Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Natural-Language Temporal Grounding in Hour-Long Videos is a Search Problem: A Benchmark and Empirical Decomposition
Sukmin Seo, Geewook Kim
Temporal grounding--returning the interval for a natural-language query over a video--is the language interface to long-form video, yet has been studied on short video…
cs.CV2024
CREPE: Coordinate-Aware End-to-End Document Parser
Yamato Okamoto, Youngmin Baek, Geewook Kim +5
In this study, we formulate an OCR-free sequence generation model for visual document understanding (VDU). Our model not only parses text from document images but also extracts the…