{"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/from-lifestyle-vlogs-to-everyday-interactions","title":"From Lifestyle Vlogs to Everyday Interactions","arxiv_id":"1712.02310","date":"2017-12-06","proceeding":"CVPR 2018 6","authors":["David F. Fouhey","Wei-cheng Kuo","Alexei A. Efros","Jitendra Malik"],"abstract":"A major stumbling block to progress in understanding basic human\ninteractions, such as getting out of bed or opening a refrigerator, is lack of\ngood training data. Most past efforts have gathered this data explicitly:\nstarting with a laundry list of action labels, and then querying search engines\nfor videos tagged with each label. In this work, we do the reverse and search\nimplicitly: we start with a large collection of interaction-rich video data and\nthen annotate and analyze it. We use Internet Lifestyle Vlogs as the source of\nsurprisingly large and diverse interaction data. We show that by collecting the\ndata first, we are able to achieve greater scale and far greater diversity in\nterms of actions and actors. Additionally, our data exposes biases built into\ncommon explicitly gathered data. We make sense of our data by analyzing the\ncentral component of interaction -- hands. We benchmark two tasks: identifying\nsemantic object contact at the video level and non-semantic contact state at\nthe frame level. We additionally demonstrate future prediction of hands.","url_abs":"http://arxiv.org/abs/1712.02310v1","url_pdf":"http://arxiv.org/pdf/1712.02310v1.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":"diversity","task_name":"Diversity"},{"task_slug":"future-prediction","task_name":"Future prediction"}],"methods":[],"datasets_introduced":[{"slug":"vlog-dataset","name":"VLOG Dataset","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1712.02310","atlas_url":"https://app.syntology.ai/?focus=1712.02310","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}