PulseAugur
中
实时 20:45:13
English(EN) An Analysis Focused on Womens Safety: Can VAD Models Be Enhanced by a Multi-modal Dataset?

新数据集ExtrAnom增强女性安全视频异常检测

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员推出了ExtrAnom数据集，这是一个新的多模态基准，旨在提高专门针对女性安全的视频异常检测（VAD）能力。该数据集包含1001个视频，其中501个被标记为异常，涵盖了跟踪、抢劫和骚扰等犯罪行为。ExtrAnom包含低光照和低分辨率等挑战性条件，并且每个视频都配有人工生成和LLM生成的文本描述，以辅助跨模态验证。 AI

影响 该数据集有望在现实世界的监控场景中催生更有效的AI系统，以检测和预防针对女性的犯罪。

排序理由 该集群包含一篇介绍特定AI任务新数据集和基准的学术论文。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新数据集ExtrAnom增强女性安全视频异常检测

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Sangeeta, Maddikuntla Sai Prajwal, Debi Prosad Dogra, Kamalakar Vijay Thakare, Hyungjoo Jung, Ig-Jae Kim, Heeseung Choi ·

    一项关注女性安全性的分析：多模态数据集能否增强VAD模型？

    arXiv:2605.25806v1 Announce Type: new Abstract: Women's safety and security are paramount for a modern society. Crimes against women occur in daylight as well as in low-light conditions. Often, such events are captured through real-world surveillance cameras that operate at lower…

  2. arXiv cs.CV TIER_1 English(EN) · Heeseung Choi ·

    聚焦女性安全分析：多模态数据集能否提升VAD模型？

    Women's safety and security are paramount for a modern society. Crimes against women occur in daylight as well as in low-light conditions. Often, such events are captured through real-world surveillance cameras that operate at lower resolutions. Despite substantial progress in CV…

相关实体

相关话题