{"id":"https://openalex.org/W4403791457","doi":"https://doi.org/10.1145/3664647.3681246","title":"Hierarchical Perceptual and Predictive Analogy-Inference Network for Abstract Visual Reasoning","display_name":"Hierarchical Perceptual and Predictive Analogy-Inference Network for Abstract Visual Reasoning","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791457","doi":"https://doi.org/10.1145/3664647.3681246"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681246","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5100351681","display_name":"Wentao He","orcid":"https://orcid.org/0000-0002-6319-1639"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wentao He","raw_affiliation_strings":["University of Nottingham Ningbo China, Ningbo, China"],"affiliations":[{"raw_affiliation_string":"University of Nottingham Ningbo China, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033219457","display_name":"Jianfeng Ren","orcid":"https://orcid.org/0000-0003-4619-6590"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Ren","raw_affiliation_strings":["University of Nottingham Ningbo China, Ningbo, China"],"affiliations":[{"raw_affiliation_string":"University of Nottingham Ningbo China, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046750599","display_name":"Ruibin Bai","orcid":"https://orcid.org/0000-0003-1722-568X"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruibin Bai","raw_affiliation_strings":["University of Nottingham Ningbo China, Ningbo, China"],"affiliations":[{"raw_affiliation_string":"University of Nottingham Ningbo China, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085533260","display_name":"Xudong Jiang","orcid":"https://orcid.org/0000-0002-9104-2315"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xudong Jiang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100351681"],"corresponding_institution_ids":["https://openalex.org/I13591777"],"apc_list":null,"apc_paid":null,"fwci":0.4986,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6612481,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4841","last_page":"4850"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9966999888420105,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9941999912261963,"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/analogy","display_name":"Analogy","score":0.9054900407791138},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7841235995292664},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6890275478363037},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6350922584533691},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5400863289833069},{"id":"https://openalex.org/keywords/predictive-inference","display_name":"Predictive inference","score":0.5109228491783142},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.5004031658172607},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4255371689796448},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.42322683334350586},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.28071266412734985},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18225589394569397},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.11149534583091736},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.10117509961128235},{"id":"https://openalex.org/keywords/frequentist-inference","display_name":"Frequentist inference","score":0.0904543399810791},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.0842689573764801},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.0652618408203125}],"concepts":[{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.9054900407791138},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7841235995292664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6890275478363037},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6350922584533691},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5400863289833069},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.5109228491783142},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.5004031658172607},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4255371689796448},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.42322683334350586},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.28071266412734985},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18225589394569397},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.11149534583091736},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.10117509961128235},{"id":"https://openalex.org/C162376815","wikidata":"https://www.wikidata.org/wiki/Q2158281","display_name":"Frequentist inference","level":4,"score":0.0904543399810791},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.0842689573764801},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0652618408203125},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681246","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":42,"referenced_works":["https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2561715562","https://openalex.org/W2897857500","https://openalex.org/W2913142708","https://openalex.org/W2963115613","https://openalex.org/W2963690694","https://openalex.org/W2981665364","https://openalex.org/W2989899308","https://openalex.org/W3000459150","https://openalex.org/W3005881764","https://openalex.org/W3090110441","https://openalex.org/W3099455966","https://openalex.org/W3117577445","https://openalex.org/W3138516171","https://openalex.org/W3174105824","https://openalex.org/W3194036410","https://openalex.org/W3207005999","https://openalex.org/W4212774754","https://openalex.org/W4295751877","https://openalex.org/W4308784724","https://openalex.org/W4312338297","https://openalex.org/W4312565042","https://openalex.org/W4312761939","https://openalex.org/W4322718246","https://openalex.org/W4372269167","https://openalex.org/W4372269769","https://openalex.org/W4379929708","https://openalex.org/W4382450481","https://openalex.org/W4382464482","https://openalex.org/W4383337770","https://openalex.org/W4383619072","https://openalex.org/W4385430086","https://openalex.org/W4386071473","https://openalex.org/W4386076283","https://openalex.org/W4386076343","https://openalex.org/W4386120668","https://openalex.org/W4386590413","https://openalex.org/W4388185892","https://openalex.org/W4403791597","https://openalex.org/W4403792529","https://openalex.org/W6767328352"],"related_works":["https://openalex.org/W2095758081","https://openalex.org/W1511447821","https://openalex.org/W3192934159","https://openalex.org/W2225746827","https://openalex.org/W3037690595","https://openalex.org/W2911337295","https://openalex.org/W2119468838","https://openalex.org/W4298105224","https://openalex.org/W2741491283","https://openalex.org/W2501472105"],"abstract_inverted_index":{"Advances":[0],"in":[1,47,57,156],"computer":[2],"vision":[3],"research":[4],"enable":[5],"human-like":[6],"high-dimensional":[7],"perceptual":[8,63],"induction":[9],"over":[10,170,184],"analogical":[11,143],"visual":[12],"reasoning":[13,124,144],"problems,":[14],"such":[15],"as":[16],"Raven's":[17],"Progressive":[18],"Matrices":[19],"(RPMs).":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"propose":[25],"a":[26,62,69,131],"Hierarchical":[27],"Perception":[28],"and":[29,76,89,139,163],"Predictive":[30,126],"Analogy-Inference":[31,127,134],"network":[32],"(HP^2AI),":[33],"consisting":[34,67],"of":[35,43,49,54,68,71,130,133,147],"three":[36],"major":[37],"components":[38],"that":[39,176],"tackle":[40],"key":[41],"challenges":[42],"RPM":[44,60,173],"problems.":[45],"Firstly,":[46],"view":[48],"the":[50,91,107,112,119,141,151,157,177,186],"limited":[51],"receptive":[52],"fields":[53],"shallow":[55],"networks":[56],"most":[58,99],"existing":[59],"solvers,":[61],"encoder":[64],"is":[65],"proposed,":[66],"series":[70],"hierarchically":[72],"coupled":[73],"Patch":[74],"Attention":[75,154],"Local":[77],"Context":[78],"(PALC)":[79],"blocks,":[80],"which":[81],"could":[82],"capture":[83,90],"local":[84],"attributes":[85,162],"at":[86,95],"early":[87],"stages":[88],"global":[92],"panel":[93],"layout":[94],"deep":[96],"stages.":[97],"Secondly,":[98],"methods":[100,188],"seek":[101],"for":[102],"object-level":[103],"similarities":[104],"to":[105,111,117,137],"map":[106],"context":[108],"images":[109],"directly":[110],"answer":[113],"image,":[114],"while":[115],"failing":[116],"extract":[118],"underlying":[120],"analogies.":[121],"The":[122],"proposed":[123,158,178],"module,":[125],"(PredAI),":[128],"consists":[129],"set":[132],"Blocks":[135],"(AIBs)":[136],"model":[138],"exploit":[140],"inherent":[142],"rules":[145],"instead":[146],"object":[148],"similarity.":[149],"Lastly,":[150],"Squeeze-and-Excitation":[152],"Channel-wise":[153],"(SECA)":[155],"PredAI":[159],"discriminates":[160],"essential":[161],"analogies":[164],"from":[165],"irrelevant":[166],"ones.":[167],"Extensive":[168],"experiments":[169],"four":[171,192],"benchmark":[172],"datasets":[174],"show":[175],"HP^2AI":[179],"achieves":[180],"significant":[181],"performance":[182],"gains":[183],"all":[185,191],"state-of-the-art":[187],"consistently":[189],"on":[190],"datasets.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}