{"id":"https://openalex.org/W4405896160","doi":"https://doi.org/10.1007/s40747-024-01746-z","title":"Semantic-enhanced panoptic scene graph generation through hybrid and axial attentions","display_name":"Semantic-enhanced panoptic scene graph generation through hybrid and axial attentions","publication_year":2024,"publication_date":"2024-12-30","ids":{"openalex":"https://openalex.org/W4405896160","doi":"https://doi.org/10.1007/s40747-024-01746-z"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-024-01746-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01746-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01746-z.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01746-z.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xinhe Kuang","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinhe Kuang","raw_affiliation_strings":["Sydney Smart Technology College, Northeastern University, Qinhuangdao, 066004, China"],"affiliations":[{"raw_affiliation_string":"Sydney Smart Technology College, Northeastern University, Qinhuangdao, 066004, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033811167","display_name":"Yuxin Che","orcid":null},"institutions":[{"id":"https://openalex.org/I135714990","display_name":"North University of China","ror":"https://ror.org/047bp1713","country_code":"CN","type":"education","lineage":["https://openalex.org/I135714990"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Che","raw_affiliation_strings":["School of Computer Science and Technology, North University of China, Taiyuan, 030051, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, North University of China, Taiyuan, 030051, China","institution_ids":["https://openalex.org/I135714990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055710985","display_name":"Huiyan Han","orcid":"https://orcid.org/0000-0001-8387-8633"},"institutions":[{"id":"https://openalex.org/I135714990","display_name":"North University of China","ror":"https://ror.org/047bp1713","country_code":"CN","type":"education","lineage":["https://openalex.org/I135714990"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiyan Han","raw_affiliation_strings":["School of Computer Science and Technology, North University of China, Taiyuan, 030051, China","Shanxi Key Laboratory of Machine Vision and Virtual Reality, Taiyuan, 030051, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, North University of China, Taiyuan, 030051, China","institution_ids":["https://openalex.org/I135714990"]},{"raw_affiliation_string":"Shanxi Key Laboratory of Machine Vision and Virtual Reality, Taiyuan, 030051, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103089519","display_name":"Yimin Liu","orcid":"https://orcid.org/0000-0002-1547-1177"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yimin Liu","raw_affiliation_strings":["Shanxi Center of Technology Innovation for Digital and Intelligent Integration of Cultural and Tourism Information, Taiyuan, 030031, China","Shanxi Cultural Tourism Group Information Technology Co., Ltd, Taiyuan, 030031, China"],"affiliations":[{"raw_affiliation_string":"Shanxi Center of Technology Innovation for Digital and Intelligent Integration of Cultural and Tourism Information, Taiyuan, 030031, China","institution_ids":["https://openalex.org/I181877577"]},{"raw_affiliation_string":"Shanxi Cultural Tourism Group Information Technology Co., Ltd, Taiyuan, 030031, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":0.7223,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73459525,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"11","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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":0.995199978351593,"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/computational-intelligence","display_name":"Computational intelligence","score":0.6829891204833984},{"id":"https://openalex.org/keywords/panopticon","display_name":"Panopticon","score":0.6533474922180176},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5354355573654175},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5286431908607483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.499114990234375},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37688469886779785},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3237917423248291},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3201720714569092},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.31166762113571167},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.1708633303642273}],"concepts":[{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.6829891204833984},{"id":"https://openalex.org/C138569888","wikidata":"https://www.wikidata.org/wiki/Q828310","display_name":"Panopticon","level":3,"score":0.6533474922180176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5354355573654175},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5286431908607483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.499114990234375},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37688469886779785},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3237917423248291},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3201720714569092},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31166762113571167},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.1708633303642273},{"id":"https://openalex.org/C2780430339","wikidata":"https://www.wikidata.org/wiki/Q10861465","display_name":"Brother","level":2,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-024-01746-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01746-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01746-z.