{"id":"https://openalex.org/W100802810","doi":null,"title":"Beyond histograms: why learned structure-preserving descriptors outperform HOG.","display_name":"Beyond histograms: why learned structure-preserving descriptors outperform HOG.","publication_year":2014,"publication_date":"2014-04-23","ids":{"openalex":"https://openalex.org/W100802810","mag":"100802810"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.639.6127","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.639.6127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2014-168.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059840903","display_name":"Thomas Guthier","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Guthier","raw_affiliation_strings":["Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001777411","display_name":"Volker Willert","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Volker Willert","raw_affiliation_strings":["Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039532032","display_name":"Julian P. Eggert","orcid":"https://orcid.org/0000-0003-4437-6133","observed_orcids":["https://orcid.org/0000-0003-4437-6133"]},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Julian Eggert","raw_affiliation_strings":["Honda (Japan), Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4437-6133","affiliations":[{"raw_affiliation_string":"Honda (Japan), Tokyo, Japan","institution_ids":["https://openalex.org/I1283473643"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00352201,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.5083000063896179,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.5083000063896179,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.22110000252723694,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.16110000014305115,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hog","display_name":"HOG","score":0.5929999947547913},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"non-negative matrix factorization","score":0.8999999761581421},{"id":"https://openalex.org/keywords/histograms","display_name":"histograms","score":0.5059999823570251},{"id":"https://openalex.org/keywords/spatial-topology","display_name":"spatial topology","score":0.7310000061988831},{"id":"https://openalex.org/keywords/human-action-recognition","display_name":"human action recognition","score":0.8569999933242798},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.5550000071525574}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8275913596153259},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.8199126720428467},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7855005264282227},{"id":"https://openalex.org/C61265191","wikidata":"https://www.wikidata.org/wiki/Q767770","display_name":"Scale-invariant feature transform","level":3,"score":0.7709039449691772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7662866115570068},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.632195234298706},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4333106577396393},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4322145879268646},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38850635290145874},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3422919511795044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3301125764846802},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.639.6127","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.639.6127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2014-168.pdf","raw_type":"text"},{"id":"mag:100802810","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/esann/esann2014.html#GuthierWE14","pdf_url":null,"source":{"id":"https://openalex.org/S4306421047","display_name":"The European Symposium on Artificial Neural Networks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"The European Symposium on Artificial Neural Networks","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W104847522","https://openalex.org/W1595717062","https://openalex.org/W1999192586","https://openalex.org/W2000364018","https://openalex.org/W2010399676","https://openalex.org/W2068611653","https://openalex.org/W2101194540","https://openalex.org/W2130789253","https://openalex.org/W2145734611","https://openalex.org/W2151103935","https://openalex.org/W2153635508","https://openalex.org/W2401783824"],"related_works":["https://openalex.org/W3014703635","https://openalex.org/W2538361501","https://openalex.org/W2750434779","https://openalex.org/W7099756319","https://openalex.org/W2791497948","https://openalex.org/W2803693645","https://openalex.org/W2007057255","https://openalex.org/W2138201914","https://openalex.org/W6903732497","https://openalex.org/W2342784309"],"abstract_inverted_index":{"Statistical":[0],"image":[1,15],"descriptors":[2],"based":[3],"on":[4,102],"histograms":[5,56],"(e.g.":[6],"SIFT":[7],"[1],":[8],"HOG":[9,49,90],"[2])":[10],"are":[11,19],"widely":[12],"used":[13],"in":[14,41],"processing,":[16],"because":[17,92],"they":[18,29],"fast":[20],"and":[21,35,50],"simple":[22],"methods":[23],"with":[24],"high":[25],"classification":[26],"performance.":[27],"However,":[28],"discard":[30],"the":[31,42,46,79,88],"local":[32],"spatial":[33,95],"topology":[34,96],"thus":[36],"lose":[37],"discriminative":[38],"information":[39],"contained":[40],"image.":[43],"We":[44],"discuss":[45],"relations":[47],"between":[48],"VNMF":[51,61,85],"descriptors,":[52],"i.e.":[53],"structure":[54],"free":[55],"ver-sus":[57],"learned":[58],"structure-preserving":[59],"patterns.":[60],"is":[62],"a":[63,75],"shift-invariant,":[64],"sparse,":[65],"non-negative":[66],"unsupervised":[67],"learning":[68],"algorithm":[69],"[8,":[70],"9,":[71],"5],":[72],"that":[73],"provides":[74],"distinct":[76],"decom-position":[77],"of":[78],"input":[80],"into":[81],"its":[82],"parts.":[83],"The":[84],"descriptor":[86],"outperforms":[87],"statistical":[89],"descriptor,":[91],"it":[93],"preserves":[94],"leading":[97],"to":[98],"better":[99],"classifica-tion":[100],"results":[101],"real-world":[103],"human":[104],"action":[105],"recognition":[106],"benchmarks":[107],"[11,":[108],"12].":[109],"1":[110]},"counts_by_year":[],"updated_date":"2026-10-01T08:54:57.152042","created_date":"2016-06-24T00:00:00"}