{"id":"https://openalex.org/W4403576604","doi":"https://doi.org/10.1145/3688865.3689482","title":"AssistGPT: Towards Multi-modal Agent for Human-Centric AI Assistant","display_name":"AssistGPT: Towards Multi-modal Agent for Human-Centric AI Assistant","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403576604","doi":"https://doi.org/10.1145/3688865.3689482"},"language":"en","primary_location":{"id":"doi:10.1145/3688865.3689482","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3688865.3689482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Human-centric Multimedia Analysis","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/A5001133932","display_name":"Difei Gao","orcid":"https://orcid.org/0000-0001-8494-3492"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Difei Gao","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035047807","display_name":"Siyuan Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Siyuan Hu","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083481253","display_name":"Kevin Qinghong Lin","orcid":"https://orcid.org/0000-0003-2568-2346"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qinghong Lin","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068937750","display_name":"Mike Zheng Shou","orcid":"https://orcid.org/0000-0002-7681-2166"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mike Zheng Shou","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001133932"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16298418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9749000072479248,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9749000072479248,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9724000096321106,"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"}},{"id":"https://openalex.org/T12128","display_name":"AI in Service Interactions","score":0.9549999833106995,"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":0.7019283771514893},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6287001967430115},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.061065733432769775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7019283771514893},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6287001967430115},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.061065733432769775},{"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:10.1145/3688865.3689482","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3688865.3689482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Human-centric Multimedia Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4390873341"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,69],"Multi-modal":[3],"Large":[4],"Language":[5],"Models":[6],"have":[7],"significantly":[8],"enhanced":[9],"the":[10,22],"capabilities":[11],"of":[12,24,85],"AI":[13],"assistants,":[14],"enabling":[15],"users":[16,78,132],"to":[17,88,112,123],"perform":[18],"question-answering":[19],"based":[20],"on":[21],"content":[23],"images":[25,58],"or":[26],"videos.":[27],"However,":[28],"addressing":[29],"complex":[30],"visual-based":[31],"tasks,":[32,136],"particularly":[33],"those":[34],"involving":[35],"fine-grained":[36],"human":[37],"actions":[38],"from":[39],"lengthy":[40],"videos,":[41],"remains":[42],"a":[43,62,93,125],"formidable":[44],"challenge.":[45],"To":[46],"tackle":[47],"this":[48],"issue,":[49],"we":[50],"introduce":[51],"AssistGPT,":[52],"an":[53,70],"MLLM-based":[54],"agent":[55],"that":[56,129],"takes":[57],"and":[59,61,66,74,106,108,144],"videos":[60],"query":[63],"as":[64,92,138],"input":[65],"outputs":[67],"response":[68],"interleaved":[71],"video,":[72],"image,":[73],"text":[75],"format,":[76],"providing":[77],"with":[79,133],"comprehensive":[80],"answers.":[81],"The":[82],"core":[83],"idea":[84],"AssistGPT":[86,97],"is":[87],"approach":[89,120],"visual":[90,117],"QA":[91],"multi-step":[94],"reasoning":[95],"problem.":[96],"decomposes":[98],"queries":[99],"into":[100],"sequential":[101],"steps,":[102],"employing":[103],"action":[104],"recognition,":[105],"temporal":[107],"spatial":[109],"grounding":[110],"models":[111],"search":[113],"for":[114],"information":[115],"within":[116],"inputs.":[118],"This":[119],"enables":[121],"us":[122],"create":[124],"versatile":[126],"multi-modal":[127],"assistant":[128],"can":[130],"help":[131],"various":[134],"human-centric":[135],"such":[137],"daily":[139],"activities,":[140],"learning":[141],"sports":[142],"skills,":[143],"healthcare.":[145]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
