{"id":"https://openalex.org/W4288045581","doi":"https://doi.org/10.1109/mic.2022.3176500","title":"Common Sense Knowledge Infusion for Visual Understanding and Reasoning: Approaches, Challenges, and Applications","display_name":"Common Sense Knowledge Infusion for Visual Understanding and Reasoning: Approaches, Challenges, and Applications","publication_year":2022,"publication_date":"2022-05-20","ids":{"openalex":"https://openalex.org/W4288045581","doi":"https://doi.org/10.1109/mic.2022.3176500"},"language":"en","primary_location":{"id":"doi:10.1109/mic.2022.3176500","is_oa":true,"landing_page_url":"https://doi.org/10.1109/mic.2022.3176500","pdf_url":"https://ieeexplore.ieee.org/ielx7/4236/9841406/09779470.pdf","source":{"id":"https://openalex.org/S205899252","display_name":"IEEE Internet Computing","issn_l":"1089-7801","issn":["1089-7801","1941-0131"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/4236/9841406/09779470.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037898063","display_name":"Muhammad Jaleed Khan","orcid":"https://orcid.org/0000-0003-4727-4722"},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Muhammad Jaleed Khan","raw_affiliation_strings":["Data Science Institute, National University of Ireland, Galway, Ireland"],"raw_orcid":"https://orcid.org/0000-0003-4727-4722","affiliations":[{"raw_affiliation_string":"Data Science Institute, National University of Ireland, Galway, Ireland","institution_ids":["https://openalex.org/I188760350"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090996360","display_name":"John G. Breslin","orcid":"https://orcid.org/0000-0001-5790-050X"},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"John G. Breslin","raw_affiliation_strings":["Data Science Institute, National University of Ireland, Galway, Ireland"],"raw_orcid":"https://orcid.org/0000-0001-5790-050X","affiliations":[{"raw_affiliation_string":"Data Science Institute, National University of Ireland, Galway, Ireland","institution_ids":["https://openalex.org/I188760350"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027850521","display_name":"Edward Curry","orcid":"https://orcid.org/0000-0001-8236-6433"},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Edward Curry","raw_affiliation_strings":["Data Science Institute, National University of Ireland, Galway, Ireland"],"raw_orcid":"https://orcid.org/0000-0001-8236-6433","affiliations":[{"raw_affiliation_string":"Data Science Institute, National University of Ireland, Galway, Ireland","institution_ids":["https://openalex.org/I188760350"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037898063"],"corresponding_institution_ids":["https://openalex.org/I188760350"],"apc_list":null,"apc_paid":null,"fwci":1.1225,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.78724104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"26","issue":"4","first_page":"21","last_page":"27"},"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":0.9987999796867371,"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":0.996399998664856,"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":0.7807872295379639},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.6503955125808716},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.6413686275482178},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.641067624092102},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.5526502728462219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5483260750770569},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.5352141857147217},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.518944263458252},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.5167431235313416},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4720488488674164},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36779898405075073},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3628818988800049},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3258986175060272},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.18074873089790344},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.13900312781333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7807872295379639},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.6503955125808716},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6413686275482178},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.641067624092102},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.5526502728462219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5483260750770569},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.5352141857147217},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.518944263458252},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5167431235313416},