ConceptVision: A Flexible Scene Classification Framework
We introduce ConceptVision, a method that aims for high accuracy in categorizing large number of scenes, while keeping the model relatively simpler and efficient for scalability. The proposed method combines the advantages of both low-level representations and high-level semantic categories, and eli...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Iscen, Ahmet Golge, Eren Sarac, Ilker Duygulu, Pinar |
| description | We introduce ConceptVision, a method that aims for high accuracy in
categorizing large number of scenes, while keeping the model relatively simpler
and efficient for scalability. The proposed method combines the advantages of
both low-level representations and high-level semantic categories, and
eliminates the distinctions between different levels through the definition of
concepts. The proposed framework encodes the perspectives brought through
different concepts by considering them in concept groups. Different
perspectives are ensembled for the final decision. Extensive experiments are
carried out on benchmark datasets to test the effects of different concepts,
and methods used to ensemble. Comparisons with state-of-the-art studies show
that we can achieve better results with incorporation of concepts in different
levels with different perspectives. |
| doi_str_mv | 10.48550/arxiv.1401.0733 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1401_0733</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1401_0733</sourcerecordid><originalsourceid>FETCH-LOGICAL-a653-29faf57ecb7e0bd1ef874139a9fd958a2e855652e7c49f414fb5786448a0d2cc3</originalsourceid><addsrcrecordid>eNotj71qwzAURrV0KE73TkEvYFeyJEvKFkydFAIZarqaa_kKRPwT5NCmb1-77fQth49zCHnmLJNGKfYC8R4-My4Zz5gW4pGYchodXm8fYQ7TuKN7WvV4D22P9N3hiLTsYZ6DDw5uC0CrCAN-TfGyIQ8e-hmf_jchdfVal8f0dD68lftTCoUSaW49eKXRtRpZ23H0RksuLFjfWWUgx0WrUDlqJ62XXPpWaVNIaYB1uXMiIdu_21_z5hrDAPG7WQuatUD8ABXGQGc</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>ConceptVision: A Flexible Scene Classification Framework</title><source>arXiv.org</source><creator>Iscen, Ahmet ; Golge, Eren ; Sarac, Ilker ; Duygulu, Pinar</creator><creatorcontrib>Iscen, Ahmet ; Golge, Eren ; Sarac, Ilker ; Duygulu, Pinar</creatorcontrib><description>We introduce ConceptVision, a method that aims for high accuracy in
categorizing large number of scenes, while keeping the model relatively simpler
and efficient for scalability. The proposed method combines the advantages of
both low-level representations and high-level semantic categories, and
eliminates the distinctions between different levels through the definition of
concepts. The proposed framework encodes the perspectives brought through
different concepts by considering them in concept groups. Different
perspectives are ensembled for the final decision. Extensive experiments are
carried out on benchmark datasets to test the effects of different concepts,
and methods used to ensemble. Comparisons with state-of-the-art studies show
that we can achieve better results with incorporation of concepts in different
levels with different perspectives.</description><identifier>DOI: 10.48550/arxiv.1401.0733</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2014-01</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1401.0733$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1401.0733$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Iscen, Ahmet</creatorcontrib><creatorcontrib>Golge, Eren</creatorcontrib><creatorcontrib>Sarac, Ilker</creatorcontrib><creatorcontrib>Duygulu, Pinar</creatorcontrib><title>ConceptVision: A Flexible Scene Classification Framework</title><description>We introduce ConceptVision, a method that aims for high accuracy in
categorizing large number of scenes, while keeping the model relatively simpler
and efficient for scalability. The proposed method combines the advantages of
both low-level representations and high-level semantic categories, and
eliminates the distinctions between different levels through the definition of
concepts. The proposed framework encodes the perspectives brought through
different concepts by considering them in concept groups. Different
perspectives are ensembled for the final decision. Extensive experiments are
carried out on benchmark datasets to test the effects of different concepts,
and methods used to ensemble. Comparisons with state-of-the-art studies show
that we can achieve better results with incorporation of concepts in different
levels with different perspectives.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj71qwzAURrV0KE73TkEvYFeyJEvKFkydFAIZarqaa_kKRPwT5NCmb1-77fQth49zCHnmLJNGKfYC8R4-My4Zz5gW4pGYchodXm8fYQ7TuKN7WvV4D22P9N3hiLTsYZ6DDw5uC0CrCAN-TfGyIQ8e-hmf_jchdfVal8f0dD68lftTCoUSaW49eKXRtRpZ23H0RksuLFjfWWUgx0WrUDlqJ62XXPpWaVNIaYB1uXMiIdu_21_z5hrDAPG7WQuatUD8ABXGQGc</recordid><startdate>20140103</startdate><enddate>20140103</enddate><creator>Iscen, Ahmet</creator><creator>Golge, Eren</creator><creator>Sarac, Ilker</creator><creator>Duygulu, Pinar</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20140103</creationdate><title>ConceptVision: A Flexible Scene Classification Framework</title><author>Iscen, Ahmet ; Golge, Eren ; Sarac, Ilker ; Duygulu, Pinar</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a653-29faf57ecb7e0bd1ef874139a9fd958a2e855652e7c49f414fb5786448a0d2cc3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Iscen, Ahmet</creatorcontrib><creatorcontrib>Golge, Eren</creatorcontrib><creatorcontrib>Sarac, Ilker</creatorcontrib><creatorcontrib>Duygulu, Pinar</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Iscen, Ahmet</au><au>Golge, Eren</au><au>Sarac, Ilker</au><au>Duygulu, Pinar</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>ConceptVision: A Flexible Scene Classification Framework</atitle><date>2014-01-03</date><risdate>2014</risdate><abstract>We introduce ConceptVision, a method that aims for high accuracy in
categorizing large number of scenes, while keeping the model relatively simpler
and efficient for scalability. The proposed method combines the advantages of
both low-level representations and high-level semantic categories, and
eliminates the distinctions between different levels through the definition of
concepts. The proposed framework encodes the perspectives brought through
different concepts by considering them in concept groups. Different
perspectives are ensembled for the final decision. Extensive experiments are
carried out on benchmark datasets to test the effects of different concepts,
and methods used to ensemble. Comparisons with state-of-the-art studies show
that we can achieve better results with incorporation of concepts in different
levels with different perspectives.</abstract><doi>10.48550/arxiv.1401.0733</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.1401.0733 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_1401_0733 |
| source | arXiv.org |
| subjects | Computer Science - Computer Vision and Pattern Recognition |
| title | ConceptVision: A Flexible Scene Classification Framework |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T06%3A24%3A25IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=ConceptVision:%20A%20Flexible%20Scene%20Classification%20Framework&rft.au=Iscen,%20Ahmet&rft.date=2014-01-03&rft_id=info:doi/10.48550/arxiv.1401.0733&rft_dat=%3Carxiv_GOX%3E1401_0733%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |