{"id":"https://openalex.org/W7124993640","doi":"https://doi.org/10.1109/access.2026.3655826","title":"A Unified Lightweight Network for Complex Scene Image Understanding via Multi-Task Joint Learning","display_name":"A Unified Lightweight Network for Complex Scene Image Understanding via Multi-Task Joint Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7124993640","doi":"https://doi.org/10.1109/access.2026.3655826"},"language":null,"primary_location":{"id":"doi:10.1109/access.2026.3655826","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3655826","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3655826","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007589773","display_name":"Tingting Guo","orcid":"https://orcid.org/0009-0008-1732-8631"},"institutions":[{"id":"https://openalex.org/I186272606","display_name":"Guangdong University of Foreign Studies","ror":"https://ror.org/00fhc9y79","country_code":"CN","type":"education","lineage":["https://openalex.org/I186272606"]},{"id":"https://openalex.org/I4402553993","display_name":"Guangdong Teachers College of Foreign Language and Arts","ror":"https://ror.org/02regkz96","country_code":null,"type":"education","lineage":["https://openalex.org/I4402553993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Guo","raw_affiliation_strings":["Guangdong Teachers College of Foreign Language and Arts, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Teachers College of Foreign Language and Arts, Guangzhou, China","institution_ids":["https://openalex.org/I186272606","https://openalex.org/I4402553993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064711501","display_name":"Sainan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I186272606","display_name":"Guangdong University of Foreign Studies","ror":"https://ror.org/00fhc9y79","country_code":"CN","type":"education","lineage":["https://openalex.org/I186272606"]},{"id":"https://openalex.org/I4402553993","display_name":"Guangdong Teachers College of Foreign Language and Arts","ror":"https://ror.org/02regkz96","country_code":null,"type":"education","lineage":["https://openalex.org/I4402553993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sainan Yang","raw_affiliation_strings":["Guangdong Teachers College of Foreign Language and Arts, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-3455-9534","affiliations":[{"raw_affiliation_string":"Guangdong Teachers College of Foreign Language and Arts, Guangzhou, China","institution_ids":["https://openalex.org/I186272606","https://openalex.org/I4402553993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103245345","display_name":"Yao Fu","orcid":"https://orcid.org/0000-0001-9805-8419"},"institutions":[{"id":"https://openalex.org/I186272606","display_name":"Guangdong University of Foreign Studies","ror":"https://ror.org/00fhc9y79","country_code":"CN","type":"education","lineage":["https://openalex.org/I186272606"]},{"id":"https://openalex.org/I4402553993","display_name":"Guangdong Teachers College of Foreign Language and Arts","ror":"https://ror.org/02regkz96","country_code":null,"type":"education","lineage":["https://openalex.org/I4402553993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Fu","raw_affiliation_strings":["Guangdong Teachers College of Foreign Language and Arts, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Teachers College of Foreign Language and Arts, Guangzhou, China","institution_ids":["https://openalex.org/I186272606","https://openalex.org/I4402553993"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092278547","display_name":"Daitao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4403386539","display_name":"Software Engineering Institute of Guangzhou","ror":"https://ror.org/0549ke970","country_code":null,"type":"education","lineage":["https://openalex.org/I4403386539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daitao Wang","raw_affiliation_strings":["Department of Network Technology, Software Engineering Institute of Guangzhou, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-7377-6520","affiliations":[{"raw_affiliation_string":"Department of Network Technology, Software Engineering Institute of Guangzhou, Guangzhou, China","institution_ids":["https://openalex.org/I4403386539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06265478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"14916","last_page":"14930"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.18770000338554382,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.18770000338554382,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.15070000290870667,"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/T11846","display_name":"Cultural Heritage Management and Preservation","score":0.09109999984502792,"subfield":{"id":"https://openalex.org/subfields/1204","display_name":"Archeology"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6312000155448914},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5983999967575073},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5871000289916992},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5723999738693237},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5719000101089478},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5327000021934509},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4968999922275543},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47269999980926514},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.45179998874664307},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.41819998621940613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8837000131607056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6395000219345093},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6312000155448914},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5983999967575073},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5871000289916992},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5723999738693237},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5719000101089478},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5327000021934509},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4968999922275543},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4235000014305115},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4083000123500824},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.40639999508857727},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36550000309944153},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C60671577","wikidata":"https://www.wikidata.org/wiki/Q210272","display_name":"Cultural