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4720488488674164},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36779898405075073},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3628818988800049},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3258986175060272},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.18074873089790344},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.13900312781333923},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mic.2022.3176500","is_oa":true,"landing_page_url":"https://doi.org/10.1109/mic.2022.3176500","pdf_url":"https://ieeexplore.ieee.org/ielx7/4236/9841406/09779470.pdf","source":{"id":"https://openalex.org/S205899252","display_name":"IEEE Internet Computing","issn_l":"1089-7801","issn":["1089-7801","1941-0131"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet Computing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/mic.2022.3176500","is_oa":true,"landing_page_url":"https://doi.org/10.1109/mic.2022.3176500","pdf_url":"https://ieeexplore.ieee.org/ielx7/4236/9841406/09779470.pdf","source":{"id":"https://openalex.org/S205899252","display_name":"IEEE Internet Computing","issn_l":"1089-7801","issn":["1089-7801","1941-0131"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[{"id":"https://openalex.org/G2394637485","display_name":null,"funder_award_id":"18/CRT/6223","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G3695527833","display_name":null,"funder_award_id":"12/RC/2289_P2","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G3778540993","display_name":null,"funder_award_id":"12/RC/2289\\_P2","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G5098725405","display_name":null,"funder_award_id":"12/RC/","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4288045581.pdf","grobid_xml":"https://content.openalex.org/works/W4288045581.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2479423890","https://openalex.org/W2607855566","https://openalex.org/W2950096400","https://openalex.org/W2962785943","https://openalex.org/W2963184176","https://openalex.org/W2963536419","https://openalex.org/W2963650529","https://openalex.org/W2982378168","https://openalex.org/W3034984754","https://openalex.org/W3036869132","https://openalex.org/W3095279991","https://openalex.org/W3108864070","https://openalex.org/W3114427170","https://openalex.org/W3165066581","https://openalex.org/W3217675893","https://openalex.org/W4206305425","https://openalex.org/W4285620459","https://openalex.org/W4287235428","https://openalex.org/W4386435682","https://openalex.org/W4388816994","https://openalex.org/W6770922693","https://openalex.org/W6784868143","https://openalex.org/W6787982190","https://openalex.org/W6793771069","https://openalex.org/W6810790650"],"related_works":["https://openalex.org/W4226538672","https://openalex.org/W4287759503","https://openalex.org/W3034469251","https://openalex.org/W2981750021","https://openalex.org/W4285208802","https://openalex.org/W4302773889","https://openalex.org/W2184048809","https://openalex.org/W4385584398","https://openalex.org/W3173399746","https://openalex.org/W4288045581"],"abstract_inverted_index":{"Visual":[0],"understanding":[1,150],"involves":[2],"detecting":[3],"objects":[4],"in":[5,85,115,139],"a":[6],"scene":[7,25,32,39,94,129],"and":[8,54,90,97,106,109,125,132,136,151],"investigating":[9],"rich":[10,105],"semantic":[11],"relationships":[12],"between":[13],"the":[14,35,38,64,87,93,113,123,128,133],"objects,":[15],"which":[16],"is":[17,27,45],"required":[18],"for":[19,30,42,72,148],"downstream":[20],"visual":[21,43,116,149],"reasoning":[22,44,102],"tasks.":[23],"The":[24],"graph":[26,40,95,130],"widely":[28],"used":[29],"structured":[31],"representation,":[33],"however,":[34],"performance":[36],"of":[37,63,92,127],"generation":[41,96,131],"limited":[46],"due":[47],"to":[48],"challenges":[49,138],"posed":[50],"by":[51,103],"imbalanced":[52],"datasets":[53],"insufficient":[55],"attention":[56],"toward":[57],"common":[58,140],"sense":[59,141],"knowledge":[60,73,77,81,111,142,146],"infusion.":[61,74],"Most":[62],"existing":[65],"approaches":[66,135],"use":[67],"statistical":[68],"or":[69],"language":[70],"priors":[71],"Common":[75],"Sense":[76],"infusion":[78,143],"using":[79,144],"heterogeneous":[80,145],"graphs":[82,147],"can":[83],"help":[84],"improving":[86],"accuracy,":[88],"robustness,":[89],"generalizability":[91],"enable":[98],"explainable":[99],"higher":[100],"level":[101],"providing":[104],"diverse":[107],"background":[108,124],"factual":[110],"about":[112],"concepts":[114],"scenes.":[117],"In":[118],"this":[119],"article,":[120],"we":[121],"present":[122],"applications":[126],"initial":[134],"key":[137],"reasoning.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
