{"id":"https://openalex.org/W4404562731","doi":"https://doi.org/10.1109/tcsvt.2024.3502755","title":"Hierarchical Context Transformer for Multi-Level Semantic Scene Understanding","display_name":"Hierarchical Context Transformer for Multi-Level Semantic Scene Understanding","publication_year":2024,"publication_date":"2024-11-20","ids":{"openalex":"https://openalex.org/W4404562731","doi":"https://doi.org/10.1109/tcsvt.2024.3502755"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3502755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3502755","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5031252766","display_name":"Luoying Hao","orcid":"https://orcid.org/0000-0003-2838-546X"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luoying Hao","raw_affiliation_strings":["Department of Computer Science and Engineering, Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen, China","Research Institute of Trustworthy Autonomous Systems and Dept. of Computer Science and Engineering, Southern University of Science and Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Research Institute of Trustworthy Autonomous Systems and Dept. of Computer Science and Engineering, Southern University of Science and Technology, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057374436","display_name":"Yan Hu","orcid":"https://orcid.org/0000-0002-7663-3096"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Hu","raw_affiliation_strings":["Department of Computer Science and Engineering, Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen, China","Research Institute of Trustworthy Autonomous Systems and Dept. of Computer Science and Engineering, Southern University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-7663-3096","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Research Institute of Trustworthy Autonomous Systems and Dept. of Computer Science and Engineering, Southern University of Science and Technology, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Yue","orcid":"https://orcid.org/0009-0006-8505-3057"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang Yue","raw_affiliation_strings":["School of Computer Science, University of Birmingham, Birmingham, U.K","School of Computer Science, University of Birmingham, UK"],"raw_orcid":"https://orcid.org/0009-0006-8505-3057","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Birmingham, Birmingham, U.K","institution_ids":["https://openalex.org/I79619799"]},{"raw_affiliation_string":"School of Computer Science, University of Birmingham, UK","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326385","display_name":"Wu Li","orcid":"https://orcid.org/0000-0002-2175-4579"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Wu","raw_affiliation_strings":["MGI Tech Company Ltd., Shenzhen, China","MGI Tech Co., Ltd, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MGI Tech Company Ltd., Shenzhen, China","institution_ids":[]},{"raw_affiliation_string":"MGI Tech Co., Ltd, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010970485","display_name":"Huazhu Fu","orcid":"https://orcid.org/0000-0002-9702-5524"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huazhu Fu","raw_affiliation_strings":["Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Fusionopolis, Singapore","Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore"],"raw_orcid":"https://orcid.org/0000-0002-9702-5524","affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Fusionopolis, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3004594783"]},{"raw_affiliation_string":"Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3004594783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078754523","display_name":"Jinming Duan","orcid":"https://orcid.org/0000-0002-5108-2128"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinming Duan","raw_affiliation_strings":["School of Computer Science, University of Birmingham, Birmingham, U.K","School of Computer Science, University of Birmingham, UK"],"raw_orcid":"https://orcid.org/0000-0002-5108-2128","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Birmingham, Birmingham, U.K","institution_ids":["https://openalex.org/I79619799"]},{"raw_affiliation_string":"School of Computer Science, University of Birmingham, UK","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100325209","display_name":"Jiang Liu","orcid":"https://orcid.org/0000-0001-6281-6505"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang Liu","raw_affiliation_strings":["Department of Computer Science and Engineering, Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen, China","Research Institute of Trustworthy Autonomous Systems and Dept. of Computer Science and Engineering, Southern University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0001-6281-6505","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Research Institute of Trustworthy Autonomous Systems and Dept. of Computer Science and Engineering, Southern University of Science and Technology, China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1514,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78356668,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"35","issue":"4","first_page":"3134","last_page":"3145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9415000081062317,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9415000081062317,"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":0.6755257248878479},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.47834512591362},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44338905811309814},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.41100814938545227},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39434105157852173},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3662782311439514},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10377997159957886},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.09