Byungseok Roh
9 papers · 2021–2024 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (6) π Cross-Pollinator (13) π Renaissance Researcher (5)
πΊοΈ
Taxonomy Completionist
(23)
π£
Hot Topic Early Bird
Conferences
CVPR (4)
AISTATS (1)
COLING (1)
EMNLP (1)
ICCV (1)
ICLR (1)
Top co-authors
Keywords
contrastive learning
(3)
zero-shot learning
(2)
benchmark evaluation
(1)
semantic segmentation
(1)
image captioning
(1)
causal reasoning
(1)
self-supervised learning
(1)
image-text pair
(1)
temporal reasoning
(1)
multimodal learning
(1)
object detection
(1)
video understanding
(1)
instruction tuning
(1)
foundation model
(1)
representation learning
(1)
multimodal large language model
(1)
image-text retrieval
(1)
multimodal representation
(1)
geometric transformation
(1)
meta learning
(1)
Papers
Towards a Complete Benchmark on Video Moment Localization
AISTATS 2024
Honeybee: Locality-enhanced Projector for Multimodal LLM
CVPR 2024
MELTR: Meta Loss Transformer for Learning To Fine-Tune Video Foundation Models
CVPR 2023
Learning To Generate Text-Grounded Mask for Open-World Semantic Segmentation From Only Image-Text Pairs
CVPR 2023
Large Language Models are Temporal and Causal Reasoners for Video Question Answering
EMNLP 2023
Noise-Aware Learning from Web-Crawled Image-Text Data for Image Captioning
ICCV 2023
Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity
ICLR 2022
Efficient Multilingual Multi-modal Pre-training through Triple Contrastive Loss
COLING 2022
Spatially Consistent Representation Learning
CVPR 2021