VideoLoom:一种用于联合空间-时间理解的视频大语言模型
VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding
AI总结:
VideoLoom是一种用于联合空间-时间理解的视频大语言模型,通过LoomData-8.7k数据集和LoomBench基准测试,在多个视频理解任务中取得优异性能。
摘要:
本文提出了VideoLoom,一种用于联合空间-时间理解的统一视频大语言模型(Video LLM)。为了促进细粒度空间和时间定位能力的发展,我们整理了LoomData-8.7k,一个以人为中心的视频数据集,具有时间接地和空间局部化的描述。借助这一数据集,VideoLoom在多种空间和时间基准测试中实现了最先进的或高度竞争性的性能(例如,在ReVOS上针对指称视频对象分割的63.1 J&F,以及在Charades-STA上针对时间接地的48.3 R1@0.7)。此外,我们引入了LoomBench,一个由时间、空间和组成视频问题对组成的新型基准,使Video LLMs能够从多个方面进行全面评估。总体而言,这些贡献提供了一种通用且有效的工具集,用于联合空间-时间视频理解,为多模态智能设定了新的标准。
英文摘要:
This paper presents VideoLoom, a unified Video Large Language Model (Video LLM) for joint spatial-temporal understanding. To facilitate the development of fine-grained spatial and temporal localization capabilities, we curate LoomData-8.7k, a human-centric video dataset with temporally grounded and spatially localized captions. With this, VideoLoom achieves state-of-the-art or highly competitive performance across a variety of spatial and temporal benchmarks (e.g., 63.1 J&F on ReVOS for referring video object segmentation, and 48.3 R1@0.7 on Charades-STA for temporal grounding). In addition, we introduce LoomBench, a novel benchmark consisting of temporal, spatial, and compositional video-question pairs, enabling a comprehensive evaluation of Video LLMs from diverse aspects. Collectively, these contributions offer a universal and effective suite for joint spatial-temporal video understanding, setting a new standard in multimodal intelligence.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。