QVHighlights

QVHighlights is a benchmark dataset used to evaluate the performance of video-language models in the task of temporal localization in videos.

Papers using QVHighlights (4)

Chrono: A Simple Blueprint for Representing Time in MLLMs2024 · 3 citesSee More, Store Less: Memory-Efficient Resolution for Video Moment Retrieval2026Language-guided Temporal Token Pruning For Efficient Videollm Processing2025MLVTG: Mamba-based Feature Alignment And Llm-driven Purification For Multi-modal Video Temporal Grounding2025