1.3k citations
- Korea Institute of Science and TechnologyKR299 papers
- Institute for Basic ScienceKR253 papers
- Seoul National UniversityKR172 papers
- Korea Institute for Advanced StudyKR134 papers
- Pohang University of Science and TechnologyKR102 papers
- Centre National de la Recherche ScientifiqueFR86 papers
- Korea UniversityKR86 papers
- Kootenay Association for Science & TechnologyCA74 papers
- The University of TokyoJP74 papers
- Massachusetts Institute of TechnologyUS71 papers
- National Institute for Mathematical SciencesKR69 papers
- University of MichiganUS69 papers
249 papers · 1 filter
Metric-Driven Reinforcement Learning for Object Hallucination Reduction in LVLM-Based Image Captioning
Thanh Nguyen, Hee Suk Yoon, Tung Minh Luu +2
Large Vision-Language Models (LVLMs) have excelled in joint visual and language understanding, particularly in image captioning. However, LVLMs remain prone to object hallucination…
Contrastive Knowledge Distillation for Anomaly Detection in Multi-Illumination/Focus Display Images
Jihyun Lee, Hangil Park, Yongmin Seo +4
In this paper, we tackle automatic anomaly detection in multi-illumination and multi-focus display images. The minute defects on the display surface are hard to spot out in RGB ima…
Unleashing the Power of Text: Text-Guided Flow Matching for Image Fusion under Complex Degradations
Axi Niu, Jieheng Li, Kang Zhang +3
Infrared-visible image fusion under realistic degradation scenarios is a challenging task, as degradations not only cause a loss of reliable modality-specific information in observ…
Splat-based 3D Scene Reconstruction with Extreme Motion-blur
Hyeonjoong Jang, Dongyoung Choi, Donggun Kim +2
We propose a splat-based 3D scene reconstruction method from RGB-D input that effectively handles extreme motion blur, a frequent challenge in low-light environments. Under dim ill…
HistoSeg++: Delving deeper with attention and multiscale feature fusion for biomarker segmentation
Saad Wazir, Rao Faizan, Daeyoung Kim
Segmentation of biomarkers in medical images is frequently viewed as a first step towards medical image analysis in any bioinformatics or biomedical application. Despite progress,…
EgoGapBench: Benchmarking Egocentric Action Selection in Multi-Agent Scenes
Jihyeok Jung, Jeewu Lee, Sanghyeop Kim +2
Existing egocentric benchmarks have primarily constructed the egocentric setting from first-person-view data, which makes it difficult to evaluate egocentric perspective itself in…