arXiv cs.AI· Luoyuan Zhang, Xuanyu Zheng, Yancheng Long, Haoyang Xu, Bin Wen, Tingting Gao·· 2 小时前AI 评分34
VideoACE 基准:用高帧率动作视频评测智能体式视频理解
VideoACE: Benchmarking Agentic Video Understanding through High-Frame-Rate Actions
AI 导读
研究者提出 VideoACE 基准,评测模型在高帧率动作视频下通过主动交互获取证据的视频理解能力。基准包含 1,000 道选择题,覆盖六类细粒度动作理解,配有时间证据标注,评估环境结合视频检查工具与用户模拟器,模型可调整时间覆盖、采样密度、空间细节并修订判断。对五个模型的评测显示各模型在证据获取与响应进一步交互机会上存在不同模式。
正文 · 原文
Abstract:Agentic video understanding requires models to actively interact with video environments to gather evidence and form judgments. Evaluating this capability therefore requires assessing whether models can translate opportunities for interaction into better understanding. We introduce VideoACE, a benchmark for assessing video understanding under conditions that support sustained interaction. We focus on high-frame-rate action videos, where rapid, subtle changes make targeted observation especially valuable. The benchmark comprises 1,000 multiple-choice questions spanning six categories of fine-grained action understanding, accompanied by temporal evidence annotations and user hints screened for answer leakage. Its evaluation environment combines video inspection tools with a user simulator, allowing models to adjust temporal coverage, sampling density, and spatial detail, and to revisit evidence and revise their judgments under simulated user feedback. We evaluate single-pass observation, autonomous tool use, and tool use combined with user feedback to examine how effectively models exploit these opportunities. Evaluation of five models reveals distinct patterns in how they acquire evidence and respond to opportunities for further interaction. These findings establish VideoACE as a testbed for examining agentic video understanding beyond performance under a fixed observation setting.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Multimedia (cs.MM) |
| Cite as: | arXiv:2611.24184 [cs.CV] |
| (or arXiv:2611.24184v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.24184 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Luoyuan Zhang [view email]
[v1]
Wed, 18 Nov 2026 10:26:07 UTC (3,669 KB)
来源:arXiv cs.AI · arxiv.org