{"id":"https://openalex.org/W2965719571","doi":"https://doi.org/10.24963/ijcai.2019/907","title":"Vision beyond Pixels: Visual Reasoning via Blocksworld Abstractions","display_name":"Vision beyond Pixels: Visual Reasoning via Blocksworld Abstractions","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2965719571","doi":"https://doi.org/10.24963/ijcai.2019/907","mag":"2965719571"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/907","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/907","pdf_url":"https://www.ijcai.org/proceedings/2019/0907.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0907.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035343276","display_name":"Tejas Gokhale","orcid":"https://orcid.org/0000-0002-5593-2804"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tejas Gokhale","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5035343276"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.07147021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"6436","last_page":"6437"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9923999905586243,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9883999824523926,"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":0.7706067562103271},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6665128469467163},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6353435516357422},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5676347017288208},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5615841746330261},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5564556121826172},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.5371094346046448},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.49434900283813477},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.4236680567264557},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.340528666973114},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3231147527694702},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12327522039413452},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09109872579574585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706067562103271},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6665128469467163},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6353435516357422},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5676347017288208},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5615841746330261},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5564556121826172},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.5371094346046448},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.49434900283813477},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.4236680567264557},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.340528666973114},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3231147527694702},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12327522039413452},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09109872579574585},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/907","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/907","pdf_url":"https://www.ijcai.org/proceedings/2019/0907.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/907","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/907","pdf_url":"https://www.ijcai.org/proceedings/2019/0907.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965719571.pdf","grobid_xml":"https://content.openalex.org/works/W2965719571.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2463104958","https://openalex.org/W2520858206","https://openalex.org/W2561715562","https://openalex.org/W2624614404","https://openalex.org/W2770804203","https://openalex.org/W2799262568","https://openalex.org/W2908694274","https://openalex.org/W2963150697","https://openalex.org/W2963683498","https://openalex.org/W2963907629","https://openalex.org/W6719341012","https://openalex.org/W6791858558"],"related_works":["https://openalex.org/W2378076731","https://openalex.org/W4286888643","https://openalex.org/W3210795196","https://openalex.org/W2088988140","https://openalex.org/W3171015545","https://openalex.org/W2103019253","https://openalex.org/W2951529875","https://openalex.org/W2391453316","https://openalex.org/W2297768894","https://openalex.org/W1988064119"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"trained":[3],"in":[4,13,17,77],"an":[5],"end-to-end":[6],"fashion":[7],"have":[8],"brought":[9],"about":[10,32],"exceptional":[11],"advances":[12],"computer":[14],"vision,":[15],"especially":[16],"computational":[18],"perception.":[19],"We":[20,42,83],"go":[21],"beyond":[22],"perception":[23,92],"and":[24,40,53,80,93,96],"seek":[25],"to":[26,30,104],"enable":[27],"vision":[28],"modules":[29],"reason":[31],"perceived":[33],"visual":[34,46,91],"entities":[35],"such":[36],"as":[37],"scenes,":[38],"objects":[39],"actions.":[41],"introduce":[43],"a":[44,71],"challenging":[45],"reasoning":[47],"task,":[48],"Image-Based":[49],"Event":[50],"Sequencing":[51],"(IES)":[52],"compile":[54],"the":[55,66,85],"first":[56],"IES":[57],"dataset,":[58],"Blocksworld":[59],"Image":[60],"Reasoning":[61],"Dataset":[62],"(BIRD).":[63],"Motivated":[64],"by":[65,75],"blocksworld":[67],"concept,":[68],"we":[69],"propose":[70],"modular":[72],"approach":[73,100],"supported":[74],"literature":[76],"cognitive":[78],"psychology":[79],"children's":[81],"development.":[82],"decompose":[84],"problem":[86],"into":[87],"two":[88],"stages":[89],"-":[90],"event":[94],"sequencing,":[95],"show":[97],"that":[98],"our":[99],"can":[101],"be":[102],"extended":[103],"natural":[105],"images":[106],"without":[107],"re-training.":[108]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
