Kumara Kahatapitiya

Donghyun Kim

Shivchander Sudalairaj

Quanfu Fan

Michael S. Ryoo

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024

Adaptive Self-training Framework for Fine-grained Scene Graph Generation.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

LLM4SGG: Large Language Model for Weakly Supervised Scene Graph Generation.

[BibT_eX]

[DOI]

CoRR, 2023

Mind the Backbone: Minimizing Backbone Distortion for Robust Object Detection.

[BibT_eX]

[DOI]

CoRR, 2023

Learning Human Action Recognition Representations Without Real Humans.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

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

[BibT_eX]

[DOI]

Paola Cascante-Bonilla

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

CDAC: Cross-domain Attention Consistency in Transformer for Domain Adaptive Semantic Segmentation.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Going Beyond Nouns With Vision & Language Models Using Synthetic Data.

[BibT_eX]

[DOI]

Paola Cascante-Bonilla

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

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

[BibT_eX]

[DOI]

James Seale Smith

Leonid Karlinsky

Vyshnavi Gutta

Paola Cascante-Bonilla

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

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

[BibT_eX]

[DOI]

James Seale Smith

Paola Cascante-Bonilla

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

Learning generalizable and transferable representations across domains and modalities

[BibT_eX]

[DOI]

Donghyun Kim

PhD thesis, 2022

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

[BibT_eX]

[DOI]

CoRR, 2022

Teaching Structured Vision&Language Concepts to Vision&Language Models.

[BibT_eX]

[DOI]

CoRR, 2022

Temporal Relevance Analysis for Video Action Models.

[BibT_eX]

[DOI]

CoRR, 2022

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

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2022, 2022

A Unified Framework for Domain Adaptive Pose Estimation.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2022, 2022

2021

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

[BibT_eX]

[DOI]

CoRR, 2021

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

[BibT_eX]

[DOI]

Kuniaki Saito

Donghyun Kim

Kate Saenko

CoRR, 2021

OpenMatch: Open-Set Semi-supervised Learning with Open-set Consistency Regularization.

[BibT_eX]

[DOI]

Kuniaki Saito

Donghyun Kim

Kate Saenko

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

VisDA 2022 Challenge: Domain Adaptation for Industrial Waste Sorting.

[BibT_eX]

[DOI]

Proceedings of the NeurIPS 2022 Competition Track, 2021

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

[BibT_eX]

[DOI]

Chandramouli Rajagopalan

Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, 2021

Self-supervised Visual Attribute Learning for Fashion Compatibility.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2021

MILA: Multi-Task Learning from Videos via Efficient Inter-Frame Attention.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2021

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

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Learning Cross-Modal Contrastive Features for Video Domain Adaptation.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

CDS: Cross-Domain Self-supervised Pre-training.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

2020

Self-supervised Visual Attribute Learning for Fashion Compatibility.

[BibT_eX]

[DOI]

CoRR, 2020

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

[BibT_eX]

[DOI]

CoRR, 2020

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

[BibT_eX]

[DOI]

CoRR, 2020

Multi-way Encoding for Robustness.

[BibT_eX]

[DOI]

Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2020

Universal Domain Adaptation through Self Supervision.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Learning to Scale Multilingual Representations for Vision-Language Tasks.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

MULE: Multimodal Universal Language Embedding.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019

Semi-Supervised Domain Adaptation via Minimax Entropy.

[BibT_eX]

[DOI]

Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

2018

Excitation Backprop for RNNs.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

2017

Deep 3D face identification.

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE International Joint Conference on Biometrics, 2017

2016

Expression invariant 3D face modeling from an RGB-D video.

[BibT_eX]

[DOI]

Proceedings of the 23rd International Conference on Pattern Recognition, 2016

Accurate 3D face modeling and recognition from RGB-D stream in the presence of large pose changes.

[BibT_eX]

[DOI]

Proceedings of the 2016 IEEE International Conference on Image Processing, 2016

Donghyun Kim

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...