Jaeseok Byun
5 papers · 2021–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (3) π Renaissance Researcher (6) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (17) π§ Keyword Pioneer
π£
Hot Topic Early Bird
π
Cross-Pollinator
(15)
Conferences
CVPR (2)
ICCV (2)
ECCV (1)
Top co-authors
Keywords
composed image retrieval
(2)
contrastive learning
(2)
transfer learning
(1)
multimodal learning
(1)
multi-modal learning
(1)
image denoising
(1)
label smoothing
(1)
vision-language pre-training
(1)
text encoder
(1)
point cloud processing
(1)
image-text matching
(1)
false negative
(1)
semantic composition
(1)
hard negative
(1)
poisson-gaussian noise
(1)
large language model
(1)
neural network
(1)
blind denoising
(1)
noise parameter estimation
(1)
false negative handling
(1)
Papers
MA-CIR: A Multimodal Arithmetic Benchmark for Composed Image Retrieval
ICCV 2025
An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval
ICCV 2025
MAFA: Managing False Negatives for Vision-Language Pre-training
CVPR 2024
GRIT-VLP: Grouped Mini-Batch Sampling for Efficient Vision and Language Pre-training
ECCV 2022
FBI-Denoiser: Fast Blind Image Denoiser for Poisson-Gaussian Noise
CVPR 2021