{"id":"https://openalex.org/W3089929663","doi":"https://doi.org/10.1109/icip40778.2020.9190724","title":"Towards Human-Like Interpretable Object Detection Via Spatial Relation Encoding","display_name":"Towards Human-Like Interpretable Object Detection Via Spatial Relation Encoding","publication_year":2020,"publication_date":"2020-09-30","ids":{"openalex":"https://openalex.org/W3089929663","doi":"https://doi.org/10.1109/icip40778.2020.9190724","mag":"3089929663"},"language":"en","primary_location":{"id":"doi:10.1109/icip40778.2020.9190724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9190724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Image Processing (ICIP)","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/A5036936141","display_name":"Jung Uk Kim","orcid":"https://orcid.org/0000-0003-4533-4875"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung Uk Kim","raw_affiliation_strings":["Image and Video Systems Lab, School of Electrical Engineering, KAIST, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Image and Video Systems Lab, School of Electrical Engineering, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103104504","display_name":"Sungjune Park","orcid":"https://orcid.org/0000-0001-7482-4553"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungjune Park","raw_affiliation_strings":["Image and Video Systems Lab, School of Electrical Engineering, KAIST, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Image and Video Systems Lab, School of Electrical Engineering, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038798134","display_name":"Yong Man Ro","orcid":"https://orcid.org/0000-0001-5306-6853"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong Man Ro","raw_affiliation_strings":["Image and Video Systems Lab, School of Electrical Engineering, KAIST, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Image and Video Systems Lab, School of Electrical Engineering, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6852,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.72374648,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3284","last_page":"3288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9984999895095825,"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":0.9984999895095825,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9977999925613403,"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/T10036","display_name":"Advanced Neural Network Applications","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"}}],"keywords":[{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7385254502296448},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7131398320198059},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6054958701133728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5712030529975891},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5409712195396423},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5390244722366333},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.5212852954864502},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.4634219706058502},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4560858905315399},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38348662853240967},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2635953426361084},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.16660812497138977},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.1338680386543274}],"concepts":[{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7385254502296448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7131398320198059},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6054958701133728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5712030529975891},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5409712195396423},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5390244722366333},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.5212852954864502},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4634219706058502},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4560858905315399},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38348662853240967},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2635953426361084},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.16660812497138977},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.1338680386543274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip40778.2020.9190724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9190724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1159302035","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2040488056","https://openalex.org/W2111267645","https://openalex.org/W2122710056","https://openalex.org/W2134158406","https://openalex.org/W2194775991","https://openalex.org/W2282821441","https://openalex.org/W2295107390","https://openalex.org/W2407521645","https://openalex.org/W2565639579","https://openalex.org/W2606462007","https://openalex.org/W2606833507","https://openalex.org/W2613718673","https://openalex.org/W2626639386","https://openalex.org/W2889698616","https://openalex.org/W2895739182","https://openalex.org/W2899771611","https://openalex.org/W2917092108","https://openalex.org/W2932399282","https://openalex.org/W2950800384","https://openalex.org/W2962858109","https://openalex.org/W2964241181","https://openalex.org/W2971107655","https://openalex.org/W2986384370","https://openalex.org/W3015777237","https://openalex.org/W3101609372","https://openalex.org/W4253455575","https://openalex.org/W4293861706","https://openalex.org/W4368066555","https://openalex.org/W6620707391","https://openalex.org/W6639102338","https://openalex.org/W6714138976","https://openalex.org/W6739575509"],"related_works":["https://openalex.org/W4235381733","https://openalex.org/W2355022049","https://openalex.org/W4292830139","https://openalex.org/W4319309705","https://openalex.org/W2520082489","https://openalex.org/W2362913948","https://openalex.org/W2116266067","https://openalex.org/W2027795965","https://openalex.org/W2364189591","https://openalex.org/W2028237718"],"abstract_inverted_index":{"The":[0,87],"performance":[1],"of":[2,49,57,90,110],"recent":[3],"deep":[4],"neural":[5],"networks":[6,29],"in":[7,33],"various":[8],"computer":[9],"vision":[10],"areas":[11],"such":[12,21],"as":[13],"object":[14,78,115,120,133],"detection":[15],"has":[16],"increased":[17],"significantly.":[18],"Along":[19],"with":[20,131],"advances,":[22],"attempts":[23],"to":[24,35,53,71,103],"visualize":[25],"and":[26,96,139],"interpret":[27],"the":[28,55,82,91,97,128],"have":[30],"been":[31],"made":[32],"order":[34],"understand":[36],"how":[37],"a":[38,41,47,65],"network":[39],"predicts":[40],"certain":[42],"result.":[43],"However,":[44],"there":[45],"is":[46],"lack":[48],"research":[50],"on":[51,135],"ways":[52],"improve":[54],"interpretability":[56],"networks\u2019":[58,74],"features.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"propose":[64],"spatial":[66,92,99,105],"relation":[67,100],"reasoning":[68],"(SRR)":[69],"framework":[70,130],"encode":[72,118],"interpretable":[73],"features,":[75],"especially":[76],"an":[77,111],"detector,":[79],"by":[80],"mimicking":[81],"human":[83],"visual":[84,124],"cognition":[85],"system.":[86],"SRR":[88],"consists":[89],"feature":[93],"encoder":[94,101],"(SFE)":[95],"graph-based":[98],"(GSRE)":[102],"consider":[104],"relationships":[106],"between":[107],"different":[108],"parts":[109],"object.":[112],"So":[113],"that,":[114],"detectors":[116,134],"can":[117],"spatially-related":[119],"features":[121],"enabling":[122],"humanlike":[123],"interpretation.":[125],"We":[126],"verified":[127],"proposed":[129],"general":[132],"public":[136],"datasets-PAS-CAL":[137],"VOC":[138],"MS":[140],"COCO.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}