MovingFashion

MovingFashion数据集由意大利维罗纳大学计算机科学系创建，是首个公开的视频到购物挑战基准数据集。该数据集包含15045个社交视频，每个视频都与电子商务中的‘购物’图像相关联，其中对应的服装项目被清晰描绘。数据集的视频来源于Net-A-Porter、Instagram和TikTok，包含数百帧每件商品，分为常规和困难两种设置。MovingFashion数据集旨在解决视频中服装识别与匹配的问题，为电子时尚领域提供了一个新的研究方向。

The MovingFashion dataset, developed by the Department of Computer Science at the University of Verona in Italy, is the first publicly available benchmark dataset for the video-to-fashion shopping challenge. This dataset comprises 15,045 social media videos, each paired with e-commerce "shopping" images that clearly depict the corresponding clothing items. The videos in the dataset are sourced from Net-A-Porter, Instagram and TikTok, with hundreds of frames per item, and it is divided into two experimental settings: standard and challenging. The MovingFashion dataset aims to address the problem of clothing recognition and matching in videos, providing a novel research direction for the e-fashion domain.