Historical Film Shot Dataset V1 (HistShotDS V1)

<em>Paper title: </em> <strong>HistShot: A Shot Type Dataset based on Historical Documentation during WWII</strong> <em>Conference title: </em> International Conference on Pattern Recognition Applications and Methods (ICPRAM 2022) <em>Description:</em> Automated shot type classification plays a significant role in film preservation and indexing of film datasets. In this paper a historical shot type dataset (HistShot) is presented, where the frames have been extracted from original historical documentary films. A center frame of each shot has been chosen for the dataset and is annotated according to the following shot types: Close-Up (CU), Medium-Shot (MS), Long-Shot (LS), Extreme-Long-Shot (ELS), Intertitle (I), and Not Available/None (NA). The validity to choose the center frame is shown by a user study. Additionally, standard CNN-based methods (ResNet50, VGG16) have been applied to provide a baseline for the HistShot dataset. <em>References: </em> Github Repository: https://github.com/dahe-cvl/ICPRAM2022_histshotV1 VHH-MMSI: https://vhh-mmsi.eu/ VHH-project Page: https://www.vhh-project.eu/论文标题：《HistShot：基于二战历史影像资料的镜头类型数据集》 会议名称：国际模式识别应用与方法会议（ICPRAM 2022） 数据集描述：自动化镜头类型分类在电影档案保存与电影数据集索引工作中具有重要意义。本文提出了一款历史镜头类型数据集（HistShot），其帧数据均取自原始历史纪录片。该数据集选取每段镜头的中心帧作为样本，并按照以下镜头类型进行标注：特写镜头（Close-Up, CU）、中景镜头（Medium-Shot, MS）、全景镜头（Long-Shot, LS）、极远景镜头（Extreme-Long-Shot, ELS）、字幕帧（Intertitle, I）以及无可用标注/无（Not Available/None, NA）。一项用户研究验证了选取中心帧作为样本的合理性。此外，本文采用了基于卷积神经网络（Convolutional Neural Network, CNN）的经典方法（ResNet50、VGG16），为HistShot数据集构建了基准性能基线。 参考文献：GitHub仓库：https://github.com/dahe-cvl/ICPRAM2022_histshotV1；VHH-MMSI官网：https://vhh-mmsi.eu/；VHH项目官网：https://www.vhh-project.eu/