{"id":"https://openalex.org/W4404654668","doi":"https://doi.org/10.1007/978-3-031-72995-9_11","title":"X-InstructBLIP: A Framework for\u00a0Aligning Image, 3D, Audio, Video to\u00a0LLMs and\u00a0its Emergent Cross-Modal Reasoning","display_name":"X-InstructBLIP: A Framework for\u00a0Aligning Image, 3D, Audio, Video to\u00a0LLMs and\u00a0its Emergent Cross-Modal Reasoning","publication_year":2024,"publication_date":"2024-11-23","ids":{"openalex":"https://openalex.org/W4404654668","doi":"https://doi.org/10.1007/978-3-031-72995-9_11"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-72995-9_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-72995-9_11","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5084018235","display_name":"Artemis Panagopoulou","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]},{"id":"https://openalex.org/I922845939","display_name":"Philadelphia University","ror":"https://ror.org/03zzmyz63","country_code":"US","type":"education","lineage":["https://openalex.org/I922845939"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Artemis Panagopoulou","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, USA","institution_ids":["https://openalex.org/I922845939","https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100733668","display_name":"Le Xue","orcid":"https://orcid.org/0000-0003-2810-770X"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Le Xue","raw_affiliation_strings":["Salesforce AI Research, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Salesforce AI Research, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752316","display_name":"Ning Yu","orcid":"https://orcid.org/0000-0002-3046-4338"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ning Yu","raw_affiliation_strings":["Salesforce AI Research, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Salesforce AI Research, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100608759","display_name":"Junnan Li","orcid":"https://orcid.org/0000-0002-5217-9204"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junnan Li","raw_affiliation_strings":["Salesforce AI Research, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Salesforce AI Research, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386792","display_name":"Dongxu Li","orcid":"https://orcid.org/0000-0001-8543-4761"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongxu Li","raw_affiliation_strings":["Salesforce AI Research, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Salesforce AI Research, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005443526","display_name":"Shafiq Joty","orcid":"https://orcid.org/0000-0002-9222-2641"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shafiq Joty","raw_affiliation_strings":["Salesforce AI Research, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Salesforce AI Research, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056643573","display_name":"Ran Xu","orcid":"https://orcid.org/0000-0003-2913-9420"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ran Xu","raw_affiliation_strings":["Salesforce AI Research, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Salesforce AI Research, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042646536","display_name":"Silvio Savarese","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Silvio Savarese","raw_affiliation_strings":["Salesforce AI Research, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Salesforce AI Research, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032046813","display_name":"Caiming Xiong","orcid":"https://orcid.org/0000-0003-0349-8628"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caiming Xiong","raw_affiliation_strings":["Salesforce AI Research, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Salesforce AI Research, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018518655","display_name":"Juan Carlos Niebles","orcid":"https://orcid.org/0000-0001-8225-9793"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Carlos Niebles","raw_affiliation_strings":["Salesforce AI Research, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Salesforce AI Research, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210155268"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5084018235"],"corresponding_institution_ids":["https://openalex.org/I79576946","https://openalex.org/I922845939"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":4.2425,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.96917685,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"177","last_page":"197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11439","display_name":"Video Analysis and Summarization","score":0.9962999820709229,"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/T11309","display_name":"Music and Audio Processing","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/audio-visual","display_name":"Audio visual","score":0.7851015329360962},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7819810509681702},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7107067108154297},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4811376631259918},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47322240471839905},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3991573452949524},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.38192036747932434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36825835704803467},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3243139982223511}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7851015329360962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7819810509681702},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7107067108154297},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4811376631259918},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47322240471839905},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3991573452949524},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.38192036747932434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36825835704803467},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3243139982223511},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-72995-9_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-72995-9_11","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2052666245","https://openalex.org/W2090048052","https://openalex.org/W2560674852","https://openalex.org/W2949376505","https://openalex.org/W2964213933","https://openalex.org/W2981440248","https://openalex.org/W2989322838","https://openalex.org/W3015591594","https://openalex.org/W3035524453","https://openalex.org/W3091588028","https://openalex.org/W3103022576","https://openalex.org/W3109643012","https://openalex.org/W3135367836","https://openalex.org/W3173905097","https://openalex.org/W3176445421","https://openalex.org/W3199693760","https://openalex.org/W3204588463","https://openalex.org/W4221143046","https://openalex.org/W4225323055","https://openalex.org/W4226321975","https://openalex.org/W4281633595","https://openalex.org/W4285249364","https://openalex.org/W4312380001","https://openalex.org/W4312605942","https://openalex.org/W4313014461","https://openalex.org/W4313068342","https://openalex.org/W4313190371","https://openalex.org/W4320458302","https://openalex.org/W4322718246","https://openalex.org/W4372340819","https://openalex.org/W4376312115","https://openalex.org/W4382202558","https://openalex.org/W4383175523","https://openalex.org/W4385565405","https://openalex.org/W4385572450","https://openalex.org/W4385574358","https://openalex.org/W4385823465","https://openalex.org/W4386065596","https://openalex.org/W4386065627","https://openalex.org/W4386071687","https://openalex.org/W4386071707","https://openalex.org/W4386076522","https://openalex.org/W4386566765","https://openalex.org/W4387891768","https://openalex.org/W4389519587","https://openalex.org/W4389520080","https://openalex.org/W4402671548","https://openalex.org/W4402727922","https://openalex.org/W4403778769","https://openalex.org/W4404783556","https://openalex.org/W6601804787","https://openalex.org/W6640300118","https://openalex.org/W6748148878","https://openalex.org/W6778883912","https://openalex.org/W6796581206","https://openalex.org/W6800875267","https://openalex.org/W6848208918","https://openalex.org/W6850503672","https://openalex.org/W6855425132"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}