61 citations
- Chonnam National UniversityKR2 papers
- Advanced Institute of Convergence TechnologyKR1 paper
- Brigham and Women's HospitalUS1 paper
- Carnegie Mellon UniversityUS1 paper
- Chung-Ang UniversityKR1 paper
- Dalhousie UniversityCA1 paper
- Decision Systems (United States)US1 paper
- Delft University of TechnologyNL1 paper
- Dongguk UniversityKR1 paper
- Florida Atlantic UniversityUS1 paper
- Georgetown UniversityUS1 paper
- Georgetown University Medical CenterUS1 paper
Showing cs.CVShow all
3 papers · 1 filter
cs.CV2024★ 3 cited
CIC: A Framework for Culturally-Aware Image Captioning
Youngsik Yun, Jihie Kim
Image Captioning generates descriptive sentences from images using Vision-Language Pre-trained models (VLPs) such as BLIP, which has improved greatly. However, current methods lack…
cs.CV2023★ 3 cited
Capsule network with shortcut routing
Dang Thanh Vu, Vo Hoang Trong, Yu Gwang-Hyun +1
This study introduces "shortcut routing," a novel routing mechanism in capsule networks that addresses computational inefficiencies by directly activating global capsules from loca…
cs.CV2021★ 61 cited
Weighted Intersection over Union (wIoU) for Evaluating Image Segmentation
Yeong-Jun Cho
In recent years, many semantic segmentation methods have been proposed to predict label of pixels in the scene. In general, we measure area prediction errors or boundary prediction…