{"id":238200,"date":"2016-06-01T00:00:00","date_gmt":"2016-06-01T07:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/highlight-detection-with-pairwise-deep-ranking-for-first-person-video-summarization\/"},"modified":"2018-10-16T20:01:55","modified_gmt":"2018-10-17T03:01:55","slug":"highlight-detection-with-pairwise-deep-ranking-for-first-person-video-summarization","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/highlight-detection-with-pairwise-deep-ranking-for-first-person-video-summarization\/","title":{"rendered":"Highlight Detection with Pairwise Deep Ranking for First-Person Video Summarization"},"content":{"rendered":"<div class=\"asset-content\">\n<p>The emergence of wearable devices such as portable cameras and smart glasses makes it possible to record life logging first-person videos. Browsing such long unstructured videos is time-consuming and tedious. This paper studies the discovery of moments of user\u2019s major or special interest (i.e., highlights) in a video, for generating the summarization of first-person videos. Specifically, we propose a novel pairwise deep ranking model that employs deep learning techniques to learn the relationship between highlight and non-highlight video segments. A two-stream network structure by representing video segments from complementary information on appearance of video frames and temporal dynamics across frames is developed for video highlight detection. Given a long personal video, equipped with the highlight detection model, a highlight score is assigned to each segment. The obtained highlight segments are applied for summarization in two ways: video timelapse and video skimming. The former plays the highlight (non-highlight) segments at low (high) speed rates, while the latter assembles the sequence of segments with the highest scores. On 100 hours of first-person videos for 15 unique sports categories, our highlight detection achieves the improvement over the state-of-the-art RankSVM method by 10.5% in terms of accuracy. Moreover, our approaches produce video summary with better quality by a user study from 35 human subjects.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>The emergence of wearable devices such as portable cameras and smart glasses makes it possible to record life logging first-person videos. Browsing such long unstructured videos is time-consuming and tedious. This paper studies the discovery of moments of user\u2019s major or special interest (i.e., highlights) in a video, for generating the summarization of first-person videos. [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13562,13551],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-238200","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-computer-vision","msr-research-area-graphics-and-multimedia","msr-locale-en_us"],"msr_publishername":"","msr_edition":"Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)","msr_affiliation":"","msr_published_date":"2016-06-01","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"238473","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"Yao%20CVPR16%20-%20Highlight%20Detection%20with%20Pairwise%20Deep%20Ranking.pdf","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/Yao20CVPR1620-20Highlight20Detection20with20Pairwise20Deep20Ranking-1.pdf","id":238473,"label_id":0},{"type":"file","title":"2219.pdf","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/2219-1.pdf","id":238474,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":238473,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/Yao20CVPR1620-20Highlight20Detection20with20Pairwise20Deep20Ranking-1.pdf"},{"id":238474,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/2219-1.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"tiyao","user_id":34069,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=tiyao"},{"type":"user_nicename","value":"tmei","user_id":34188,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=tmei"},{"type":"user_nicename","value":"yongrui","user_id":35040,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=yongrui"}],"msr_impact_theme":[],"msr_research_lab":[199560],"msr_event":[],"msr_group":[144916],"msr_project":[239357,212087],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/238200"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/238200\/revisions"}],"predecessor-version":[{"id":519382,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/238200\/revisions\/519382"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=238200"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=238200"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=238200"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=238200"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=238200"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=238200"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=238200"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=238200"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=238200"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=238200"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=238200"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=238200"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=238200"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=238200"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=238200"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}