{"corpus_id":1577831,"paper_sha":"4c4db93ea130ba18bd2c53de2b22e213c6823ec8","doi":"10.1007/978-3-319-46448-0_40","arxiv_id":"1606.01621","pmid":null,"pmcid":null,"mag_id":2951262072,"dblp_id":"journals/corr/KongSLMF16","acl_id":null,"title":"Photo Aesthetics Ranking Network with Attributes and Content Adaptation","year":2016,"publication_date":"2016-06-06","venue":"European Conference on Computer Vision","journal":{"name":null,"pages":"662-679","volume":null},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle","Conference"],"pubmed_pub_types":null,"s2_fields_of_study":["Mathematics","Computer Science"],"reference_count":38,"citation_count":501,"influential_citation_count":118,"is_open_access":false,"arxiv_categories":["cs.CV","cs.IR","cs.MM"],"arxiv_license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":null,"s2_open_access_landing_url":null,"s2_open_access_license":null,"s2_open_access_status":null,"pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"Real-world applications could benefit from the ability to automatically generate a fine-grained ranking of photo aesthetics. However, previous methods for image aesthetics analysis have primarily focused on the coarse, binary categorization of images into high- or low-aesthetic categories. In this work, we propose to learn a deep convolutional neural network to rank photo aesthetics in which the relative ranking of photo aesthetics are directly modeled in the loss function. Our model incorporates joint learning of meaningful photographic attributes and image content information which can help regularize the complicated photo aesthetics rating problem.","claims":[{"public_id":"cl_845919da3c520252cafdf91ba662a92f","status":"active","text":"A deep convolutional neural network is proposed to rank photo aesthetics, directly modeling relative ranking in the loss function.","confidence":0.95,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/claims/cl_845919da3c520252cafdf91ba662a92f"},{"public_id":"cl_0402f251bc80ecf447b48936637c78ed","status":"active","text":"The model incorporates joint learning of meaningful photographic attributes and image content information to regularize the photo aesthetics rating problem.","confidence":0.9,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/claims/cl_0402f251bc80ecf447b48936637c78ed"}],"concepts":[{"public_id":"co_1c9b765e6421c5ec3d859327be8b0fdd","status":"active","name":"photo aesthetics ranking","description":"The task of generating a fine-grained ranking of photo aesthetics, as opposed to coarse binary categorization.","types":["task"],"aliases":["fine-grained aesthetics ranking"],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/concepts/co_1c9b765e6421c5ec3d859327be8b0fdd"},{"public_id":"co_215ac6d48fef764532da7587e072e867","status":"active","name":"image content information","description":"Content information from images that is jointly learned alongside photographic attributes to regularize aesthetics rating.","types":["feature"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/concepts/co_215ac6d48fef764532da7587e072e867"},{"public_id":"co_5cf77719da43d384b2e84ee736cea3b1","status":"active","name":"deep convolutional neural network","description":"A deep neural network architecture using convolutional layers, employed here to learn photo aesthetics ranking.","types":["method"],"aliases":["deep CNN"],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/concepts/co_5cf77719da43d384b2e84ee736cea3b1"},{"public_id":"co_61bb9f387d7f03cc331fc439e608da2b","status":"active","name":"relative ranking loss","description":"A loss function that directly models the relative ranking of photo aesthetics during training.","types":["method"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/concepts/co_61bb9f387d7f03cc331fc439e608da2b"},{"public_id":"co_692fdfaa7fdf3be02683240dc89d531a","status":"active","name":"photographic attributes","description":"Meaningful attributes of photographs that are jointly learned to help regularize the aesthetics rating problem.","types":["feature"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/concepts/co_692fdfaa7fdf3be02683240dc89d531a"},{"public_id":"co_8757d16ae70d21cdf35653dde2083e54","status":"active","name":"photo aesthetics rating","description":"The complicated problem of rating photo aesthetics, which the proposed model regularizes via joint learning of attributes and content.","types":["problem"],"aliases":["aesthetics rating problem"],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/concepts/co_8757d16ae70d21cdf35653dde2083e54"}],"external_ids":{"DOI":"10.1007/978-3-319-46448-0_40","ArXiv":"1606.01621","PubMed":null,"PubMedCentral":null,"MAG":2951262072,"DBLP":"journals/corr/KongSLMF16","ACL":null},"open_access":{"is_open_access":true,"pdf_url":"https://arxiv.org/pdf/1606.01621","landing_url":"https://arxiv.org/abs/1606.01621","source":"arxiv","pdf_url_source":"derived_arxiv","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","reason":null},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":true,"full_text_source":"arxiv","count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":635589,"paper_uid":"8d70d4e1-765a-467d-bbed-535fdd905093","canonical_identity":{"paper_id":635589,"paper_uid":"8d70d4e1-765a-467d-bbed-535fdd905093","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/1577831"}