{"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/a-weighted-sparse-sampling-and-smoothing-1","title":"A Weighted Sparse Sampling and Smoothing Frame Transition Approach for Semantic Fast-Forward First-Person Videos","arxiv_id":"1802.08722","date":"2018-02-23","proceeding":"CVPR 2018","authors":["Michel Melo Silva","Washington Luis Souza Ramos","Joao Klock Ferreira","Felipe Cadar Chamone","Mario Fernando Montenegro Campos","Erickson Rangel Nascimento"],"abstract":"Thanks to the advances in the technology of low-cost digital cameras and the\npopularity of the self-recording culture, the amount of visual data on the\nInternet is going to the opposite side of the available time and patience of\nthe users. Thus, most of the uploaded videos are doomed to be forgotten and\nunwatched in a computer folder or website. In this work, we address the problem\nof creating smooth fast-forward videos without losing the relevant content. We\npresent a new adaptive frame selection formulated as a weighted minimum\nreconstruction problem, which combined with a smoothing frame transition method\naccelerates first-person videos emphasizing the relevant segments and avoids\nvisual discontinuities. The experiments show that our method is able to\nfast-forward videos to retain as much relevant information and smoothness as\nthe state-of-the-art techniques in less time. We also present a new 80-hour\nmultimodal (RGB-D, IMU, and GPS) dataset of first-person videos with\nannotations for recorder profile, frame scene, activities, interaction, and\nattention.","url_abs":"http://arxiv.org/abs/1802.08722v4","url_pdf":"http://arxiv.org/pdf/1802.08722v4.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":[{"paper_slug":"a-weighted-sparse-sampling-and-smoothing-1","repo_url":"https://github.com/verlab/SemanticFastForward_CVPR_2018","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"culture","task_name":"Cultural Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[{"slug":"domsev","name":"DoMSEV","full_name":"Dataset of Multimodal Semantic Egocentric Video"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.08722","atlas_url":"https://app.syntology.ai/?focus=1802.08722","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}