Recognizing and understanding conversational groups, or F-formations, is a critical task for situated agents designed to interact with humans. F-formations contain complex structures and dynamics, yet are used intuitively by people in everyday face-to-face conversations. Prior research exploring ways of identifying F-formations has largely relied on heuristic algorithms that may not capture the rich dynamic behaviors employed by humans. We introduce REFORM (REcognize F-FORmations with Machine learning), a data-driven approach for detecting F-formations given human and agent positions and orientations. REFORM decomposes the scene into all possible pairs and then reconstructs F-formations with a voting-based scheme. We evaluated our approach across three datasets: the SALSA dataset, a newly collected human-only dataset, and a new set of acted human-robot scenarios, and found that REFORM yielded improved accuracy over a state-of-the-art F-formation detection algorithm. We also introduce symmetry and tightness as quantitative measures to characterize F-formations. Supplementary video: this https URL , Dataset available at: this http URL<\/p>\n","protected":false},"excerpt":{"rendered":"
Recognizing and understanding conversational groups, or F-formations, is a critical task for situated agents designed to interact with humans. F-formations contain complex structures and dynamics, yet are used intuitively by people in everyday face-to-face conversations. Prior research exploring ways of identifying F-formations has largely relied on heuristic algorithms that may not capture the rich dynamic […]<\/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":[13556],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[246694,246691,246898,246685,249001,249004,249013],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-714820","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-field-of-study-artificial-intelligence","msr-field-of-study-computer-science","msr-field-of-study-heuristic","msr-field-of-study-machine-learning","msr-field-of-study-situated","msr-field-of-study-social-robot","msr-field-of-study-voting"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2020-8-16","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":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/arxiv.org\/pdf\/2008.07668","label_id":"243132","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/export.arxiv.org\/pdf\/2008.07668","label_id":"243132","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/arxiv.org\/abs\/2008.07668","label_id":"243109","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/dblp.uni-trier.de\/db\/journals\/corr\/corr2008.html#abs-2008-07668","label_id":"243109","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/export.arxiv.org\/abs\/2008.07668","label_id":"243109","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/il.arxiv.org\/abs\/2008.07668","label_id":"243109","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/www.arxiv-vanity.com\/papers\/2008.07668\/","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Hooman Hedayati","user_id":0,"rest_url":false},{"type":"text","value":"Annika Muehlbradt","user_id":0,"rest_url":false},{"type":"text","value":"Daniel J. Szafir","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Sean Andrist","user_id":36443,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Sean Andrist"}],"msr_impact_theme":[],"msr_research_lab":[199565],"msr_event":[],"msr_group":[144633],"msr_project":[390800],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/714820"}],"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\/714820\/revisions"}],"predecessor-version":[{"id":714823,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/714820\/revisions\/714823"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=714820"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=714820"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=714820"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=714820"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=714820"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=714820"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=714820"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=714820"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=714820"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=714820"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=714820"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=714820"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=714820"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=714820"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=714820"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}