{"id":163099,"date":"2012-01-01T00:00:00","date_gmt":"2012-01-01T00:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/spring-lattice-counting-grids-scene-recognition-using-deformable-positional-constraints\/"},"modified":"2018-10-16T21:32:48","modified_gmt":"2018-10-17T04:32:48","slug":"spring-lattice-counting-grids-scene-recognition-using-deformable-positional-constraints","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/spring-lattice-counting-grids-scene-recognition-using-deformable-positional-constraints\/","title":{"rendered":"Spring Lattice Counting Grids: Scene Recognition Using Deformable Positional Constraints"},"content":{"rendered":"<div class=\"asset-content\">\n<p>Adopting the Counting Grid (CG) representation [1], the Spring Lattice Counting Grid (SLCG) model uses a grid of feature counts to capture the spatial layout that a variety of images tend to follow. The images are mapped to the counting grid with their features rearranged so as to strike a balance between the mapping quality and the extent of the necessary rearrangement. In particular, the feature sets originating from different image sectors are mapped to different sub-windows in the count ing grid in a configuration that is close, but not exactly the same as the configuration of the source sectors. The distribution over deformations of the sector configuration is learnable using a new spring lattice model, while the rearrangement of features within a sector is unconstrained. As a result, the CG model gains a more appropriate level of invariance to realistic image transformations like view point changes, rotations or scales. We tested SLCG on standard scene recognition datasets and on a dataset collected with a wearable camera which recorded the wearer&#8217;s visual input over three weeks. Our algorithm is capable of correctly classifying the visited locations more than 80% of the time, outperforming previous approaches to visual location recognition. At this level of performance, a variety of real-world applications of wearable cameras become feasible.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Adopting the Counting Grid (CG) representation [1], the Spring Lattice Counting Grid (SLCG) model uses a grid of feature counts to capture the spatial layout that a variety of images tend to follow. The images are mapped to the counting grid with their features rearranged so as to strike a balance between the mapping quality [&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":[13552],"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-163099","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-hardware-devices","msr-locale-en_us"],"msr_publishername":"","msr_edition":"European Conference on Computer Vision (ECCV)","msr_affiliation":"","msr_published_date":"2012-01-01","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":"219589","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"eccv_cr.pdf","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2012\/01\/eccv_cr.pdf","id":219589,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":219589,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2012\/01\/eccv_cr.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"alperina","user_id":30958,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=alperina"},{"type":"user_nicename","value":"jojic","user_id":32384,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=jojic"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/163099"}],"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\/163099\/revisions"}],"predecessor-version":[{"id":415934,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/163099\/revisions\/415934"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=163099"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=163099"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=163099"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=163099"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=163099"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=163099"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=163099"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=163099"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=163099"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=163099"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=163099"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=163099"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=163099"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=163099"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=163099"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}