{"id":"https://openalex.org/W4408345923","doi":"https://doi.org/10.1109/icassp49660.2025.10887586","title":"LLaVA-SG: Leveraging Scene Graphs as Visual Semantic Expression in Vision-Language Models","display_name":"LLaVA-SG: Leveraging Scene Graphs as Visual Semantic Expression in Vision-Language Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345923","doi":"https://doi.org/10.1109/icassp49660.2025.10887586"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5015234413","display_name":"Jingyi Wang","orcid":"https://orcid.org/0009-0009-1198-2832"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingyi Wang","raw_affiliation_strings":["Tsinghua University,BNRist, THUAI,Department of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist, THUAI,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113407620","display_name":"Jianzhong Ju","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhong Ju","raw_affiliation_strings":["Xiaomi AI Lab,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Xiaomi AI Lab,Beijing,China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051287176","display_name":"Jian Luan","orcid":"https://orcid.org/0000-0002-3851-0829"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Luan","raw_affiliation_strings":["Xiaomi AI Lab,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Xiaomi AI Lab,Beijing,China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102011846","display_name":"Zhidong Deng","orcid":"https://orcid.org/0000-0001-9970-1023"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhidong Deng","raw_affiliation_strings":["Tsinghua University,BNRist, THUAI,Department of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist, THUAI,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015234413"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.319,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77886244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9485999941825867,"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":0.9330999851226807,"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/computer-science","display_name":"Computer science","score":0.8017697334289551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5689823627471924},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5592886209487915},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46309542655944824},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4053425192832947},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13014152646064758}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8017697334289551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5689823627471924},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5592886209487915},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46309542655944824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4053425192832947},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13014152646064758}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2277195237","https://openalex.org/W2560730294","https://openalex.org/W2963514444","https://openalex.org/W2963518342","https://openalex.org/W3094502228","https://openalex.org/W4387968447","https://openalex.org/W4389519483","https://openalex.org/W4389523832","https://openalex.org/W4390874575","https://openalex.org/W4392903970","https://openalex.org/W4402670135","https://openalex.org/W4402727624","https://openalex.org/W4402727669","https://openalex.org/W4402727764","https://openalex.org/W4402917081","https://openalex.org/W4403081466","https://openalex.org/W6791353385","https://openalex.org/W6809665764","https://openalex.org/W6811013733","https://openalex.org/W6843405348","https://openalex.org/W6849177959","https://openalex.org/W6851592950","https://openalex.org/W6851607685","https://openalex.org/W6853116092","https://openalex.org/W6854222408","https://openalex.org/W6855350031","https://openalex.org/W6859364510","https://openalex.org/W6859963071"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,28,60,97,103],"large":[3],"vision-language":[4,98],"models":[5],"(LVLMs)":[6],"typically":[7],"employ":[8],"vision":[9],"encoders":[10],"based":[11],"on":[12],"the":[13,21,34,68,76,94],"Vision":[14],"Transformer":[15],"(ViT)":[16],"architecture.":[17],"The":[18],"division":[19],"of":[20,38,82],"images":[22],"into":[23],"patches":[24],"by":[25,52],"ViT":[26],"results":[27],"a":[29,54],"fragmented":[30],"perception,":[31],"thereby":[32,74],"hindering":[33],"visual":[35,111],"understanding":[36,80],"capabilities":[37],"LVLMs.":[39,61,83],"In":[40],"this":[41,50],"paper,":[42],"we":[43],"propose":[44],"an":[45],"innovative":[46],"enhancement":[47],"to":[48],"address":[49],"limitation":[51],"introducing":[53],"Scene":[55],"Graph":[56],"Expression":[57],"(SGE)":[58],"module":[59,63,91],"This":[62],"extracts":[64],"and":[65,79,108],"structurally":[66],"expresses":[67],"complex":[69],"semantic":[70,106],"information":[71],"within":[72],"images,":[73],"improving":[75],"foundational":[77],"perception":[78],"abilities":[81],"Extensive":[84],"experiments":[85],"demonstrate":[86],"that":[87],"integrating":[88],"our":[89],"SGE":[90],"significantly":[92],"enhances":[93],"LVLM\u2019s":[95],"performance":[96],"tasks,":[99],"indicating":[100],"its":[101],"effectiveness":[102],"preserving":[104],"intricate":[105],"details":[107],"facilitating":[109],"better":[110],"understanding.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}