Dahun Kim

73 papers A* 20A 7B 1Journal 43Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
Taking Shortcuts for Categorical VQA Using Super Neurons.
CoRR
Pierre Musacchio, Jaeyi Jeong, Dahun Kim, Jaesik Park
2025 J jnl
Context-Adaptive Multi-Prompt Embedding with Large Language Models for Vision-Language Alignment.
CoRR
Dahun Kim, Anelia Angelova
2025 J jnl
EmbeddingGemma: Powerful and Lightweight Text Representations.
CoRR
Henrique Schechter Vera, Sahil Dua, Biao Zhang, Daniel Salz, Ryan Mullins, Sindhu Raghuram Panyam, Sara Smoot, Iftekhar Naim, Joe Zou, Feiyang Chen, Daniel Cer, Alice Lisak, Min Choi, Lucas Gonzalez, Omar Sanseviero, Glenn Cameron, Ian Ballantyne, Kat Black, Kaifeng Chen, Weiyi Wang, Zhe Li, Gus Martins, Jinhyuk Lee, Mark Sherwood, Ju-yeong Ji, Renjie Wu, Jingxiao Zheng, Jyotinder Singh, Abheesht Sharma, Divyashree Sreepathihalli, Aashi Jain, Adham Elarabawy, AJ Co, Andreas Doumanoglou, Babak Samari, Ben Hora, Brian Potetz, Dahun Kim, Enrique Alfonseca, Fedor Moiseev, Feng Han, Frank Palma Gomez, Gustavo Hernández Ábrego, Hesen Zhang, Hui Hui, Jay Han, Karan Gill, Ke Chen, Koert Chen, Madhuri Shanbhogue, Michael Boratko, Paul Suganthan, Sai Meher Karthik Duddu, Sandeep Mariserla, Setareh Ariafar, Shanfeng Zhang, Shijie Zhang, Simon Baumgartner, Sonam Goenka, Steve Qiu, Tanmaya Dabral, Trevor Walker, Vikram Rao, Waleed Khawaja, Wenlei Zhou, Xiaoqi Ren, Ye Xia, Yichang Chen, Yi-Ting Chen, Zhe Dong, Zhongli Ding, Francesco Visin, Gaël Liu, Jiageng Zhang, Kathleen Kenealy, Michelle Casbon, Ravin Kumar, Thomas Mesnard, Zach Gleicher, Cormac Brick, Olivier Lacombe, Adam Roberts, Qin Yin, Yun-Hsuan Sung, Raphael Hoffmann, Tris Warkentin, Armand Joulin, Tom Duerig, Mojtaba Seyedhosseini
2025 A conf
Learning Visual Grounding from Generative Vision and Language Model.
WACV
Shijie Wang, Dahun Kim, Ali Taalimi, Chen Sun, Weicheng Kuo
2025 J jnl
Time-Scaling State-Space Models for Dense Video Captioning.
CoRR
A. J. Piergiovanni, Ganesh Satish Mallya, Dahun Kim, Anelia Angelova
2025 A* conf
VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models.
CVPR
Dahun Kim, A. J. Piergiovanni, Ganesh Satish Mallya, Anelia Angelova
2025 J jnl
VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models.
CoRR
Dahun Kim, A. J. Piergiovanni, Ganesh Satish Mallya, Anelia Angelova
2025 J jnl
Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications.
CoRR
Ganesh Satish Mallya, Yotam Gigi, Dahun Kim, Maxim Neumann, Genady Beryozkin, Tomer Shekel, Anelia Angelova
2024 J jnl
Learning Visual Grounding from Generative Vision and Language Model.
CoRR
Shijie Wang, Dahun Kim, Ali Taalimi, Chen Sun, Weicheng Kuo
2024 A* conf
Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities.
CVPR
A. J. Piergiovanni, Isaac Noble, Dahun Kim, Michael S. Ryoo, Victor Gomes, Anelia Angelova
2024 J jnl
OmniBind: Teach to Build Unequal-Scale Modality Interaction for Omni-Bind of All.
CoRR
Yuanhuiyi Lyu, Xu Zheng, Dahun Kim, Lin Wang
2024 — conf
Region-Centric Image-Language Pretraining for Open-Vocabulary Detection.
