{"id":"https://openalex.org/W4388623217","doi":"https://doi.org/10.1109/ro-man57019.2023.10309342","title":"Open-Ended Multi-Modal Relational Reasoning for Video Question Answering","display_name":"Open-Ended Multi-Modal Relational Reasoning for Video Question Answering","publication_year":2023,"publication_date":"2023-08-28","ids":{"openalex":"https://openalex.org/W4388623217","doi":"https://doi.org/10.1109/ro-man57019.2023.10309342"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man57019.2023.10309342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man57019.2023.10309342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5085445569","display_name":"Haozheng Luo","orcid":"https://orcid.org/0000-0001-9826-2874"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]},{"id":"https://openalex.org/I2802805919","display_name":"Science North","ror":"https://ror.org/028k36c88","country_code":"CA","type":"archive","lineage":["https://openalex.org/I2802805919"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Haozheng Luo","raw_affiliation_strings":["Northwestern University,Department of Electrical Engineering and Computer Science,Evanston","Department of Electrical Engineering and Computer Science, Northwestern University, Evanston"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University,Department of Electrical Engineering and Computer Science,Evanston","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Northwestern University, Evanston","institution_ids":["https://openalex.org/I2802805919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011529786","display_name":"Ruiyang Qin","orcid":"https://orcid.org/0000-0001-8295-8666"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruiyang Qin","raw_affiliation_strings":["University of Notre Dame,Department of Computer Science and Engineering,Notre Dame,IN","Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame,Department of Computer Science and Engineering,Notre Dame,IN","institution_ids":["https://openalex.org/I107639228"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100815630","display_name":"Chenwei Xu","orcid":"https://orcid.org/0009-0005-5282-4241"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]},{"id":"https://openalex.org/I2802805919","display_name":"Science North","ror":"https://ror.org/028k36c88","country_code":"CA","type":"archive","lineage":["https://openalex.org/I2802805919"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Chenwei Xu","raw_affiliation_strings":["Northwestern University,Department of Electrical Engineering and Computer Science,Evanston","Department of Electrical Engineering and Computer Science, Northwestern University, Evanston"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University,Department of Electrical Engineering and Computer Science,Evanston","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Northwestern University, Evanston","institution_ids":["https://openalex.org/I2802805919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100655342","display_name":"Guo Ye","orcid":"https://orcid.org/0000-0001-9361-9977"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]},{"id":"https://openalex.org/I2802805919","display_name":"Science North","ror":"https://ror.org/028k36c88","country_code":"CA","type":"archive","lineage":["https://openalex.org/I2802805919"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Guo Ye","raw_affiliation_strings":["Northwestern University,Department of Electrical Engineering and Computer Science,Evanston","Department of Electrical Engineering and Computer Science, Northwestern University, Evanston"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University,Department of Electrical Engineering and Computer Science,Evanston","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Northwestern University, Evanston","institution_ids":["https://openalex.org/I2802805919"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102528054","display_name":"Zening Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]},{"id":"https://openalex.org/I2802805919","display_name":"Science North","ror":"https://ror.org/028k36c88","country_code":"CA","type":"archive","lineage":["https://openalex.org/I2802805919"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Zening Luo","raw_affiliation_strings":["Northwestern University,Department of Electrical Engineering and Computer Science,Evanston","Department of Electrical Engineering and Computer Science, Northwestern University, Evanston"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University,Department of Electrical Engineering and Computer Science,Evanston","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Northwestern