{"id":"https://openalex.org/W4403780506","doi":"https://doi.org/10.1145/3664647.3688992","title":"LLaVA-VSD: Large Language-and-Vision Assistant for Visual Spatial Description","display_name":"LLaVA-VSD: Large Language-and-Vision Assistant for Visual Spatial Description","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780506","doi":"https://doi.org/10.1145/3664647.3688992"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3688992","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3688992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5113052534","display_name":"Yizhang Jin","orcid":"https://orcid.org/0009-0008-6892-2964"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhang Jin","raw_affiliation_strings":["Tencent &amp; Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-6892-2964","affiliations":[{"raw_affiliation_string":"Tencent &amp; Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402508","display_name":"Jian Li","orcid":"https://orcid.org/0000-0002-0242-6481"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Li","raw_affiliation_strings":["Tencent, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0242-6481","affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021861529","display_name":"Jiangning Zhang","orcid":"https://orcid.org/0000-0001-8891-6766"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangning Zhang","raw_affiliation_strings":["Tencent, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8891-6766","affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianlong Hu","orcid":"https://orcid.org/0009-0000-8629-2101"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlong Hu","raw_affiliation_strings":["Tencent, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-8629-2101","affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075598739","display_name":"Zhenye Gan","orcid":"https://orcid.org/0000-0002-2431-1159"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenye Gan","raw_affiliation_strings":["Tencent, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2431-1159","affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080281882","display_name":"Xin Tan","orcid":"https://orcid.org/0000-0001-9346-1196"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Tan","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9346-1196","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115501056","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0001-9945-8131"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Tencent, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9945-8131","affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028731909","display_name":"Yabiao Wang","orcid":"https://orcid.org/0000-0002-6592-8411"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yabiao Wang","raw_affiliation_strings":["Tencent, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6592-8411","affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023834700","display_name":"Chengjie Wang","orcid":"https://orcid.org/0000-0003-4216-8090"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengjie Wang","raw_affiliation_strings":["Tencent, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4216-8090","affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084218062","display_name":"Lizhuang Ma","orcid":"https://orcid.org/0000-0003-1653-4341"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhuang Ma","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1653-4341","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11420","last_page":"11425"},"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":0.9965999722480774,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9848999977111816,"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":0.7575814723968506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5181344747543335},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4281710684299469}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7575814723968506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5181344747543335},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4281710684299469}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3688992","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3688992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2277195237","https://openalex.org/W4390873312","https://openalex.org/W4402716288","https://openalex.org/W4402727764","https://openalex.org/W4402753519","https://openalex.org/W4402753807"],"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":{"Visual":[0,54],"Spatial":[1,55],"Description":[2],"(VSD)":[3],"aims":[4],"to":[5,95,121,142],"generate":[6],"texts":[7],"that":[8],"describe":[9],"the":[10,26,63,74,88,123],"spatial":[11,19,27,71,80],"relationships":[12,148],"between":[13,29],"objects":[14,31],"within":[15],"images.":[16,113,150],"Traditional":[17],"visual":[18,70,79],"relationship":[20,28],"classification":[21],"(VSRC)":[22],"methods":[23],"typically":[24],"output":[25],"two":[30],"in":[32,149],"an":[33],"image,":[34],"often":[35],"neglecting":[36],"world":[37],"knowledge":[38],"and":[39,66,100,110,129,137],"lacking":[40],"general":[41],"language":[42,117],"capabilities.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"propose":[48],"a":[49,78,97,115],"Large":[50,98],"Language-and-Vision":[51],"Assistant":[52,102],"for":[53,62,87,103],"Description,":[56],"named":[57],"LLaVA-VSD,":[58],"which":[59,105],"is":[60,119],"designed":[61],"classification,":[64],"description,":[65],"open-ended":[67,140],"description":[68],"of":[69],"relationships.":[72],"Specifically,":[73],"model":[75,118],"first":[76],"constructs":[77],"instruction-following":[81],"dataset":[82],"using":[83],"given":[84],"figure-caption":[85],"pairs":[86],"three":[89],"tasks.":[90],"It":[91],"then":[92],"employs":[93],"LoRA":[94],"fine-tune":[96],"Language":[99],"Vision":[101],"VSD,":[104],"has":[106],"13":[107],"billion":[108],"parameters":[109],"supports":[111],"high-resolution":[112],"Finally,":[114],"large":[116],"used":[120],"refine":[122],"generated":[124],"sentences,":[125],"enhancing":[126],"their":[127],"diversity":[128],"accuracy.":[130],"LLaVA-VSD":[131],"demonstrates":[132],"excellent":[133],"multimodal":[134],"conversational":[135],"capabilities":[136],"can":[138],"follow":[139],"instructions":[141],"assist":[143],"with":[144],"inquiries":[145],"about":[146],"object":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
