{"id":"https://openalex.org/W7131079828","doi":"https://doi.org/10.1109/iccvw69036.2025.00412","title":"AesCrop: Aesthetic-Driven Cropping Guided by Composition","display_name":"AesCrop: Aesthetic-Driven Cropping Guided by Composition","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131079828","doi":"https://doi.org/10.1109/iccvw69036.2025.00412"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5126619178","display_name":"Yen-Hong Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Yen-Hong Wong","raw_affiliation_strings":["Multimedia University Persiaran Multimedia,Faculty of Computing and Informatics,Cyberjaya,Selangor,Malaysia"],"affiliations":[{"raw_affiliation_string":"Multimedia University Persiaran Multimedia,Faculty of Computing and Informatics,Cyberjaya,Selangor,Malaysia","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126618289","display_name":"Lai-Kuan Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Lai-Kuan Wong","raw_affiliation_strings":["Multimedia University Persiaran Multimedia,Faculty of Computing and Informatics,Cyberjaya,Selangor,Malaysia"],"affiliations":[{"raw_affiliation_string":"Multimedia University Persiaran Multimedia,Faculty of Computing and Informatics,Cyberjaya,Selangor,Malaysia","institution_ids":["https://openalex.org/I173029219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5126619178"],"corresponding_institution_ids":["https://openalex.org/I173029219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.826768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3965","last_page":"3972"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12253","display_name":"Urban Agriculture and Sustainability","score":0.06830000132322311,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12253","display_name":"Urban Agriculture and Sustainability","score":0.06830000132322311,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11862","display_name":"Agriculture, Land Use, Rural Development","score":0.0608999989926815,"subfield":{"id":"https://openalex.org/subfields/1100","display_name":"General Agricultural and Biological Sciences"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12665","display_name":"Bamboo properties and applications","score":0.04529999941587448,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6744999885559082},{"id":"https://openalex.org/keywords/cropping","display_name":"Cropping","score":0.4699999988079071},{"id":"https://openalex.org/keywords/globality","display_name":"Globality","score":0.426800012588501},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4032999873161316},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4002000093460083},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.3700999915599823},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3628000020980835},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.36070001125335693}],"concepts":[{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6744999885559082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5871000289916992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5005999803543091},{"id":"https://openalex.org/C13558536","wikidata":"https://www.wikidata.org/wiki/Q785116","display_name":"Cropping","level":3,"score":0.4699999988079071},{"id":"https://openalex.org/C2778749631","wikidata":"https://www.wikidata.org/wiki/Q5570927","display_name":"Globality","level":3,"score":0.426800012588501},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4002000093460083},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3849000036716461},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.3456999957561493},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3021000027656555},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29179999232292175},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C160174412","wikidata":"https://www.wikidata.org/wiki/Q873806","display_name":"Thumbnail","level":3,"score":0.2815999984741211},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1975521048","https://openalex.org/W2586372171","https://openalex.org/W2798986039","https://openalex.org/W2807107013","https://openalex.org/W2964332053","https://openalex.org/W2973725754","https://openalex.org/W3034818671","https://openalex.org/W3110416571","https://openalex.org/W3186050100","https://openalex.org/W3202461321","https://openalex.org/W4214627427","https://openalex.org/W4312598291","https://openalex.org/W4382777567","https://openalex.org/W4386596832","https://openalex.org/W4390190485","https://openalex.org/W4393155962","https://openalex.org/W4403532799"],"related_works":[],"abstract_inverted_index":{"Aesthetic-driven":[0],"image":[1,110,129],"cropping":[2],"is":[3,26],"crucial":[4],"for":[5],"applications":[6],"like":[7],"view":[8],"recommendation":[9],"and":[10,44,76,121,173],"thumbnail":[11],"generation,":[12],"where":[13],"visual":[14,24],"appeal":[15,25],"significantly":[16],"impacts":[17],"user":[18],"engagement.":[19],"A":[20],"key":[21,89],"factor":[22],"in":[23],"composition-the":[27],"deliberate":[28],"arrangement":[29],"of":[30],"elements":[31],"within":[32],"an":[33],"image.":[34],"Some":[35],"methods":[36,49,54,81],"have":[37,64],"successfully":[38],"incorporated":[39],"compositional":[40,143],"knowledge":[41],"through":[42],"evaluation-based":[43,48],"regression-based":[45,53],"paradigms.":[46],"However,":[47],"lack":[50,55],"globality":[51],"while":[52],"diversity.":[56],"Recently,":[57],"hybrid":[58,80,103],"approaches":[59],"that":[60,91,106,163],"integrate":[61],"both":[62],"paradigms":[63],"emerged,":[65],"bridging":[66],"the":[67,136,146,155],"gap":[68],"between":[69],"these":[70],"two":[71],"to":[72,125,152],"achieve":[73],"better":[74],"diversity":[75],"globality.":[77],"Notably,":[78],"existing":[79],"do":[82],"not":[83],"incorporate":[84],"photographic":[85,93],"composition":[86],"guidance,":[87],"a":[88,101,108,114,122],"attribute":[90],"defines":[92],"aesthetics.":[94],"In":[95],"this":[96],"work,":[97],"we":[98],"introduce":[99],"AesCrop,":[100],"composition-aware":[102],"image-cropping":[104],"model":[105],"integrates":[107],"VMamba":[109],"encoder,":[111],"augmented":[112],"with":[113,135],"novel":[115],"Mamba":[116],"Composition":[117],"Attention":[118],"Bias":[119],"(MCAB)":[120],"transformer":[123],"decoder":[124],"perform":[126],"end-to-end":[127],"rank-based":[128],"cropping,":[130],"generating":[131],"multiple":[132],"crops":[133],"along":[134],"corresponding":[137],"quality":[138],"scores.":[139],"By":[140],"explicitly":[141],"encoding":[142],"cues":[144],"into":[145],"attention":[147],"mechanism,":[148],"MCAB":[149],"directs":[150],"AesCrop":[151,164],"focus":[153],"on":[154],"most":[156],"compositionally":[157],"salient":[158],"regions.":[159],"Extensive":[160],"experiments":[161],"demonstrate":[162],"outperforms":[165],"current":[166],"state-of-the-art":[167],"methods,":[168],"delivering":[169],"superior":[170],"quantitative":[171],"metrics":[172],"qualitatively":[174],"more":[175],"pleasing":[176],"crops.":[177]},"counts_by_year":[],"updated_date":"2026-02-25T06:17:34.324206","created_date":"2026-02-24T00:00:00"}