525376558303833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6755257248878479},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47834512591362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44338905811309814},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.41100814938545227},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39434105157852173},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3662782311439514},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10377997159957886},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.09525376558303833},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2024.3502755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3502755","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/d11d0701-7068-49f3-b4e0-937b5308e563","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/d11d0701-7068-49f3-b4e0-937b5308e563","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Hao, L, Hu, Y, Yue, Y, Wu, L, Fu, H, Duan, J & Liu, J 2025, 'Hierarchical Context Transformer for Multi-Level Semantic Scene Understanding', IEEE Transactions on Circuits and Systems for Video Technology, vol. 35, no. 4, pp. 3134-3145. https://doi.org/10.1109/TCSVT.2024.3502755","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G4874454907","display_name":null,"funder_award_id":"82102189","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8999964948","display_name":null,"funder_award_id":"82272086","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2016545368","https://openalex.org/W2266464013","https://openalex.org/W2921303908","https://openalex.org/W2963524571","https://openalex.org/W2975042877","https://openalex.org/W2980852587","https://openalex.org/W3101712992","https://openalex.org/W3137763248","https://openalex.org/W3150630416","https://openalex.org/W3160614854","https://openalex.org/W3196971551","https://openalex.org/W3198379050","https://openalex.org/W4214614183","https://openalex.org/W4282969740","https://openalex.org/W4285818716","https://openalex.org/W4308184372","https://openalex.org/W4312064789","https://openalex.org/W4312275869","https://openalex.org/W4312769131","https://openalex.org/W4360584327","https://openalex.org/W4364321471","https://openalex.org/W4364321974","https://openalex.org/W4378194725","https://openalex.org/W4381299118","https://openalex.org/W4382240182","https://openalex.org/W4386071754","https://openalex.org/W4387211814","https://openalex.org/W4387211845","https://openalex.org/W4393207082","https://openalex.org/W4396605036","https://openalex.org/W4399039310","https://openalex.org/W6620707391","https://openalex.org/W6756911974","https://openalex.org/W6758742486","https://openalex.org/W6759579507","https://openalex.org/W6773996751","https://openalex.org/W6775468141","https://openalex.org/W6780593743","https://openalex.org/W6790544665","https://openalex.org/W6797801312","https://openalex.org/W6809665764","https://openalex.org/W6842830045","https://openalex.org/W6843230717","https://openalex.org/W6846313647","https://openalex.org/W6849878650"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"A":[0],"comprehensive":[1],"and":[2,62,83,110,161,179],"explicit":[3],"understanding":[4,69],"of":[5,121,151,190],"surgical":[6,30],"scenes":[7],"plays":[8],"a":[9,76,94,180,199],"vital":[10],"role":[11],"in":[12,17],"developing":[13],"context-aware":[14],"computer-assisted":[15],"systems":[16],"the":[18,40,86,89,118,122,133,148,152,159,187,195],"operating":[19],"theatre.":[20],"However,":[21],"few":[22],"works":[23],"provide":[24],"systematical":[25],"analysis":[26],"to":[27,38,102,131,135,157,164],"enable":[28],"hierarchical":[29,78,95],"scene":[31,68],"understanding.":[32],"In":[33],"this":[34,72],"work,":[35],"we":[36,74,154],"propose":[37,75,155],"represent":[39],"tasks":[41],"set":[42],"[phase":[43],"recognition":[44,53],"<inline-formula":[45,54],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[46,55,208],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[47,56],"<tex-math":[48,57],"notation=\"LaTeX\">$\\rightarrow":[49,58],"$":[50,59],"</tex-math></inline-formula>":[51,60],"step":[52],"action":[61],"instrument":[63],"detection]":[64],"as":[65],"multi-level":[66,107],"semantic":[67],"(MSSU).":[70],"For":[71],"target,":[73],"novel":[77],"context":[79],"transformer":[80],"(HCT)":[81],"network":[82],"thoroughly":[84],"explore":[85],"relations":[87],"across":[88],"different":[90,123],"level":[91],"tasks.":[92,145],"Specifically,":[93],"relation":[96],"aggregation":[97],"module":[98],"(HRAM)":[99],"is":[100,129,204],"designed":[101],"concurrently":[103],"relate":[104],"entries":[105],"inside":[106],"interaction":[108],"information":[109,142],"then":[111],"augment":[112],"task-specific":[113],"features.":[114],"To":[115],"further":[116],"boost":[117],"representation":[119],"learning":[120,127],"tasks,":[124],"inter-task":[125],"contrastive":[126],"(ICL)":[128],"presented":[130],"guide":[132],"model":[134],"learn":[136],"task-wise":[137],"features":[138],"via":[139],"absorbing":[140],"complementary":[141],"from":[143],"other":[144],"Furthermore,":[146],"considering":[147],"computational":[149],"costs":[150],"transformer,":[153],"HCT+":[156],"integrate":[158],"spatial":[160],"temporal":[162],"adapter":[163],"access":[165],"competitive":[166],"performance":[167,189],"on":[168,175],"substantially":[169],"fewer":[170],"tunable":[171],"parameters.":[172],"Extensive":[173],"experiments":[174],"our":[176,191],"cataract":[177],"dataset":[178,185],"publicly":[181],"available":[182,205],"endoscopic":[183],"PSI-AVA":[184],"demonstrate":[186],"outstanding":[188],"method,":[192],"consistently":[193],"exceeding":[194],"state-of-the-art":[196],"methods":[197],"by":[198],"large":[200],"margin.":[201],"The":[202],"code":[203],"at":[206],"<uri":[207],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/Aurora-hao/HCT</uri>.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}