2 papers
cs.CV2026
CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video-Language Models
Mukhtiar Ali, Harsh Dubey, Sugam Mishra +1
Benchmarking video-language models has largely focused on short clips and single-sentence metrics, leaving open whether current systems can generate accurate long-form, paragraph-l…
cs.CV2025
A Novel Dataset for Flood Detection Robust to Seasonal Changes in Satellite Imagery
Youngsun Jang, Dongyoun Kim, Chulwoo Pack +1
This study introduces a novel dataset for segmenting flooded areas in satellite images. After reviewing 77 existing benchmarks utilizing satellite imagery, we identified a shortage…