{"id":"https://openalex.org/W4388915293","doi":"https://doi.org/10.1016/j.hcc.2023.100184","title":"Coreference resolution helps visual dialogs to focus","display_name":"Coreference resolution helps visual dialogs to focus","publication_year":2023,"publication_date":"2023-11-22","ids":{"openalex":"https://openalex.org/W4388915293","doi":"https://doi.org/10.1016/j.hcc.2023.100184"},"language":"en","primary_location":{"id":"doi:10.1016/j.hcc.2023.100184","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.hcc.2023.100184","pdf_url":null,"source":{"id":"https://openalex.org/S4210186527","display_name":"High-Confidence Computing","issn_l":"2667-2952","issn":["2667-2952"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"High-Confidence Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.hcc.2023.100184","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045003110","display_name":"Tianwei Yue","orcid":"https://orcid.org/0000-0003-1219-153X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianwei Yue","raw_affiliation_strings":["Carnegie Mellon University, 5555 Forbes Ave, Pittsburgh, 15213, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, 5555 Forbes Ave, Pittsburgh, 15213, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023352184","display_name":"Wenping Wang","orcid":"https://orcid.org/0000-0001-9665-3783"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wenping Wang","raw_affiliation_strings":["Carnegie Mellon University, 5555 Forbes Ave, Pittsburgh, 15213, PA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9665-3783","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, 5555 Forbes Ave, Pittsburgh, 15213, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037632839","display_name":"Liang Chen","orcid":"https://orcid.org/0000-0001-8015-4867"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Liang","raw_affiliation_strings":["Carnegie Mellon University, 5555 Forbes Ave, Pittsburgh, 15213, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, 5555 Forbes Ave, Pittsburgh, 15213, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104178561","display_name":"Dachi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dachi Chen","raw_affiliation_strings":["Carnegie Mellon University, 5555 Forbes Ave, Pittsburgh, 15213, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, 5555 Forbes Ave, Pittsburgh, 15213, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037717172","display_name":"Congrui Hetang","orcid":"https://orcid.org/0000-0001-8553-9053"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Congrui Hetang","raw_affiliation_strings":["Carnegie Mellon University, 5555 Forbes Ave, Pittsburgh, 15213, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, 5555 Forbes Ave, Pittsburgh, 15213, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100684665","display_name":"Xuewei Wang","orcid":"https://orcid.org/0009-0003-9068-8346"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuewei Wang","raw_affiliation_strings":["Carnegie Mellon University, 5555 Forbes Ave, Pittsburgh, 15213, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, 5555 Forbes Ave, Pittsburgh, 15213, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5023352184"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":{"value":1500,"currency":"USD","value_usd":1500},"apc_paid":{"value":1500,"currency":"USD","value_usd":1500},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14703151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":"2","first_page":"100184","last_page":"100184"},"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":0.9969000220298767,"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":0.9937999844551086,"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":0.8500831723213196},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.6892596483230591},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6147140860557556},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5762311220169067},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5321521162986755},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5281558036804199},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5252075791358948},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.48859888315200806},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.48006853461265564},{"id":"https://openalex.org/keywords/coreference","display_name":"Coreference","score":0.4752885103225708},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.471874862909317},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.4581936299800873},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36504876613616943},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.22504034638404846},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10043802857398987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8500831723213196},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.6892596483230591},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6147140860557556},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5762311220169067},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5321521162986755},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5281558036804199},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5252075791358948},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.48859888315200806},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.48006853461265564},{"id":"https://openalex.org/C28076734","wikidata":"https://www.wikidata.org/wiki/Q63087","display_name":"Coreference","level":3,"score":0.4752885103225708},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.471874862909317},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4581936299800873},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36504876613616943},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.22504034638404846},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10043802857398987},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.hcc.2023.100184","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.hcc.2023.100184","pdf_url":null,"source":{"id":"https://openalex.org/S4210186527","display_name":"High-Confidence