five

Mouse Grooming Behavior

收藏
OpenDataLab2026-05-17 更新2024-05-09 收录
下载链接:
https://opendatalab.org.cn/OpenDataLab/Mouse_Grooming_Behavior
下载链接
链接失效反馈
官方服务:
资源简介:
生成此数据集以表征鼠标修饰行为。鼠标修饰具有许多适应性功能,例如毛发和身体护理、减轻压力、去唤醒、社交功能、体温调节、伤害感受以及其他功能。这种行为的改变被测量并用于人类精神疾病的小鼠临床前模型。老鼠的梳理行为包含多种视觉上不同的句法,包括但不限于舔爪子、洗脸和舔侧面。此外,该数据集包括视觉上多样化的小鼠,包括 157 只个体小鼠,跨越 60 个不同的近交系和 F1 杂交小鼠品系。此功能与大多数其他小鼠行为数据集截然不同,后者通常仅包含 1-2 个近交系。该数据集包括 1,253 个小鼠视频片段,这些视频片段是从自上而下的视角成像的开放视野中的老鼠。每个视频剪辑都包含一个 112x112 的视频小管,在鼠标在露天场地周围行走时围绕鼠标的质心进行裁剪。视频剪辑的长度可变,总计 2,637,363 帧。注释者需要为每一帧提供“修饰”或“不修饰”注释。还提供了注释者不同意的框架。

This dataset was generated to characterize mouse grooming behavior. Mouse grooming serves numerous adaptive functions, including hair and body care, stress reduction, arousal reduction, social functions, thermoregulation, nociception, and other such functions. Alterations in this behavior are measured and utilized in preclinical mouse models of human psychiatric disorders. Mouse grooming behavior encompasses a variety of visually distinct syntactic patterns, including but not limited to paw licking, face washing, and flank licking. Additionally, this dataset includes visually diverse mice, comprising 157 individual mice across 60 distinct inbred and F1 hybrid mouse strains. This feature distinguishes it from most other mouse behavior datasets, which typically only contain 1-2 inbred strains. The dataset includes 1,253 mouse video clips, which were captured from a top-down perspective of mice in an open field. Each video clip contains an 112x112 video crop centered on the mouse's centroid as the mouse traverses the open field. The video clips vary in length, totaling 2,637,363 frames. Annotators were required to provide "grooming" or "not grooming" annotations for each frame. Frames where annotators disagreed are also provided.
提供机构:
OpenDataLab
创建时间:
2022-05-23
搜集汇总
数据集介绍
main_image_url
背景与挑战
背景概述
该数据集专注于小鼠梳理行为的研究,包含1,253个视频片段和超过260万帧的标注数据,每帧都标注了'修饰'或'不修饰'状态,适用于视频分类和动作检测任务。其独特之处在于涵盖了157只个体小鼠和60个不同品系,增加了数据的多样性和泛化能力,常用于人类精神疾病的临床前模型分析。数据集由美国杰克逊实验室于2021年发布,采用CC BY-NC-ND 4.0许可证,总大小为33.3GB。
以上内容由遇见数据集搜集并总结生成
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作