heritage","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.31310001015663147},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.25369998812675476},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2026.3655826","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3655826","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3655826","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3655826","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5995734333992004,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2040582952","https://openalex.org/W2110764733","https://openalex.org/W2157331557","https://openalex.org/W2340897893","https://openalex.org/W2395611524","https://openalex.org/W2412782625","https://openalex.org/W2562137921","https://openalex.org/W2618530766","https://openalex.org/W2752782242","https://openalex.org/W2787091153","https://openalex.org/W2798441115","https://openalex.org/W2963125010","https://openalex.org/W2964217532","https://openalex.org/W2982083293","https://openalex.org/W3034704453","https://openalex.org/W3112503277","https://openalex.org/W3169865585","https://openalex.org/W3196904463","https://openalex.org/W4292261175","https://openalex.org/W4312688875","https://openalex.org/W4385245566","https://openalex.org/W4386076267","https://openalex.org/W4386497700","https://openalex.org/W4390175399","https://openalex.org/W4390273016","https://openalex.org/W4390403315","https://openalex.org/W4390479310","https://openalex.org/W4390501440","https://openalex.org/W4390506468","https://openalex.org/W4392374634","https://openalex.org/W4397023700","https://openalex.org/W4401577246","https://openalex.org/W4413277254","https://openalex.org/W4414404778","https://openalex.org/W4414499292"],"related_works":[],"abstract_inverted_index":{"Multi-task":[0],"joint":[1,40],"learning":[2,91],"for":[3,43,65,215],"complex":[4],"scene":[5],"image":[6,44],"understanding":[7,62,218],"faces":[8],"multiple":[9],"challenges,":[10],"including":[11],"diverse":[12],"visual":[13,61,217],"elements,":[14],"task-specific":[15],"demands,":[16],"and":[17,48,68,100,114,138,151,157,168,176,195,212,223,230],"constrained":[18],"computational":[19],"resources.":[20],"These":[21,141],"challenges":[22],"are":[23,233],"particularly":[24],"prominent":[25],"in":[26,219],"specialized":[27],"domains":[28],"such":[29],"as":[30],"Intangible":[31],"Cultural":[32],"Heritage":[33],"(ICH),":[34],"where":[35],"current":[36],"research":[37,208],"lacks":[38],"effective":[39],"modeling":[41],"approaches":[42],"classification,":[45,97],"semantic":[46,124],"segmentation,":[47],"object":[49],"localization":[50],"tasks.":[51],"To":[52,81],"address":[53],"this":[54,83],"gap,":[55],"we":[56,85],"introduce":[57],"a":[58,70,107,127,181,210],"novel":[59],"multi-task":[60,90],"problem":[63],"tailored":[64],"ICH":[66,79],"scenarios,":[67],"construct":[69],"high-quality":[71],"dataset\u2014ICH-Scene3800\u2014comprising":[72],"3,800":[73],"annotated":[74],"images":[75],"across":[76,149],"12":[77],"representative":[78],"categories.":[80],"tackle":[82],"task,":[84],"propose":[86],"the":[87,145,158,201],"first":[88],"lightweight":[89,129],"framework":[92,105],"capable":[93],"of":[94,185],"performing":[95],"image-level":[96],"instance-level":[98,101],"localization,":[99],"detection":[102],"simultaneously.":[103],"The":[104,228],"employs":[106],"shared":[108],"backbone":[109],"to":[110,133],"learn":[111],"general-purpose":[112],"features":[113],"integrates":[115],"an":[116,189],"attention-guided":[117],"dynamic":[118],"fusion":[119],"mechanism":[120],"that":[121,162],"facilitates":[122],"cross-task":[123],"interaction.":[125],"Furthermore,":[126],"group-convolution-based":[128],"architecture":[130],"is":[131],"introduced":[132],"enable":[134],"efficient":[135,213],"feature":[136],"extraction":[137],"resource-aware":[139],"deployment.":[140],"designs":[142],"significantly":[143,196],"enhance":[144],"model\u2019s":[146],"generalization":[147],"ability":[148],"tasks":[150],"scenes.":[152],"Extensive":[153],"experiments":[154],"on":[155,188,200],"ICH-Scene3800":[156],"Cityscapes":[159],"dataset":[160],"demonstrate":[161],"our":[163],"model":[164],"achieves":[165],"92.19%":[166],"mIoU":[167],"82.36%":[169],"mIoU,":[170],"respectively,":[171],"with":[172],"only":[173],"0.024M":[174],"parameters":[175],"0.085":[177],"GFLOPs.":[178],"It":[179],"reaches":[180],"real-time":[182],"processing":[183],"speed":[184],"98.5":[186],"FPS":[187],"NVIDIA":[190],"GeForce":[191],"GTX":[192],"1060":[193],"(6GB)":[194],"outperforms":[197],"existing":[198],"methods":[199],"LSES":[202],"metric,":[203],"achieving":[204],"state-of-the-art":[205],"performance.":[206],"This":[207],"provides":[209],"practical":[211],"solution":[214],"intelligent":[216],"cultural":[220],"heritage":[221],"preservation":[222],"other":[224],"resource-constrained":[225],"application":[226],"scenarios.":[227],"code":[229],"related":[231],"materials":[232],"available":[234],"at":[235],"https://github.com/Upno111/ICH.":[236]},"counts_by_year":[],"updated_date":"2026-02-02T03:55:41.653505","created_date":"2026-01-21T00:00:00"}