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:96e1323cadbc466db32e20f788a19502","is_oa":true,"landing_page_url":"https://doaj.org/article/96e1323cadbc466db32e20f788a19502","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 11, Iss 1, Pp 1-15 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-024-01746-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01746-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01746-z.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1534702153","display_name":null,"funder_award_id":"62272426","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405896160.pdf","grobid_xml":"https://content.openalex.org/works/W4405896160.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W2155996867","https://openalex.org/W2277195237","https://openalex.org/W2579549467","https://openalex.org/W2910628332","https://openalex.org/W2963514444","https://openalex.org/W2963536419","https://openalex.org/W2963938081","https://openalex.org/W2965182628","https://openalex.org/W2999219213","https://openalex.org/W3096609285","https://openalex.org/W3108864070","https://openalex.org/W3181556077","https://openalex.org/W3203581965","https://openalex.org/W4200498145","https://openalex.org/W4226054716","https://openalex.org/W4309714908","https://openalex.org/W4312338297","https://openalex.org/W4312492610","https://openalex.org/W4312563197","https://openalex.org/W4312578903","https://openalex.org/W4312936847","https://openalex.org/W4313037583","https://openalex.org/W4366352717","https://openalex.org/W4382202846","https://openalex.org/W4382450240","https://openalex.org/W4382460199","https://openalex.org/W4386075842","https://openalex.org/W4387968400","https://openalex.org/W4393154528","https://openalex.org/W4396982232","https://openalex.org/W4401537510","https://openalex.org/W4402576334","https://openalex.org/W4402916696","https://openalex.org/W4402980606","https://openalex.org/W6603963165"],"related_works":["https://openalex.org/W2921107741","https://openalex.org/W2197002326","https://openalex.org/W2494728058","https://openalex.org/W3204968380","https://openalex.org/W1710116222","https://openalex.org/W2800383628","https://openalex.org/W2345320341","https://openalex.org/W4233922521","https://openalex.org/W2492288033","https://openalex.org/W2110567475"],"abstract_inverted_index":{"The":[0,133],"generation":[1,76],"of":[2,17,33,71,86,108,145],"panoramic":[3,73,166],"scene":[4,12,74,167,183],"graphs":[5,168],"represents":[6],"a":[7,68,84],"cutting-edge":[8],"challenge":[9],"in":[10,163,182],"image":[11],"understanding,":[13],"necessitating":[14],"sophisticated":[15],"predictions":[16,57],"both":[18,93],"intra-object":[19],"relationships":[20,41,181],"and":[21,25,52,79,98,106,110],"interactions":[22],"between":[23],"objects":[24],"their":[26],"backgrounds.":[27],"This":[28],"complexity":[29],"tests":[30],"the":[31,94,104,114,142,151,177],"limits":[32],"current":[34],"predictive":[35],"models'":[36],"ability":[37,144,178],"to":[38,48,56,140,179],"discern":[39],"nuanced":[40],"within":[42,92,123],"images.":[43],"Conventional":[44],"approaches":[45],"often":[46],"fail":[47],"effectively":[49],"combine":[50],"visual":[51,109],"semantic":[53,111],"data,":[54],"leading":[55],"that":[58,155],"are":[59,90],"semantically":[60],"impoverished.":[61],"To":[62],"address":[63],"these":[64],"issues,":[65],"we":[66],"propose":[67],"novel":[69],"method":[70],"semantic-enhanced":[72],"graph":[75,184],"through":[77],"hybrid":[78,87,115],"axial":[80,134],"attentions":[81],"(PSGAtten).":[82],"Specifically,":[83],"series":[85],"attention":[88,116,135],"networks":[89],"stacked":[91],"object":[95],"context":[96,100],"encoding":[97,101],"relationship":[99],"modules,":[102],"enhancing":[103,176],"refinement":[105,122],"fusion":[107,130],"information.":[112,147],"Within":[113],"networks,":[117],"self-attention":[118],"mechanisms":[119,127],"facilitate":[120],"feature":[121,129],"modalities,":[124],"while":[125],"cross-attention":[126],"promote":[128],"across":[131],"modalities.":[132],"model":[136],"is":[137],"further":[138],"applied":[139],"enhance":[141],"integration":[143],"global":[146],"Experimental":[148],"validation":[149],"on":[150],"PSG":[152],"dataset":[153],"confirms":[154],"our":[156],"approach":[157],"not":[158],"only":[159],"surpasses":[160],"existing":[161],"methods":[162],"generating":[164],"detailed":[165],"but":[169],"also":[170],"significantly":[171],"improves":[172],"recall":[173],"rates,":[174],"thereby":[175],"predict":[180],"generation.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}