{"id":"https://openalex.org/W4415401451","doi":"https://doi.org/10.1145/3746266.3762160","title":"Prospective Analysis of Semantic Image Retrieval: Comparing Scene Graph, Visual Features, and Captions","display_name":"Prospective Analysis of Semantic Image Retrieval: Comparing Scene Graph, Visual Features, and Captions","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415401451","doi":"https://doi.org/10.1145/3746266.3762160"},"language":null,"primary_location":{"id":"doi:10.1145/3746266.3762160","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746266.3762160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Deep Multimodal Generation and Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5047823141","display_name":"Takahiro Komamizu","orcid":"https://orcid.org/0000-0002-3041-4330"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takahiro Komamizu","raw_affiliation_strings":["Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3041-4330","affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5047823141"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"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":"47","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980999827384949,"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/pairwise-comparison","display_name":"Pairwise comparison","score":0.6330999732017517},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6017000079154968},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5910000205039978},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5803999900817871},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5608999729156494},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5527999997138977},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5422000288963318},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4763000011444092}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6840000152587891},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6330999732017517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6158000230789185},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6017000079154968},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5910000205039978},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5839999914169312},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5803999900817871},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5608999729156494},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5527999997138977},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5422000288963318},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49459999799728394},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4763000011444092},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.40529999136924744},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31209999322891235},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.30820000171661377},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.2863999903202057},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746266.3762160","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746266.3762160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Deep Multimodal Generation and Retrieval","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":22,"referenced_works":["https://openalex.org/W1983681808","https://openalex.org/W2008857988","https://openalex.org/W2046589280","https://openalex.org/W2111993661","https://openalex.org/W2124509324","https://openalex.org/W2559091987","https://openalex.org/W2620629206","https://openalex.org/W2903106696","https://openalex.org/W2905544595","https://openalex.org/W2963536419","https://openalex.org/W3026458074","https://openalex.org/W3137228985","https://openalex.org/W3175684172","https://openalex.org/W3188851454","https://openalex.org/W3205173298","https://openalex.org/W4310923309","https://openalex.org/W4312563197","https://openalex.org/W4386953147","https://openalex.org/W4390874121","https://openalex.org/W4401633552","https://openalex.org/W4403853618","https://openalex.org/W4404609192"],"related_works":[],"abstract_inverted_index":{"Semantic":[0],"image":[1,26,74,174],"retrieval":[2,75,155],"aims":[3],"to":[4,11,21,153],"retrieve":[5],"images":[6],"that":[7,112,129],"are":[8,88,99,117],"semantically":[9],"similar":[10],"a":[12,15,69],"query":[13],"image,":[14],"fundamental":[16],"yet":[17],"challenging":[18],"task":[19],"due":[20],"the":[22,91,142,163],"multifaceted":[23],"nature":[24],"of":[25,72,144,162],"semantics.":[27],"While":[28],"visual":[29,149],"feature":[30],"embeddings":[31,152],"and":[32,43,81,95,103,108,114,150,167,169],"caption-based":[33,82,151],"representations":[34,56],"have":[35],"achieved":[36],"strong":[37],"performance":[38],"in":[39],"capturing":[40],"global":[41],"appearance":[42],"descriptive":[44],"scene":[45],"semantics,":[46],"they":[47],"often":[48],"overlook":[49],"fine-grained":[50],"relational":[51,60,133],"structures":[52],"between":[53,97],"objects.":[54],"Scene-graph":[55],"explicitly":[57],"model":[58],"such":[59],"configurations,":[61],"offering":[62],"potentially":[63],"complementary":[64],"signals.":[65],"This":[66,157],"paper":[67,158],"presents":[68],"prospective":[70],"analysis":[71],"semantic":[73,173],"by":[76,137],"systematically":[77],"comparing":[78],"scene-graph,":[79],"visual,":[80],"similarity":[83,86,122,165],"measures.":[84],"Pairwise":[85],"scores":[87],"computed":[89],"on":[90],"Visual":[92,113],"Genome":[93],"dataset,":[94,168],"relationships":[96],"modalities":[98],"quantified":[100],"using":[101],"Pearson":[102],"Spearman":[104],"correlations.":[105],"Quantitative":[106],"metrics":[107],"qualitative":[109],"examples":[110],"illustrate":[111],"caption":[115],"similarities":[116],"strongly":[118],"correlated,":[119],"while":[120],"scene-graph":[121,146],"shows":[123],"weak":[124],"correlation":[125],"with":[126,148],"both,":[127],"suggesting":[128],"it":[130],"encodes":[131],"distinct":[132],"semantics":[134],"not":[135],"captured":[136],"embeddings.":[138],"These":[139],"observations":[140],"highlight":[141],"potential":[143],"integrating":[145],"information":[147],"improve":[154],"effectiveness.":[156],"further":[159],"discusses":[160],"limitations":[161],"current":[164],"measures":[166],"future":[170],"directions":[171],"for":[172],"retrieval.":[175]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-22T00:00:00"}