{"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/ego-object-discovery","title":"Ego-Object Discovery","arxiv_id":"1504.01639","date":"2015-04-07","proceeding":null,"authors":["Marc Bolaños","Petia Radeva"],"abstract":"Lifelogging devices are spreading faster everyday. This growth can represent\ngreat benefits to develop methods for extraction of meaningful information\nabout the user wearing the device and his/her environment. In this paper, we\npropose a semi-supervised strategy for easily discovering objects relevant to\nthe person wearing a first-person camera. Given an egocentric video/images\nsequence acquired by the camera, our algorithm uses both the appearance\nextracted by means of a convolutional neural network and an object refill\nmethodology that allows to discover objects even in case of small amount of\nobject appearance in the collection of images. An SVM filtering strategy is\napplied to deal with the great part of the False Positive object candidates\nfound by most of the state of the art object detectors. We validate our method\non a new egocentric dataset of 4912 daily images acquired by 4 persons as well\nas on both PASCAL 2012 and MSRC datasets. We obtain for all of them results\nthat largely outperform the state of the art approach. We make public both the\nEDUB dataset and the algorithm code.","url_abs":"http://arxiv.org/abs/1504.01639v2","url_pdf":"http://arxiv.org/pdf/1504.01639v2.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":"ego-object-discovery","repo_url":"https://github.com/MarcBS/Ego-Object_Discovery","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-discovery","task_name":"Object Discovery"}],"methods":[{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}