{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/videomem-constructing-analyzing-predicting","title":"VideoMem: Constructing, Analyzing, Predicting Short-term and Long-term Video Memorability","arxiv_id":"1812.01973","date":"2018-12-05","proceeding":"ICCV 2019 10","authors":["Romain Cohendet","Claire-Hélène Demarty","Ngoc Q. K. Duong","Martin Engilberge"],"abstract":"Humans share a strong tendency to memorize/forget some of the visual\ninformation they encounter. This paper focuses on providing computational\nmodels for the prediction of the intrinsic memorability of visual content. To\naddress this new challenge, we introduce a large scale dataset (VideoMem)\ncomposed of 10,000 videos annotated with memorability scores. In contrast to\nprevious work on image memorability -- where memorability was measured a few\nminutes after memorization -- memory performance is measured twice: a few\nminutes after memorization and again 24-72 hours later. Hence, the dataset\ncomes with short-term and long-term memorability annotations. After an in-depth\nanalysis of the dataset, we investigate several deep neural network based\nmodels for the prediction of video memorability. Our best model using a ranking\nloss achieves a Spearman's rank correlation of 0.494 for short-term\nmemorability prediction, while our proposed model with attention mechanism\nprovides insights of what makes a content memorable. The VideoMem dataset with\npre-extracted features is publicly available.","url_abs":"http://arxiv.org/abs/1812.01973v1","url_pdf":"http://arxiv.org/pdf/1812.01973v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"memorization","task_name":"Memorization"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[{"slug":"videomem","name":"VideoMem","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.01973","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}