{"id":"https://openalex.org/W7154507312","doi":"https://doi.org/10.1145/3808220","title":"Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog","display_name":"Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog","publication_year":2026,"publication_date":"2026-04-15","ids":{"openalex":"https://openalex.org/W7154507312","doi":"https://doi.org/10.1145/3808220"},"language":"en","primary_location":{"id":"doi:10.1145/3808220","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3808220","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","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/A5041574524","display_name":"H ZHANG","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology Shenzhen, Shenzhen, China and Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-3896-170X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology Shenzhen, Shenzhen, China and Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457438","display_name":"Meng Liu","orcid":"https://orcid.org/0000-0002-1582-5764"},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Liu","raw_affiliation_strings":["School of Computer Science and Technology, Shandong Jianzhu University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-1582-5764","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110296061","display_name":"Yisen Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yisen Feng","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0006-0158-322X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133726859","display_name":"Yaowei Wang","orcid":"https://orcid.org/0000-0003-2197-9038"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaowei Wang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology Shenzhen, Shenzhen, China and Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2197-9038","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology Shenzhen, Shenzhen, China and Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075938343","display_name":"Weili Guan","orcid":"https://orcid.org/0000-0002-5658-5509"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weili Guan","raw_affiliation_strings":["School of Information Science and Technology, Harbin Institute of Technology Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5658-5509","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Harbin Institute of Technology Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42675514,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"44","issue":"4","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9829000234603882,"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":0.9829000234603882,"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/T10028","display_name":"Topic Modeling","score":0.006099999882280827,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.002899999963119626,"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/dialog-box","display_name":"Dialog box","score":0.9196000099182129},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6984000205993652},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5591999888420105},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4634000062942505},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4350000023841858},{"id":"https://openalex.org/keywords/visual-search","display_name":"Visual search","score":0.3668000102043152},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.3634999990463257},{"id":"https://openalex.org/keywords/sensory-cue","display_name":"Sensory cue","score":0.3626999855041504}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.9196000099182129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8870999813079834},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6984000205993652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6434000134468079},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5591999888420105},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4634000062942505},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38420000672340393},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3790000081062317},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3634999990463257},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31709998846054077},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27399998903274536},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3808220","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3808220","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2147564525","display_name":null,"funder_award_id":"2025A1515011732","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G5801653098","display_name":null,"funder_award_id":"62236003, 62376140, 62476071, 625B2065, U24A20328, and U23A20315","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8636298553","display_name":null,"funder_award_id":"HIT.DZJJ.2025048","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2139158514","https://openalex.org/W2147015617","https://openalex.org/W2337252826","https://openalex.org/W2952728748","https://openalex.org/W2953016680","https://openalex.org/W2964218959","https://openalex.org/W2981902456","https://openalex.org/W3034291519","https://openalex.org/W3035314827","https://openalex.org/W3099143471","https://openalex.org/W3102037269","https://openalex.org/W3107092117","https://openalex.org/W3134294468","https://openalex.org/W3137797626","https://openalex.org/W3165695488","https://openalex.org/W3171774521","https://openalex.org/W3199693760","https://openalex.org/W3207886649","https://openalex.org/W3217340782","https://openalex.org/W4283728202","https://openalex.org/W4308237915","https://openalex.org/W4321109541","https://openalex.org/W4385567055","https://openalex.org/W4385572799","https://openalex.org/W4385583991","https://openalex.org/W4387398451"],"related_works":[],"abstract_inverted_index":{"Unlike":[0],"conventional":[1],"visual":[2,63,97,109,118],"question":[3],"answering,":[4],"video-grounded":[5],"dialog":[6,14,38,85],"requires":[7],"a":[8,59,62,66,73,123],"deep":[9],"understanding":[10,91],"of":[11,58,154],"both":[12],"the":[13,17,69,84,92,96,112,128,133,150,155],"history":[15,39,86],"and":[16,40,54,65,76,106,139,152],"video":[18,43],"content":[19],"to":[20,79,104,131],"generate":[21],"accurate":[22],"responses.":[23,142],"Although":[24],"existing":[25],"methods":[26],"have":[27],"achieved":[28],"promising":[29],"results,":[30],"they":[31],"still":[32],"struggle":[33],"with":[34],"progressively":[35],"comprehending":[36],"complex":[37],"effectively":[41],"integrating":[42],"information.":[44],"To":[45],"address":[46],"these":[47],"challenges,":[48],"we":[49,121],"propose":[50],"an":[51,100],"iterative":[52,101],"search":[53,75],"reasoning":[55,102],"framework":[56],"composed":[57],"textual":[60,70],"encoder,":[61,64],"generator.":[67],"Specifically,":[68],"encoder":[71,98],"adopts":[72],"path":[74],"aggregation":[77],"strategy":[78],"identify":[80],"key":[81],"cues":[82,136],"in":[83],"that":[87],"are":[88],"essential":[89],"for":[90],"current":[93],"question.":[94],"Meanwhile,":[95],"employs":[99],"network":[103],"extract":[105],"highlight":[107],"critical":[108],"evidence":[110],"from":[111],"video,":[113],"thereby":[114],"enabling":[115],"more":[116],"comprehensive":[117],"understanding.":[119],"Finally,":[120],"use":[122],"pretrained":[124],"GPT-2":[125],"model":[126],"as":[127],"answer":[129],"generator":[130],"transform":[132],"discovered":[134],"latent":[135],"into":[137],"coherent":[138],"contextually":[140],"appropriate":[141],"Extensive":[143],"experiments":[144],"on":[145],"three":[146],"public":[147],"datasets":[148],"demonstrate":[149],"effectiveness":[151],"generalizability":[153],"proposed":[156],"framework.":[157]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-04-16T00:00:00"}