{"id":238199,"date":"2014-07-01T00:00:00","date_gmt":"2014-07-01T07:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/click-through-based-cross-view-learning-for-image-search-2\/"},"modified":"2018-10-16T20:01:51","modified_gmt":"2018-10-17T03:01:51","slug":"click-through-based-cross-view-learning-for-image-search-2","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/click-through-based-cross-view-learning-for-image-search-2\/","title":{"rendered":"Click-through-based Cross-view Learning for Image Search"},"content":{"rendered":"<div class=\"asset-content\">\n<p>One of the fundamental problems in image search is to rank image documents according to a given textual query. Existing search engines highly depend on surrounding texts for ranking images, or leverage the query-image pairs annotated by human labelers to train a series of ranking functions. However, there are two major limitations: 1) the surrounding texts are often noisy or too few to accurately describe the image content, and 2) the human annotations are resourcefully expensive and thus cannot be scaled up.<\/p>\n<p>We demonstrate in this paper that the above two fundamental challenges can be mitigated by jointly exploring the cross-view learning and the use of click-through data. The former aims to create a latent subspace with the ability in comparing information from the original incomparable views (i.e., textual and visual views), while the latter explores the largely available and freely accessible click-through data (i.e., \u201ccrowdsourced\u201d human intelligence) for understanding query. Specifically, we propose a novel cross-view learning method for image search, named Click-through-based Crossview Learning (CCL), by jointly minimizing the distance between the mappings of query and image in the latent subspace and preserving the inherent structure in each original space. On a large-scale click-based image dataset, CCL achieves the improvement over Support Vector Machinebased method by 4.0% in terms of relevance, while reducing the feature dimension by several orders of magnitude (e.g., from thousands to tens). Moreover, the experiments also demonstrate the superior performance of CCL to several state-of-the-art subspace learning techniques.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>One of the fundamental problems in image search is to rank image documents according to a given textual query. Existing search engines highly depend on surrounding texts for ranking images, or leverage the query-image pairs annotated by human labelers to train a series of ranking functions. However, there are two major limitations: 1) the surrounding [&hellip;]<\/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":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13562,13551,13555],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-238199","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-computer-vision","msr-research-area-graphics-and-multimedia","msr-research-area-search-information-retrieval","msr-locale-en_us"],"msr_publishername":"","msr_edition":"ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","msr_affiliation":"","msr_published_date":"2014-07-01","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":"238472","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"Pan%20SIGIR14%20-%20Click-through-based%20Cross-view%20Learning%20for%20Image%20Search.pdf","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/Pan20SIGIR1420-20Click-through-based20Cross-view20Learning20for20Image20Search-1.pdf","id":238472,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":238472,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/Pan20SIGIR1420-20Click-through-based20Cross-view20Learning20for20Image20Search-1.pdf"}],"msr-author-ordering":[{"type":"text","value":"Yingwei Pan","user_id":0,"rest_url":false},{"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":"text","value":"Houqiang Li","user_id":0,"rest_url":false},{"type":"text","value":"Chong-Wah Ngo","user_id":0,"rest_url":false},{"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":[],"msr_event":[],"msr_group":[144916],"msr_project":[212087],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":212087,"post_title":"Vision and Language","post_name":"video-and-language","post_type":"msr-project","post_date":"2016-01-14 20:03:50","post_modified":"2021-05-13 02:20:33","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/video-and-language\/","post_excerpt":"Automatically describing visual content with natural language is a fundamental challenge of computer vision and multimedia. Sequence learning (e.g., Recurrent Neural Networks), attention mechanism, memory networks,\u00a0etc.,\u00a0have attracted increasing attention on visual interpretation. In this project, we are focusing on the following topics related to the emerging topic of \"vision and language\": Image and video captioning, including MSR-VTT video to language grand challenge and datasets (http:\/\/ms-multimedia-challenge.com\/). Image and video commenting (conversation) Visual storytelling (e.g., generation of&hellip;","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/212087"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/238199","targetHints":{"allow":["GET"]}}],"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\/238199\/revisions"}],"predecessor-version":[{"id":519316,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/238199\/revisions\/519316"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=238199"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=238199"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=238199"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=238199"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=238199"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=238199"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=238199"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=238199"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=238199"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=238199"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=238199"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=238199"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=238199"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=238199"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=238199"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=238199"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}