Computing","issn_l":"2667-2952","issn":["2667-2952"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"High-Confidence Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b0b42b80eaa2409d98b1e596e6e2f42d","is_oa":true,"landing_page_url":"https://doaj.org/article/b0b42b80eaa2409d98b1e596e6e2f42d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"High-Confidence Computing, Vol 4, Iss 2, Pp 100184- (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.hcc.2023.100184","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.hcc.2023.100184","pdf_url":null,"source":{"id":"https://openalex.org/S4210186527","display_name":"High-Confidence Computing","issn_l":"2667-2952","issn":["2667-2952"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"High-Confidence Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2559655401","https://openalex.org/W2599940792","https://openalex.org/W2612690371","https://openalex.org/W2745461083","https://openalex.org/W2892245540","https://openalex.org/W2914761779","https://openalex.org/W2917061951","https://openalex.org/W2950297087","https://openalex.org/W2962716332","https://openalex.org/W2963191264","https://openalex.org/W2963224792","https://openalex.org/W2963383024","https://openalex.org/W2963623904","https://openalex.org/W2963644680","https://openalex.org/W2963800628","https://openalex.org/W2963976294","https://openalex.org/W2964118342","https://openalex.org/W2964303913","https://openalex.org/W2970355596","https://openalex.org/W2981902456","https://openalex.org/W4249013746","https://openalex.org/W4288090547","https://openalex.org/W4366551603","https://openalex.org/W4382993005","https://openalex.org/W4382993848","https://openalex.org/W4383333668","https://openalex.org/W4386026842","https://openalex.org/W4387337274","https://openalex.org/W4387348867","https://openalex.org/W4389116127","https://openalex.org/W4391769539","https://openalex.org/W6620707391","https://openalex.org/W6629496199","https://openalex.org/W6681756451","https://openalex.org/W6739177970","https://openalex.org/W6743696045","https://openalex.org/W6746276670","https://openalex.org/W6769101111","https://openalex.org/W6851465442","https://openalex.org/W6857832686","https://openalex.org/W6859188743"],"related_works":["https://openalex.org/W2139373276","https://openalex.org/W2227889443","https://openalex.org/W1509033667","https://openalex.org/W4385749782","https://openalex.org/W3167631113","https://openalex.org/W2145164276","https://openalex.org/W2004630825","https://openalex.org/W2324061017","https://openalex.org/W2740479527","https://openalex.org/W2810679507"],"abstract_inverted_index":{"Visual":[0,77],"Dialog":[1],"is":[2,15,68,74],"a":[3,109,151],"multi-modal":[4],"task":[5],"involving":[6],"both":[7,168],"computer":[8],"vision":[9],"and":[10,51,123,159,174],"dialog":[11,90,160],"systems.":[12],"The":[13],"goal":[14],"to":[16,59,99,126,178],"answer":[17],"multiple":[18],"questions":[19],"in":[20,44,170],"conversation":[21],"style,":[22],"given":[23],"an":[24,69,121],"image":[25,122],"as":[26,150],"the":[27,46,49,62,75,83,89,101,116,141,156,165,171],"context.":[28],"Neural":[29],"networks":[30],"with":[31,104],"attention":[32,85,102,129],"modules":[33],"are":[34],"widely":[35],"used":[36],"for":[37,155],"this":[38,54],"task,":[39],"because":[40],"of":[41,64,95,120,143,167],"their":[42],"effectiveness":[43],"reasoning":[45],"relevance":[47],"between":[48],"texts":[50],"images.":[52],"In":[53,137],"work,":[55],"we":[56,97,139],"study":[57,140],"how":[58],"further":[60,176],"improve":[61,100],"quality":[63],"such":[65],"reasoning,":[66],"which":[67,81],"open":[70],"challenge.":[71],"Our":[72],"baseline":[73],"Recursive":[76],"Attention":[78,111],"(RVA)":[79],"model,":[80],"refines":[82],"vision-text":[84],"by":[86,114],"iteratively":[87],"visiting":[88],"history.":[91],"Building":[92],"on":[93],"top":[94],"that,":[96],"propose":[98,175],"mechanism":[103],"contrastive":[105],"learning.":[106],"We":[107,163],"train":[108],"Matching-Aware":[110],"Kernel":[112],"(MAAK)":[113],"aligning":[115],"deep":[117],"feature":[118,153],"embeddings":[119],"its":[124],"caption,":[125],"provide":[127],"better":[128],"scores.":[130],"Experiments":[131],"show":[132],"consistent":[133],"improvements":[134],"from":[135],"MAAK.":[136],"addition,":[138],"effect":[142],"using":[144],"Multimodal":[145],"Compact":[146],"Bilinear":[147],"(MCB)":[148],"pooling":[149],"three-way":[152],"fusion":[154],"visual,":[157],"texutal":[158],"history":[161],"embeddings.":[162],"analyze":[164],"performance":[166],"methods":[169],"discussion":[172],"section,":[173],"ideas":[177],"resolve":[179],"current":[180],"limitations.":[181]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
