{"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/temporal-saliency-adaptation-in-egocentric","title":"Temporal Saliency Adaptation in Egocentric Videos","arxiv_id":"1808.09559","date":"2018-08-28","proceeding":null,"authors":["Panagiotis Linardos","Eva Mohedano","Monica Cherto","Cathal Gurrin","Xavier Giro-i-Nieto"],"abstract":"This work adapts a deep neural model for image saliency prediction to the\ntemporal domain of egocentric video. We compute the saliency map for each video\nframe, firstly with an off-the-shelf model trained from static images, secondly\nby adding a a convolutional or conv-LSTM layers trained with a dataset for\nvideo saliency prediction. We study each configuration on EgoMon, a new dataset\nmade of seven egocentric videos recorded by three subjects in both free-viewing\nand task-driven set ups. Our results indicate that the temporal adaptation is\nbeneficial when the viewer is not moving and observing the scene from a narrow\nfield of view. Encouraged by this observation, we compute and publish the\nsaliency maps for the EPIC Kitchens dataset, in which viewers are cooking.\nSource code and models available at\nhttps://imatge-upc.github.io/saliency-2018-videosalgan/","url_abs":"http://arxiv.org/abs/1808.09559v2","url_pdf":"http://arxiv.org/pdf/1808.09559v2.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":"temporal-saliency-adaptation-in-egocentric","repo_url":"https://github.com/imatge-upc/egocentric-2016-saliency","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"temporal-saliency-adaptation-in-egocentric","repo_url":"https://github.com/imatge-upc/saliency-2018-videosalgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"saliency-prediction","task_name":"Saliency Prediction"},{"task_slug":"video-saliency-prediction","task_name":"Video Saliency Prediction"}],"methods":[],"datasets_introduced":[{"slug":"egomon","name":"EgoMon","full_name":"Egomon Gaze & Video dataset"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}