MIVE Dataset

Name: MIVE Dataset
Creator: Agus Gunawan; Samuel Teodoro Teodoro; Munchurl Kim; Soo Ye Kim; Jihyong Oh
Published: 2026-04-17T17:24:54+08:00

IEEE2026-04-17 收录

多实例视频编辑

视频实例分割

数据链接：

https://ieee-dataport.org/documents/mive-dataset 数据链接链接失效反馈

官方服务：

资源简介：

The MIVE (Multi-Instance Video Editing) Dataset is a new dataset for multi-instance video editing tasks. It contains 200 videos with varying numbers and sizes of instances accompanied with instance-level captions and masks.

提供机构：

Agus Gunawan; Samuel Teodoro Teodoro; Munchurl Kim; Soo Ye Kim; Jihyong Oh

OVIS

视频实例分割

遮挡场景处理

OVIS数据集是由华中科技大学和阿里巴巴集团联合创建的大规模视频实例分割数据集，专注于在遮挡场景中同时检测、分割和跟踪实例。该数据集包含296,000个高质量实例掩码，涵盖25个语义类别，其中大部分对象存在遮挡情况。OVIS数据集的创建旨在探索视频理解系统在处理实际世界中广泛存在的遮挡问题时的能力，特别是在视频实例分割任务中。数据集的访问地址为http://songbai.site/ovis，适用

arXiv2022-05-18 更新450

SBM-VIS dataset

视频实例分割

计算机视觉

The zip file only contains the SBM-VIS dataset. SBM-VIS means Social Black Mice-Video Instance Segmentation, which is arranged according to the format of the video instance segmentation task.

DataCite Commons2025-06-01 更新150

Quantitative results for different metrics under varying levels of distance between instances are presented in terms of mIoU on the Youtube-VIS 2019 dataset.

视频实例分割

图像分割性能评估

Quantitative results for different metrics under varying levels of distance between instances are presented in terms of mIoU on the Youtube-VIS 2019 dataset.

Figshare2024-10-07 更新40

YouTubeVIS 视频实例分割数据集

视频实例分割

计算机视觉

YouTubeVIS 是一个可用于视频实例分割的大规模数据集，采集自 YouTubeVOS 数据集。该数据集是为视频中目标实例的同步检测、分割和跟踪等任务设计的。

超神经2022-09-19 更新220

Quantitative results for different metrics under varying levels of occlusion in terms of mIoU on the Youtube-VIS 2019 dataset.

视频实例分割

遮挡鲁棒性评估

Quantitative results for different metrics under varying levels of occlusion in terms of mIoU on the Youtube-VIS 2019 dataset.

Figshare2024-10-07 更新60