Surveillance video parsing, which segments the video frames into several labels, e.g., face, pants, left-leg, has wide applications [38, 9]. However, pixel-wisely annotating all frames is tedious and inefficient. In this paper, we develop a Single frame Video Parsing (SVP) method which requires only one labeled frame per video in training stage. To parse one particular frame, the video segment preceding the frame is jointly considered. SVP (i) roughly parses the frames within the video segment, (ii) estimates the optical flow between frames and (iii) fuses the rough parsing results warped by optical flow to produce the refined parsing result. The three components of SVP, namely frame parsing, optical flow estimation and temporal fusion are integrated in an end-to-end manner. Experimental results on two surveillance video datasets show the superiority of SVP over state-of-the-arts.<\/p>\n","protected":false},"excerpt":{"rendered":"
Surveillance video parsing, which segments the video frames into several labels, e.g., face, pants, left-leg, has wide applications [38, 9]. However, pixel-wisely annotating all frames is tedious and inefficient. In this paper, we develop a Single frame Video Parsing (SVP) method which requires only one labeled frame per video in training stage. To parse one […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":null,"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"","msr_doi":"","msr_arxiv_id":"","msr_s2_paper_id":"","msr_mag_id":"","msr_pubmed_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_original_fields_of_study":"","msr_release_tracker_id":"","msr_s2_match_type":"","msr_citation_count_updated":"","msr_published_date":"2016-11-30","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_s2_pdf_url":"","msr_year":0,"msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_match_confidence":0,"msr_microsoftintellectualproperty":true,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13562],"msr-publication-type":[193715],"msr-publisher":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-329123","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-computer-vision","msr-locale-en_us"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2016-11-30","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":"329126","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"1611-09587v1","viewUrl":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-content\/uploads\/2016\/11\/1611.09587v1.pdf","id":329126,"label_id":0}],"msr_related_uploader":"","msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Si Liu","user_id":0,"rest_url":false},{"type":"user_nicename","value":"chw","user_id":31440,"rest_url":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=chw"},{"type":"text","value":"Ruihe Qian","user_id":0,"rest_url":false},{"type":"text","value":"Han Yu","user_id":0,"rest_url":false},{"type":"text","value":"Renda Bao","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[285614,212093],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"article","related_content":{"projects":[{"ID":285614,"post_title":"Image2Text","post_name":"image2text-2","post_type":"msr-project","post_date":"2016-08-30 20:14:19","post_modified":"2017-06-15 14:52:31","post_status":"publish","permalink":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/project\/image2text-2\/","post_excerpt":"We study the problem of image captioning, i.e., automatically describing an image by a sentence. This is a challenging problem, since different from other computer vision tasks such as image classi\ufb01cation and object detection, image captioning requires not only understanding the image, but also the knowledge of natural language. We formulate this problem as a multimodal translation task, and develop novel algorithms to solve this problem.","_links":{"self":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/285614"}]}},{"ID":212093,"post_title":"Image\/Video Understanding and Analysis","post_name":"image2text","post_type":"msr-project","post_date":"2016-01-25 01:52:15","post_modified":"2017-06-15 14:48:39","post_status":"publish","permalink":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/project\/image2text\/","post_excerpt":"We target at the core problems in image\/video understanding and analysis, such as image recognition, image segmentation, image captioning, image parsing, object detection, and video segmentation.","_links":{"self":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/212093"}]}}]},"_links":{"self":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/329123","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/329123\/revisions"}],"predecessor-version":[{"id":527924,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/329123\/revisions\/527924"}],"wp:attachment":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=329123"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=329123"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=329123"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=329123"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=329123"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=329123"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=329123"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=329123"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=329123"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=329123"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=329123"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=329123"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=329123"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}