{"id":"https://openalex.org/W4388117494","doi":"https://doi.org/10.23919/eusipco58844.2023.10289877","title":"Generating Salient Scene Graphs with Weak Language Supervision","display_name":"Generating Salient Scene Graphs with Weak Language Supervision","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388117494","doi":"https://doi.org/10.23919/eusipco58844.2023.10289877"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10289877","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco58844.2023.10289877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","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/A5049864577","display_name":"Alexandros Benetatos","orcid":null},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Alexandros Benetatos","raw_affiliation_strings":["National Technical University of Athens (NTUA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Technical University of Athens (NTUA)","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089189446","display_name":"Markos Diomataris","orcid":"https://orcid.org/0000-0002-1112-0193"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Markos Diomataris","raw_affiliation_strings":["deeplab.ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"deeplab.ai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040922549","display_name":"Vassilis Pitsikalis","orcid":"https://orcid.org/0000-0002-1593-7491"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vassilis Pitsikalis","raw_affiliation_strings":["deeplab.ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"deeplab.ai","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079243420","display_name":"Petros Maragos","orcid":"https://orcid.org/0000-0003-0534-2707"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Petros Maragos","raw_affiliation_strings":["National Technical University of Athens (NTUA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Technical University of Athens (NTUA)","institution_ids":["https://openalex.org/I174458059"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4254,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.63122333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"526","last_page":"530"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":0.996999979019165,"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/T10028","display_name":"Topic Modeling","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.7190167307853699},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.695170521736145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6261105537414551},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.623242974281311},{"id":"https://openalex.org/keywords/predicate","display_name":"Predicate (mathematical logic)","score":0.5298789739608765},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5294515490531921},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5140405893325806},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.42239320278167725},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4220837652683258},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4186502695083618},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39607298374176025},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33351826667785645},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.22219040989875793},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10679441690444946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7190167307853699},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.695170521736145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6261105537414551},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.623242974281311},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.5298789739608765},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5294515490531921},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5140405893325806},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.42239320278167725},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4220837652683258},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4186502695083618},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39607298374176025},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33351826667785645},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.22219040989875793},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10679441690444946},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10289877","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco58844.2023.10289877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2081580037","https://openalex.org/W2097606805","https://openalex.org/W2222512263","https://openalex.org/W2250378130","https://openalex.org/W2277195237","https://openalex.org/W2479423890","https://openalex.org/W2506483933","https://openalex.org/W2579549467","https://openalex.org/W2591644541","https://openalex.org/W2947385066","https://openalex.org/W2963514444","https://openalex.org/W2963980128","https://openalex.org/W2992195701","https://openalex.org/W3034910302","https://openalex.org/W3035068358","https://openalex.org/W3118006287","https://openalex.org/W3184370138","https://openalex.org/W3198299822","https://openalex.org/W3201670572","https://openalex.org/W3201890160","https://openalex.org/W4304092470","https://openalex.org/W6639102338","https://openalex.org/W6725318829","https://openalex.org/W6763119976","https://openalex.org/W6783483657"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W2329500892","https://openalex.org/W1974414866","https://openalex.org/W28991112","https://openalex.org/W2149051193","https://openalex.org/W2293263892"],"abstract_inverted_index":{"Scene":[0],"Graph":[1],"Generation":[2],"(SGG),":[3],"given":[4],"an":[5,70],"image,":[6],"is":[7,48],"the":[8,37,56,101,107,136],"task":[9],"of":[10,58,100,109,135],"building":[11],"directed":[12],"graphs":[13],"where":[14,124],"edges":[15],"represent":[16],"predicted":[17],"<subject":[18],"-":[19,21,43,45],"predicate":[20],"object>":[22],"triplets.":[23],"Most":[24],"SGG":[25,63,88,110],"models":[26,89,111],"struggle":[27],"to":[28,51,128,133],"identify":[29],"important":[30],"and":[31,76,112,116],"descriptive":[32],"relations":[33,75],"in":[34,60,122],"images":[35],"flooding":[36],"graph":[38],"with":[39,90,119],"triplets":[40],"like":[41],"<window":[42],"on":[44],"building>.":[46],"This":[47],"not":[49],"due":[50],"training":[52,87],"problems":[53],"but":[54],"rather":[55],"lack":[57],"saliency":[59,79,108],"fully":[61],"supervised":[62],"datasets.":[64],"Hence,":[65],"observing":[66],"that":[67],"annotators":[68],"describing":[69],"image":[71,78,94],"naturally":[72],"omit":[73],"background":[74],"encode":[77],"we":[80,125],"(i)":[81],"introduce":[82,97],"a":[83],"generalized":[84],"method":[85],"for":[86],"weak":[91],"supervision":[92],"using":[93],"captions,":[95],"(ii)":[96],"two":[98],"variations":[99],"Recall@N":[102],"metric":[103],"which":[104],"can":[105],"quantify":[106],"(iii)":[113],"perform":[114],"quantitative":[115],"qualitative":[117],"comparisons":[118],"related":[120],"literature":[121],"VG200,":[123],"achieve":[126],"up":[127],"35":[129],"%":[130],"improvement":[131],"compared":[132],"re-implementation":[134],"SOTA.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}