{"id":"https://openalex.org/W7155043024","doi":"https://doi.org/10.48550/arxiv.2604.16500","title":"Semantically Stable Image Composition Analysis via Saliency and Gradient Vector Flow Fusion","display_name":"Semantically Stable Image Composition Analysis via Saliency and Gradient Vector Flow Fusion","publication_year":2026,"publication_date":"2026-04-14","ids":{"openalex":"https://openalex.org/W7155043024","doi":"https://doi.org/10.48550/arxiv.2604.16500"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.16500","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16500","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.16500","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134176583","display_name":"Armin Dadras","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dadras, Armin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019162549","display_name":"Robert Sablatnig","orcid":"https://orcid.org/0000-0003-4195-1593"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sablatnig, Robert","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134148256","display_name":"Franziska Proksa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Proksa, Franziska","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5014376065","display_name":"Markus Seidl","orcid":"https://orcid.org/0000-0002-7966-3602"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seidl, Markus","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9138000011444092,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9138000011444092,"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":0.014600000344216824,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.010700000450015068,"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/discriminative-model","display_name":"Discriminative model","score":0.788100004196167},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5895000100135803},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5220000147819519},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48500001430511475},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.45260000228881836},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4372999966144562},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43070000410079956},{"id":"https://openalex.org/keywords/vector-flow","display_name":"Vector flow","score":0.41260001063346863},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.39160001277923584}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.788100004196167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7146999835968018},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6912000179290771},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5895000100135803},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5220000147819519},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48500001430511475},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.45260000228881836},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43070000410079956},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4205999970436096},{"id":"https://openalex.org/C20749125","wikidata":"https://www.wikidata.org/wiki/Q7917826","display_name":"Vector flow","level":4,"score":0.41260001063346863},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.39160001277923584},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3612000048160553},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.34929999709129333},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.34709998965263367},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3068999946117401},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C167879884","wikidata":"https://www.wikidata.org/wiki/Q727568","display_name":"Balanced flow","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C182037307","wikidata":"https://www.wikidata.org/wiki/Q17039097","display_name":"Image gradient","level":5,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.16500","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16500","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.16500","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16500","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7898749113082886,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,60],"reliable":[1],"computational":[2],"assessment":[3],"of":[4,12,38],"photographic":[5],"composition":[6,31],"requires":[7],"features":[8,74,111],"that":[9,30,104],"are":[10],"discriminative":[11],"spatial":[13],"layout":[14],"yet":[15],"robust":[16],"to":[17],"semantic":[18],"content.":[19],"This":[20],"paper":[21],"proposes":[22],"a":[23,54,76,105],"low-level":[24],"representation":[25],"grounded":[26],"in":[27],"the":[28,36,84,97],"assumption":[29],"can":[32],"be":[33],"understood":[34],"as":[35],"flow":[37,57,73],"visual":[39],"attention":[40],"across":[41],"geometric":[42],"structure.":[43],"We":[44,101],"introduce":[45],"VFCNet,":[46],"which":[47],"fuses":[48],"saliency":[49],"and":[50,70,94],"edge":[51],"information":[52],"into":[53],"gradient":[55],"vector":[56],"(GVF)":[58],"field.":[59],"model":[61],"computes":[62],"dual-stream":[63],"GVF":[64],"representations,":[65],"integrates":[66],"them":[67],"via":[68],"attention,":[69],"extracts":[71],"multi-scale":[72],"with":[75],"DINOv3":[77,110],"backbone.":[78],"VFCNet":[79],"achieves":[80],"state-of-the-art":[81],"performance":[82],"on":[83,108],"PICD":[85],"benchmark":[86],"(CDA-1:":[87],"0.683,":[88],"CDA-2:":[89],"0.629),":[90],"improving":[91],"by":[92],"33.1\\%":[93],"36.1\\%":[95],"over":[96],"previous":[98],"best":[99],"method.":[100],"also":[102],"show":[103],"simple":[106],"classifier":[107],"self-supervised":[109],"substantially":[112],"outperforms":[113],"more":[114],"sophisticated,":[115],"composition-specialized":[116],"models.":[117],"Code":[118],"is":[119],"available":[120],"at":[121],"https://github.com/ADadras/VFCNet":[122]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-22T00:00:00"}