{"id":"https://openalex.org/W4394564345","doi":"https://doi.org/10.1109/tmm.2024.3385997","title":"Hybrid Graph Reasoning With Dynamic Interaction for Visual Dialog","display_name":"Hybrid Graph Reasoning With Dynamic Interaction for Visual Dialog","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394564345","doi":"https://doi.org/10.1109/tmm.2024.3385997"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3385997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3385997","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5110906316","display_name":"Shan-Shan Du","orcid":"https://orcid.org/0000-0003-1048-4574"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanshan Du","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, China","Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1048-4574","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058982350","display_name":"Hanli Wang","orcid":"https://orcid.org/0000-0002-9999-4871"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanli Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, China","Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9999-4871","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013006794","display_name":"Tengpeng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tengpeng Li","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, China","Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-2244-0567","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Key Laboratory of Embedded System and Service Computing (Ministry of Education), Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002277899","display_name":"Chang Wen Chen","orcid":"https://orcid.org/0000-0002-6720-234X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chang Wen Chen","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong","Department of Computing, Hong Kong Polytechnic University, Hung Hom, China"],"raw_orcid":"https://orcid.org/0000-0002-6720-234X","affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Computing, Hong Kong Polytechnic University, Hung Hom, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6131,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65240804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"26","issue":null,"first_page":"9095","last_page":"9108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9922000169754028,"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":0.9922000169754028,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.9728000164031982,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9671000242233276,"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":0.8683129549026489},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.6425761580467224},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5037016272544861},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46852394938468933},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4025081694126129},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34701570868492126},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3364470899105072},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14200255274772644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8683129549026489},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.6425761580467224},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5037016272544861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46852394938468933},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4025081694126129},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34701570868492126},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3364470899105072},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14200255274772644}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3385997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3385997","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2125127483","display_name":null,"funder_award_id":"62371343","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2064675550","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2798722023","https://openalex.org/W2892245540","https://openalex.org/W2917061951","https://openalex.org/W2951287298","https://openalex.org/W2962944050","https://openalex.org/W2963224792","https://openalex.org/W2963287297","https://openalex.org/W2963393494","https://openalex.org/W2963623904","https://openalex.org/W2964218959","https://openalex.org/W2964222246","https://openalex.org/W2966158321","https://openalex.org/W2967045987","https://openalex.org/W2970355596","https://openalex.org/W2981902456","https://openalex.org/W2988023442","https://openalex.org/W2997547717","https://openalex.org/W3004349648","https://openalex.org/W3018388102","https://openalex.org/W3027560576","https://openalex.org/W3034291519","https://openalex.org/W3035052826","https://openalex.org/W3035071066","https://openalex.org/W3035103424","https://openalex.org/W3035454069","https://openalex.org/W3095309002","https://openalex.org/W3096612875","https://openalex.org/W3099143471","https://openalex.org/W3107092117","https://openalex.org/W3116651605","https://openalex.org/W3165695488","https://openalex.org/W3175445769","https://openalex.org/W3179041377","https://openalex.org/W3203354307","https://openalex.org/W3207847779","https://openalex.org/W3217304284","https://openalex.org/W4213303451","https://openalex.org/W4214617019","https://openalex.org/W4223451840","https://openalex.org/W4224920289","https://openalex.org/W4229019825","https://openalex.org/W4249013746","https://openalex.org/W4292263758","https://openalex.org/W4296079526","https://openalex.org/W4312645695","https://openalex.org/W4312825258","https://openalex.org/W4316661056","https://openalex.org/W4385245566","https://openalex.org/W4385934203","https://openalex.org/W4386453561","https://openalex.org/W6631190155","https://openalex.org/W6726873649","https://openalex.org/W6729448088","https://openalex.org/W6739177970","https://openalex.org/W6743696045","https://openalex.org/W6745447533","https://openalex.org/W6775947557"],"related_works":["https://openalex.org/W2098987383","https://openalex.org/W2417260800","https://openalex.org/W1596203174","https://openalex.org/W2117933979","https://openalex.org/W4298396513","https://openalex.org/W2283130723","https://openalex.org/W103938586","https://openalex.org/W2104718772","https://openalex.org/W4233992201","https://openalex.org/W337810568"],"abstract_inverted_index":{"As":[0],"a":[1,11,103,133,158,163,168,193],"pivotal":[2],"branch":[3],"of":[4,52,122,202,211,223],"intelligent":[5],"human-computer":[6],"interaction,":[7],"visual":[8,35,171],"dialog":[9,36,172],"is":[10,82,107,138,154,178],"technically":[12],"challenging":[13],"task":[14],"that":[15],"requires":[16],"artificial":[17],"intelligence":[18],"(AI)":[19],"agents":[20],"to":[21,45,60,109,140,180,216],"answer":[22],"consecutive":[23],"questions":[24],"based":[25],"on":[26,54,198],"image":[27],"content":[28],"and":[29,57,78,93,162,186,205],"history":[30],"dialog.":[31],"Despite":[32],"considerable":[33],"progresses,":[34],"still":[37],"suffers":[38],"from":[39,147],"two":[40],"major":[41,89],"problems:":[42],"(1)":[43],"how":[44,59],"design":[46],"flexible":[47],"cross-modal":[48],"interaction":[49,77,105,115,126,184],"patterns":[50],"instead":[51],"over-reliance":[53],"expert":[55],"experience":[56],"(2)":[58],"infer":[61],"underlying":[62],"semantic":[63,143],"dependencies":[64],"between":[65,145],"dialogues":[66,146],"effectively.":[67],"To":[68],"address":[69],"these":[70],"issues,":[71],"an":[72,175],"end-to-end":[73,176],"framework":[74],"employing":[75],"dynamic":[76,104,130,183],"hybrid":[79,134,152,188],"graph":[80,135,153,161,189],"reasoning":[81,136,190],"proposed":[83,213],"in":[84,192,229],"this":[85,224],"work.":[86],"Specifically,":[87],"three":[88,123],"components":[90],"are":[91,97],"designed":[92,139],"the":[94,112,151,182,187,199,209,212],"practical":[95],"benefits":[96],"demonstrated":[98],"by":[99,156],"extensive":[100],"experiments.":[101],"First,":[102],"module":[106,137,185,191],"developed":[108,179],"automatically":[110],"determine":[111],"optimal":[113],"modality":[114],"route":[116],"for":[117],"multifarious":[118],"questions,":[119],"which":[120],"consists":[121],"elaborate":[124],"functional":[125],"blocks":[127],"endowed":[128],"with":[129,174],"routers.":[131],"Second,":[132],"explore":[141],"adequate":[142],"associations":[144],"multiple":[148],"perspectives,":[149],"where":[150],"constructed":[155],"aggregating":[157],"structured":[159],"coreference":[160],"context-aware":[164],"temporal":[165],"graph.":[166],"Third,":[167],"unified":[169],"one-stage":[170],"model":[173],"structure":[177],"train":[181],"collaborative":[194],"manner.":[195],"Extensive":[196],"experiments":[197],"benchmark":[200],"datasets":[201],"VisDial":[203,206],"v0.9":[204],"v1.0":[207],"demonstrate":[208],"effectiveness":[210],"method":[214],"compared":[215],"other":[217],"state-of-the-art":[218],"approaches.":[219],"The":[220],"source":[221],"code":[222],"work":[225],"can":[226],"be":[227],"found":[228],"<uri":[230],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[231],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://mic.tongji.edu.cn</uri>":[232],".":[233]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}