ECCV (63)
Dahun Kim, Anelia Angelova, Weicheng Kuo
2024 J jnl
Textless Unit-to-Unit Training for Many-to-Many Multilingual Speech-to-Speech Translation.
IEEE ACM Trans. Audio Speech Lang. Process.
Minsu Kim, Jeongsoo Choi, Dahun Kim, Yong Man Ro
2024 J jnl
Uni-DVPS: Unified Model for Depth-Aware Video Panoptic Segmentation.
IEEE Robotics Autom. Lett.
Ji-Yeon Kim, Oh Hyun-Bin, Byung-Ki Kwon, Dahun Kim, Yongjin Kwon, Tae-Hyun Oh
2024 A conf
Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation.
WACV
Inkyu Shin, Dahun Kim, Qihang Yu, Jun Xie, Hong-Seok Kim, Bradley Green, In So Kweon, Kuk-Jin Yoon, Liang-Chieh Chen
2024 J jnl
Whats in a Video: Factorized Autoregressive Decoding for Online Dense Video Captioning.
CoRR
A. J. Piergiovanni, Dahun Kim, Michael S. Ryoo, Isaac Noble, Anelia Angelova
2023 A* conf
Contrastive Feature Masking Open-Vocabulary Vision Transformer.
ICCV
Dahun Kim, Anelia Angelova, Weicheng Kuo
2023 J jnl
Contrastive Feature Masking Open-Vocabulary Vision Transformer.
CoRR
Dahun Kim, Anelia Angelova, Weicheng Kuo
2023 J jnl
Detection-Oriented Image-Text Pretraining for Open-Vocabulary Detection.
CoRR
Dahun Kim, Anelia Angelova, Weicheng Kuo
2023 J jnl
MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks.
CoRR
Weicheng Kuo, A. J. Piergiovanni, Dahun Kim, Xiyang Luo, Benjamin Caine, Wei Li, Abhijit S. Ogale, Luowei Zhou, Andrew M. Dai, Zhifeng Chen, Claire Cui, Anelia Angelova
2023 J jnl
MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks.
Trans. Mach. Learn. Res.
Weicheng Kuo, A. J. Piergiovanni, Dahun Kim, Xiyang Luo, Benjamin Caine, Wei Li, Abhijit S. Ogale, Luowei Zhou, Andrew M. Dai, Zhifeng Chen, Claire Cui, Anelia Angelova
2023 J jnl
Many-to-Many Spoken Language Translation via Unified Speech and Text Representation Learning with Unit-to-Unit Translation.
CoRR
Minsu Kim, Jeongsoo Choi, Dahun Kim, Yong Man Ro
2023 B conf
Memory-Aware DVFS Governing Policy for Improved Energy-Saving in the Linux Kernel.
RTCSA
Philkyue Shin, Dahun Kim, Seongsoo Hong
2023 J jnl
Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities.
CoRR
A. J. Piergiovanni, Isaac Noble, Dahun Kim, Michael S. Ryoo, Victor Gomes, Anelia Angelova
2023 A* conf
Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modeling.
ICLR
Youngjoong Kwon, Dahun Kim, Duygu Ceylan, Henry Fuchs
2023 J jnl
Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modeling.
CoRR
Youngjoong Kwon, Dahun Kim, Duygu Ceylan, Henry Fuchs
2023 J jnl
RECLIP: Resource-efficient CLIP by Training with Small Images.
CoRR
Runze Li, Dahun Kim, Bir Bhanu, Weicheng Kuo
2023 J jnl
RECLIP: Resource-efficient CLIP by Training with Small Images.
Trans. Mach. Learn. Res.
Runze Li, Dahun Kim, Bir Bhanu, Weicheng Kuo
2023 A* conf
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers.
CVPR
Dahun Kim, Anelia Angelova, Weicheng Kuo
2023 J jnl
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers.
CoRR
Dahun Kim, Anelia Angelova, Weicheng Kuo
2023 J jnl
Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation.
CoRR
Inkyu Shin, Dahun Kim, Qihang Yu, Jun Xie, Hong-Seok Kim, Bradley Green, In So Kweon, Kuk-Jin Yoon, Liang-Chieh Chen
2022 A* conf
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation.