University, Evanston","institution_ids":["https://openalex.org/I2802805919"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2428,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59067987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"363","last_page":"369"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9991999864578247,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9968000054359436,"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":0.7756222486495972},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6912323832511902},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6640675067901611},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6352643966674805},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6240167617797852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5983486175537109},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5930958986282349},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5399394631385803},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5192344784736633},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40122032165527344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7756222486495972},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6912323832511902},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6640675067901611},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6352643966674805},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6240167617797852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5983486175537109},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5930958986282349},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5399394631385803},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5192344784736633},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40122032165527344},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man57019.2023.10309342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man57019.2023.10309342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W77717277","https://openalex.org/W764651262","https://openalex.org/W1689711448","https://openalex.org/W2109778557","https://openalex.org/W2194775991","https://openalex.org/W2470673105","https://openalex.org/W2512654307","https://openalex.org/W2896457183","https://openalex.org/W2911495555","https://openalex.org/W2962739339","https://openalex.org/W2963150697","https://openalex.org/W2963155035","https://openalex.org/W2963260376","https://openalex.org/W2963524571","https://openalex.org/W2963541336","https://openalex.org/W2963925437","https://openalex.org/W2966715458","https://openalex.org/W2969127500","https://openalex.org/W2970597249","https://openalex.org/W2978395334","https://openalex.org/W2982086365","https://openalex.org/W3010593057","https://openalex.org/W3034835156","https://openalex.org/W3035044482","https://openalex.org/W3090755184","https://openalex.org/W3105858579","https://openalex.org/W3127238141","https://openalex.org/W3130085442","https://openalex.org/W4200630484","https://openalex.org/W4226278401","https://openalex.org/W4281786578","https://openalex.org/W4288093753","https://openalex.org/W4292947814","https://openalex.org/W4294170691","https://openalex.org/W4295312788","https://openalex.org/W4311000453","https://openalex.org/W4311597143","https://openalex.org/W4385245566","https://openalex.org/W6603156799","https://openalex.org/W6682691769","https://openalex.org/W6739901393","https://openalex.org/W6754944153","https://openalex.org/W6755207826","https://openalex.org/W6756486208","https://openalex.org/W6763701032","https://openalex.org/W6766904570","https://openalex.org/W6766978945","https://openalex.org/W6769024994","https://openalex.org/W6780226713","https://openalex.org/W6786140819","https://openalex.org/W6790844868","https://openalex.org/W6805704697","https://openalex.org/W6810738896","https://openalex.org/W6841765919","https://openalex.org/W6847363464","https://openalex.org/W6891825660"],"related_works":["https://openalex.org/W3157284875","https://openalex.org/W2259406085","https://openalex.org/W2099715052","https://openalex.org/W2147241511","https://openalex.org/W4226247999","https://openalex.org/W4213176082","https://openalex.org/W2187398150","https://openalex.org/W3209772662","https://openalex.org/W4200629926","https://openalex.org/W4220955952"],"abstract_inverted_index":{"In":[0],"this":[1,22],"paper,":[2],"we":[3],"introduce":[4],"a":[5,73,85],"robotic":[6,48],"agent":[7,23],"specifically":[8],"designed":[9],"to":[10,25,87,93],"analyze":[11],"external":[12],"environments":[13],"and":[14,41,65,78],"address":[15],"participants\u2019":[16],"questions.":[17],"The":[18],"primary":[19],"focus":[20],"of":[21],"is":[24],"assist":[26],"individuals":[27],"using":[28],"language-based":[29],"interactions":[30,57],"within":[31,46],"video-based":[32],"scenes.":[33],"Our":[34],"proposed":[35],"method":[36],"integrates":[37],"video":[38],"recognition":[39],"technology":[40],"natural":[42],"language":[43],"processing":[44],"models":[45],"the":[47,52],"agent.":[49],"We":[50],"investigate":[51],"crucial":[53],"factors":[54],"affecting":[55],"human-robot":[56],"by":[58],"examining":[59],"pertinent":[60],"issues":[61],"arising":[62],"between":[63,76],"participants":[64],"robot":[66],"agents.":[67],"Methodologically,":[68],"our":[69,82],"experimental":[70],"findings":[71],"reveal":[72],"positive":[74],"relationship":[75],"trust":[77],"interaction":[79],"efficiency.":[80],"Furthermore,":[81],"model":[83],"demonstrates":[84],"2%":[86],"3%":[88],"performance":[89],"enhancement":[90],"in":[91],"comparison":[92],"other":[94],"benchmark":[95],"methods.":[96]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}