arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.02243cs.DB
收藏

面向组合事件、基于大语言模型的自增强视频数据管理系统 [技术报告]

Self-Enhancing Video Data Management System for Compositional Events with Large Language Models [Technical Report]

Enhao Zhang, Nicole Sullivan, Brandon Haynes, Ranjay Krishna, Magdalena Balazinska

AI总结:

本文提出 VOCAL-UDF 自增强视频数据管理系统,利用 LLM 自动生成程序型或蒸馏模型型 UDF,并通过主动学习选择候选,以支持无预定义模块的组合视频查询。

摘要:

复杂视频查询可以通过将其分解为模块化子任务来回答。然而,现有视频数据管理系统假定每个子任务都存在预定义模块。我们提出 VOCAL-UDF,这是一种新颖的自增强系统,无需预定义模块即可支持视频上的组合查询。VOCAL-UDF 会自动识别并构建缺失模块,并将其封装为用户定义函数(UDF),从而扩展其查询能力。为此,我们构建了一个统一的 UDF 模型,利用大语言模型(LLM)辅助生成新的 UDF。VOCAL-UDF 通过同时支持基于程序的 UDF(即由 LLM 生成的 Python 函数)和蒸馏模型 UDF(从强大的预训练模型蒸馏出的轻量级视觉模型)来处理广泛的概念。为解决用户意图中固有的歧义,VOCAL-UDF 会生成多个候选 UDF,并使用主动学习高效选择最佳候选。凭借自增强能力,VOCAL-UDF 在三个视频数据集上显著提升了查询性能。

英文摘要:

Complex video queries can be answered by decomposing them into modular subtasks. However, existing video data management systems assume the existence of predefined modules for each subtask. We introduce VOCAL-UDF, a novel self-enhancing system that supports compositional queries over videos without the need for predefined modules. VOCAL-UDF automatically identifies and constructs missing modules and encapsulates them as user-defined functions (UDFs), thus expanding its querying capabilities. To achieve this, we formulate a unified UDF model that leverages large language models (LLMs) to aid in new UDF generation. VOCAL-UDF handles a wide range of concepts by supporting both program-based UDFs (i.e., Python functions generated by LLMs) and distilled-model UDFs (lightweight vision models distilled from strong pretrained models). To resolve the inherent ambiguity in user intent, VOCAL-UDF generates multiple candidate UDFs and uses active learning to efficiently select the best one. With the self-enhancing capability, VOCAL-UDF significantly improves query performance across three video datasets.

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。

↑