CVPR
Qihang Yu, Huiyu Wang, Dahun Kim, Siyuan Qiao, Maxwell D. Collins, Yukun Zhu, Hartwig Adam, Alan L. Yuille, Liang-Chieh Chen
2022 J jnl
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation.
CoRR
Qihang Yu, Huiyu Wang, Dahun Kim, Siyuan Qiao, Maxwell D. Collins, Yukun Zhu, Hartwig Adam, Alan L. Yuille, Liang-Chieh Chen
2022 J jnl
Dense Pixel-Level Interpretation of Dynamic Scenes With Video Panoptic Segmentation.
IEEE Trans. Image Process.
Dahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon
2022 J jnl
Learning Open-World Object Proposals Without Learning to Classify.
IEEE Robotics Autom. Lett.
Dahun Kim, Tsung-Yi Lin, Anelia Angelova, In So Kweon, Weicheng Kuo
2022 A conf
Tailor Me: An Editing Network for Fashion Attribute Shape Manipulation.
WACV
Youngjoong Kwon, Stefano Petrangeli, Dahun Kim, Haoliang Wang, Viswanathan Swaminathan, Henry Fuchs
2022 A* conf
TubeFormer-DeepLab: Video Mask Transformer.
CVPR
Dahun Kim, Jun Xie, Huiyu Wang, Siyuan Qiao, Qihang Yu, Hong-Seok Kim, Hartwig Adam, In So Kweon, Liang-Chieh Chen
2022 J jnl
TubeFormer-DeepLab: Video Mask Transformer.
CoRR
Dahun Kim, Jun Xie, Huiyu Wang, Siyuan Qiao, Qihang Yu, Hong-Seok Kim, Hartwig Adam, In-So Kweon, Liang-Chieh Chen
2021 J jnl
DeepLab2: A TensorFlow Library for Deep Labeling.
CoRR
Mark Weber, Huiyu Wang, Siyuan Qiao, Jun Xie, Maxwell D. Collins, Yukun Zhu, Liangzhe Yuan, Dahun Kim, Qihang Yu, Daniel Cremers, Laura Leal-Taixé, Alan L. Yuille, Florian Schroff, Hartwig Adam, Liang-Chieh Chen
2021 A conf
Global Context and Geometric Priors for Effective Non-Local Self-Attention.
BMVC
Sanghyun Woo, Dahun Kim, Joon-Young Lee, In So Kweon
2021 J jnl
Learning Open-World Object Proposals without Learning to Classify.
CoRR
Dahun Kim, Tsung-Yi Lin, Anelia Angelova, In So Kweon, Weicheng Kuo
2021 A* conf
Learning To Associate Every Segment for Video Panoptic Segmentation.
CVPR
Sanghyun Woo, Dahun Kim, Joon-Young Lee, In So Kweon
2021 J jnl
Learning to Associate Every Segment for Video Panoptic Segmentation.
CoRR
Sanghyun Woo, Dahun Kim, Joon-Young Lee, In So Kweon
2021 A* conf
Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering.
NeurIPS
Youngjoong Kwon, Dahun Kim, Duygu Ceylan, Henry Fuchs
2021 J jnl
Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering.
CoRR
Youngjoong Kwon, Dahun Kim, Duygu Ceylan, Henry Fuchs
2021 A conf
The Devil is in the Boundary: Exploiting Boundary Representation for Basis-based Instance Segmentation.
WACV
Myungchul Kim, Sanghyun Woo, Dahun Kim, In So Kweon
2020 A conf
Align-and-Attend Network for Globally and Locally Coherent Video Inpainting.
BMVC
Sanghyun Woo, Dahun Kim, Kwanyong Park, Joon-Young Lee, In So Kweon
2020 A* conf
Hide-and-Tell: Learning to Bridge Photo Streams for Visual Storytelling.
AAAI
Yunjae Jung, Dahun Kim, Sanghyun Woo, Kyungsu Kim, Sungjin Kim, In So Kweon
2020 J jnl
Hide-and-Tell: Learning to Bridge Photo Streams for Visual Storytelling.
