{"id":"https://openalex.org/W4392903152","doi":"https://doi.org/10.1109/icassp48485.2024.10447493","title":"Learning Representations from Explainable and Connectionist Approaches for Visual Question Answering","display_name":"Learning Representations from Explainable and Connectionist Approaches for Visual Question Answering","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903152","doi":"https://doi.org/10.1109/icassp48485.2024.10447493"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447493","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5009532727","display_name":"Aakansha Mishra","orcid":"https://orcid.org/0000-0002-0792-3006"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Aakansha Mishra","raw_affiliation_strings":["Samsung Research Institute Bangalore (SRIB),India","Samsung Research Institute Bangalore (SRIB), India"],"affiliations":[{"raw_affiliation_string":"Samsung Research Institute Bangalore (SRIB),India","institution_ids":["https://openalex.org/I4210139030"]},{"raw_affiliation_string":"Samsung Research Institute Bangalore (SRIB), India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048476439","display_name":"Miriyala Srinivas Soumitri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Miriyala Srinivas Soumitri","raw_affiliation_strings":["Samsung Research Institute Bangalore (SRIB),India","Samsung Research Institute Bangalore (SRIB), India"],"affiliations":[{"raw_affiliation_string":"Samsung Research Institute Bangalore (SRIB),India","institution_ids":["https://openalex.org/I4210139030"]},{"raw_affiliation_string":"Samsung Research Institute Bangalore (SRIB), India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079783021","display_name":"Vikram N Rajendiran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vikram N Rajendiran","raw_affiliation_strings":["Samsung Research Institute Bangalore (SRIB),India","Samsung Research Institute Bangalore (SRIB), India"],"affiliations":[{"raw_affiliation_string":"Samsung Research Institute Bangalore (SRIB),India","institution_ids":["https://openalex.org/I4210139030"]},{"raw_affiliation_string":"Samsung Research Institute Bangalore (SRIB), India","institution_ids":["https://openalex.org/I4210139030"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009532727"],"corresponding_institution_ids":["https://openalex.org/I4210139030"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02669374,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"6420","last_page":"6424"},"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":0.995199978351593,"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":0.9940000176429749,"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/connectionism","display_name":"Connectionism","score":0.8169921636581421},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7772361040115356},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6949962973594666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6837711334228516},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.6694701313972473},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6611075401306152},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6139180660247803},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5788169503211975},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.47384577989578247},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3861825466156006},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3464652895927429},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33550071716308594},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0809779167175293}],"concepts":[{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.8169921636581421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7772361040115356},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6949962973594666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6837711334228516},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6694701313972473},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6611075401306152},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6139180660247803},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5788169503211975},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.47384577989578247},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3861825466156006},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3464652895927429},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33550071716308594},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0809779167175293},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447493","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":25,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2560730294","https://openalex.org/W2560920409","https://openalex.org/W2563399268","https://openalex.org/W2735608653","https://openalex.org/W2745461083","https://openalex.org/W2950096400","https://openalex.org/W2963565420","https://openalex.org/W2964118342","https://openalex.org/W2969679616","https://openalex.org/W2970231061","https://openalex.org/W3108864070","https://openalex.org/W3173399746","https://openalex.org/W3201068857","https://openalex.org/W4212774754","https://openalex.org/W4226424035","https://openalex.org/W4319300945","https://openalex.org/W4366273419","https://openalex.org/W4375869270","https://openalex.org/W4385245566","https://openalex.org/W4385482769","https://openalex.org/W6620707391","https://openalex.org/W6765591853"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W2964061310","https://openalex.org/W2963477107","https://openalex.org/W2231285690","https://openalex.org/W3093385053","https://openalex.org/W4389682534","https://openalex.org/W4390091918","https://openalex.org/W3045060014","https://openalex.org/W4390241396"],"abstract_inverted_index":{"Reasoning":[0],"conditioned":[1,67],"on":[2,68,96],"visual":[3,44,55,121],"and":[4,88,99,136,159,161,166],"linguistic":[5],"information":[6],"has":[7,22],"gained":[8],"immense":[9],"importance":[10],"in":[11,17,26,58,147,164,176],"recent":[12],"times.":[13],"The":[14,132,151],"prior":[15],"art":[16],"Visual":[18],"Question":[19],"Answering":[20],"(VQA)":[21],"been":[23],"predominantly":[24],"connectionist":[25,33,85],"nature.":[27],"To":[28],"resolve":[29],"the":[30,69,74,97,102,108,117,142,157,174],"issues":[31],"of":[32,77,119,134,145],"AI":[34],"models,":[35],"Symbolic":[36],"models":[37,52],"were":[38],"proposed":[39,110],"that":[40,61,115],"allowed":[41],"for":[42,64],"explainable":[43,70,120,177],"reasoning.":[45],"In":[46,105],"addition":[47],"to":[48],"semantic":[49,143],"parsing,":[50],"such":[51],"worked":[53],"towards":[54],"parsing":[56,144],"resulting":[57],"scene":[59,71,124],"graphs":[60,125],"provided":[62],"scope":[63],"accurate":[65],"reasoning":[66,122],"graphs.":[72],"However,":[73],"real":[75],"scenarios":[76],"VQA":[78,149],"cannot":[79],"always":[80,94],"be":[81],"segregated":[82],"exclusively":[83],"into":[84],"(neural":[86],"networks)":[87],"conceptual":[89,137],"modalities.":[90,104],"Rather,":[91],"they":[92],"are":[93,139],"dependent":[95],"relationships":[98],"interactions":[100],"between":[101],"two":[103],"this":[106],"work,":[107],"authors":[109],"a":[111,127],"question-guided":[112],"attention":[113,130],"mechanism":[114],"combines":[116],"approach":[118],"through":[123,141],"with":[126,156],"cross-modality-based":[128],"multi-head":[129],"mechanism.":[131],"contributions":[133],"con-nectionist":[135],"modalities":[138],"learned":[140],"questions":[146],"each":[148],"task.":[150],"novel":[152],"method":[153],"is":[154,171],"tested":[155],"VQA2.0":[158],"GQA":[160],"it":[162],"resulted":[163],"65.31%":[165],"63.06%":[167],"accuracy,":[168],"respectively,":[169],"which":[170],"better":[172],"than":[173],"state-of-the-art":[175],"AI.":[178]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}
