PulseAugur
中
实时 10:01:04
English(EN) V-STORM: A Structure-Aware Grounded Chain of Thought Dataset for Faithful and Fine-Grained Spatio-Temporal Video Reasoning

V-STORM数据集增强MLLM时空视频推理能力

作者 PulseAugur 编辑部 · [1 个来源] ·

研究人员推出了一种名为V-STORM的新型框架，旨在增强多模态大语言模型（MLLMs）的时空推理能力。该框架将视频转换为时空场景图（STSGs），并从经过验证的证据路径中提取基础思维链（GCoT）注释，使每个推理步骤都可追溯。使用此方法构建了一个包含260,000个样本的数据集和一个3,000个样本的基准测试，结果表明，尽管当前的MLLMs能够识别相关的时空线索，但它们在将这些线索整合到多步推理中时存在困难。使用V-STORM进行微调已显著提高了答案准确性和基础忠实度。 AI

影响 该数据集和框架可以改进AI模型理解和推理视频内容的方式，从而在视频分析和摘要等领域带来更高级的应用。

排序理由 该集群描述了一个用于视频推理研究的新数据集和框架。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

V-STORM数据集增强MLLM时空视频推理能力

本文如何被排名

Signal score
15 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群描述了一个用于视频推理研究的新数据集和框架。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.CV TIER_1 English(EN) · Dian Jiao, Yuqian Yuan, Jiaqi Zhu, Mingjian Gao, Siwen Tan, Yunqi Cao, Jinhui Li, Sijing Li, Zhenxuan Fan, Haoyang Wang, Wenqiao Zhang, Siliang Tang ·

    V-STORM：一个结构感知式地面思维链数据集，用于忠实且细粒度的时空视频推理

    arXiv:2611.09511v1 Announce Type: new Abstract: While MLLMs can often identify what happens in a video, they still struggle with fine-grained spatio-temporal reasoning, which requires precise grounding when and where the supporting evidence appears and composing such evidence int…

相关实体

相关话题