FAIRView: Visual Explanations for Video Summaries

<em><strong>FAIRView Corpus: Visual Explanations for Video Summaries</strong></em> This repository contains: 200 videos machine annotated with key concepts extracted from video subtitles and video frames; 800 video summaries (four summaries per video) machine annotated with concepts extracted from video subtitles and frames; 3200 visual explanations (four explanations per video summary with different levels of <em>transparency</em>): semantic coverage semantic prominence quantity coverage distance human validated <strong>utility</strong> of each visual explanation type (mTurk crowdsourcing study_1 with 20 videos and single summary) human validated <strong>representativeness</strong> of video summaries with regard to their original videos (mTurk crowdsourcing study_2 with 18 videos with 2 summaries per video). In total 36 video-summary pairs. <br> All results are published in the following paper: Oana Inel, Nava Tintarev and Lora Aroyo: **Eliciting User Preferences for Personalized Explanations for Video Summaries**. UMAP 2020. <br> If you find the paper and the data useful in your research, please consider citing: <br> @inproceedings{inel2020eliciting,<br> title={Eliciting User Preferences for Personalized Explanations for Video Summaries},<br> author={Inel, Oana and Tintarev, Nava and Aroyo, Lora},<br> booktitle={To Appear in the Proceedings of the 28th Conference on User Modeling, Adaptation and Personalization (UMAP)},<br> year={2020},<br> organization={ACM}<br> }