CoRR
Yunjae Jung, Dahun Kim, Sanghyun Woo, Kyungsu Kim, Sungjin Kim, In So Kweon
2020 J jnl
Recurrent Temporal Aggregation Framework for Deep Video Inpainting.
IEEE Trans. Pattern Anal. Mach. Intell.
Dahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon
2020 A* conf
Rotationally-Consistent Novel View Synthesis for Humans.
ACM Multimedia
Youngjoong Kwon, Stefano Petrangeli, Dahun Kim, Haoliang Wang, Henry Fuchs, Viswanathan Swaminathan
2020 — conf
Rotationally-Temporally Consistent Novel View Synthesis of Human Performance Video.
ECCV (4)
Youngjoong Kwon, Stefano Petrangeli, Dahun Kim, Haoliang Wang, Eunbyung Park, Viswanathan Swaminathan, Henry Fuchs
2020 J jnl
The Devil is in the Boundary: Exploiting Boundary Representation for Basis-based Instance Segmentation.
CoRR
Myungchul Kim, Sanghyun Woo, Dahun Kim, In So Kweon
2020 A* conf
Video Panoptic Segmentation.
CVPR
Dahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon
2020 J jnl
Video Panoptic Segmentation.
CoRR
Dahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon
2019 J jnl
Align-and-Attend Network for Globally and Locally Coherent Video Inpainting.
CoRR
Sanghyun Woo, Dahun Kim, Kwanyong Park, Joon-Young Lee, In So Kweon
2019 A* conf
Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence.
CVPR
Dahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon
2019 J jnl
Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence.
CoRR
Dahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon
2019 A* conf
Deep Video Inpainting.
CVPR
Dahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon
2019 J jnl
Deep Video Inpainting.
CoRR
Dahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon
2019 A* conf
Discriminative Feature Learning for Unsupervised Video Summarization.
AAAI
Yunjae Jung, Donghyeon Cho, Dahun Kim, Sanghyun Woo, In So Kweon
2019 A* conf
Preserving Semantic and Temporal Consistency for Unpaired Video-to-Video Translation.
ACM Multimedia
Kwanyong Park, Sanghyun Woo, Dahun Kim, Donghyeon Cho, In So Kweon
2019 J jnl
Preserving Semantic and Temporal Consistency for Unpaired Video-to-Video Translation.
CoRR
Kwanyong Park, Sanghyun Woo, Dahun Kim, Donghyeon Cho, In So Kweon
2019 A* conf
Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles.
AAAI
Dahun Kim, Donghyeon Cho, In So Kweon
2019 A* conf
Video Retargeting: Trade-off between Content Preservation and Spatio-temporal Consistency.
ACM Multimedia
Donghyeon Cho, Yunjae Jung, François Rameau, Dahun Kim, Sanghyun Woo, In So Kweon
2018 J jnl
Discriminative Feature Learning for Unsupervised Video Summarization.
CoRR
Yunjae Jung, Donghyeon Cho, Dahun Kim, Sanghyun Woo, In So Kweon
2018 A conf
Learning Image Representations by Completing Damaged Jigsaw Puzzles.
WACV
Dahun Kim, Donghyeon Cho, Donggeun Yoo, In So Kweon
2018 J jnl
Learning Image Representations by Completing Damaged Jigsaw Puzzles.
CoRR
Dahun Kim, Donghyeon Cho, Donggeun Yoo, In So Kweon
2018 A* conf
LinkNet: Relational Embedding for Scene Graph.
NeurIPS
Sanghyun Woo, Dahun Kim, Donghyeon Cho, In So Kweon
2018 J jnl
LinkNet: Relational Embedding for Scene Graph.
CoRR
Sanghyun Woo, Dahun Kim, Donghyeon Cho, In So Kweon
2018 J jnl
Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles.
CoRR
Dahun Kim, Donghyeon Cho, In So Kweon
2017 A* conf
Two-Phase Learning for Weakly Supervised Object Localization.
ICCV
Dahun Kim, Donghyeon Cho, Donggeun Yoo
2017 J jnl
Two-Phase Learning for Weakly Supervised Object Localization.
CoRR
Dahun Kim, Donghyeon Cho, Donggeun Yoo, In So Kweon