{"id":"https://openalex.org/W7204186482","doi":"https://doi.org/10.48550/arxiv.2608.21443","title":"Text-Guided Visual Dependency Graph Learning with Cross-Modal Attention Priors","display_name":"Text-Guided Visual Dependency Graph Learning with Cross-Modal Attention Priors","publication_year":2026,"publication_date":"2026-08-19","ids":{"openalex":"https://openalex.org/W7204186482","doi":"https://doi.org/10.48550/arxiv.2608.21443"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.21443","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21443","pdf_url":"https://arxiv.org/pdf/2608.21443","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.21443","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148121926","display_name":"Fei Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Fei","raw_affiliation_strings":["Stony Brook University , USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University , USA,","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143809387","display_name":"Yutong Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Yutong","raw_affiliation_strings":["Sichuan University , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University , China,","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148147931","display_name":"Yang Ye","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139322472","display_name":"Universiti Sains Malaysia","ror":"https://ror.org/02rgb2k63","country_code":"MY","type":"education","lineage":["https://openalex.org/I139322472"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Ye, Yang","raw_affiliation_strings":["Universiti Sains Malaysia , Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiti Sains Malaysia , Malaysia","institution_ids":["https://openalex.org/I139322472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111264213","display_name":"jinxian chen","orcid":"https://orcid.org/0009-0001-6590-1016","observed_orcids":["https://orcid.org/0009-0001-6590-1016"]},"institutions":[{"id":"https://openalex.org/I139322472","display_name":"Universiti Sains Malaysia","ror":"https://ror.org/02rgb2k63","country_code":"MY","type":"education","lineage":["https://openalex.org/I139322472"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Chen, Jinxian","raw_affiliation_strings":["Universiti Sains Malaysia , Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiti Sains Malaysia , Malaysia","institution_ids":["https://openalex.org/I139322472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148114323","display_name":"Wang Wenshuai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139322472","display_name":"Universiti Sains Malaysia","ror":"https://ror.org/02rgb2k63","country_code":"MY","type":"education","lineage":["https://openalex.org/I139322472"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Wenshuai, Wang","raw_affiliation_strings":["Universiti Sains Malaysia , Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiti Sains Malaysia , Malaysia","institution_ids":["https://openalex.org/I139322472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123711955","display_name":"Xiong Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Xiong","raw_affiliation_strings":["University of Science and Technology of China , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China , China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9355000257492065,"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":0.9355000257492065,"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":0.03759999945759773,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.0024999999441206455,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sparse-gaussian-graphical-models","display_name":"sparse Gaussian graphical models","score":0.6740000247955322},{"id":"https://openalex.org/keywords/cross-modal-attention","display_name":"cross-modal attention","score":0.6790000200271606},{"id":"https://openalex.org/keywords/vision-language-representation-learning","display_name":"vision-language representation learning","score":0.6510000228881836},{"id":"https://openalex.org/keywords/admm-optimization","display_name":"ADMM optimization","score":0.6060000061988831}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6510999798774719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6309000253677368},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6193000078201294},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5559999942779541},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5357999801635742},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.5095999836921692},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4763000011444092},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.47130000591278076},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4090000092983246},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3952000141143799},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38350000977516174},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3422999978065491},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2906999886035919},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C5134670","wikidata":"https://www.wikidata.org/wiki/Q1626444","display_name":"Cut","level":4,"score":0.28200000524520874},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C13251829","wikidata":"https://www.wikidata.org/wiki/Q3085841","display_name":"Dense graph","level":5,"score":0.2597000002861023},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.251800000667572},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.21443","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21443","pdf_url":"https://arxiv.org/pdf/2608.21443","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.21443","doi":"https://doi.org/10.48550/arxiv.2608.21443","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.21443","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.21443","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21443","pdf_url":"https://arxiv.org/pdf/2608.21443","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/16","score":0.4724811017513275,"display_name":"Peace, justice, and strong institutions"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204186482.pdf","grobid_xml":"https://content.openalex.org/works/W7204186482.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7151516353","https://openalex.org/W7134072624","https://openalex.org/W7137952383","https://openalex.org/W7213520406","https://openalex.org/W3105486918","https://openalex.org/W7155057884","https://openalex.org/W7104281278","https://openalex.org/W7115059507","https://openalex.org/W3038476992","https://openalex.org/W4304098627"],"abstract_inverted_index":{"Estimating":[0],"interpretable":[1],"conditional-dependence":[2,196],"structures":[3],"from":[4],"multimodal":[5],"visual-linguistic":[6],"features":[7],"remains":[8],"largely":[9],"unexplored.":[10],"We":[11],"propose":[12],"CM-GLasso":[13,29,150],"(Cross-Modal":[14],"Graphical":[15,27],"Lasso),":[16],"a":[17,35,63,69,78,97,109,132,138],"framework":[18],"that":[19,39,73,101,149],"bridges":[20],"vision-language":[21],"representation":[22],"learning":[23],"and":[24,45,104,119,137,160,176,188],"sparse":[25,127,195],"Gaussian":[26],"Models.":[28],"introduces":[30],"three":[31],"key":[32],"components:":[33],"(i)":[34],"text":[36],"visualization":[37],"strategy":[38],"renders":[40],"class-attribute":[41],"descriptions":[42],"as":[43,54],"images":[44],"processes":[46],"them":[47],"through":[48],"the":[49,114,164,170,177,182],"same":[50],"SigLIP-2":[51],"vision":[52],"encoder":[53],"natural":[55],"images,":[56],"yielding":[57,193],"prototype-indexed":[58],"patch-level":[59],"attention":[60],"footprints":[61],"in":[62],"shared":[64,103],"feature":[65],"coordinate":[66],"system;":[67],"(ii)":[68],"cross-attention":[70],"distillation":[71],"mechanism":[72],"condenses":[74],"high-dimensional":[75],"patches":[76],"into":[77],"small":[79],"set":[80],"of":[81],"semantic":[82],"graph":[83,128],"nodes,":[84],"whose":[85],"attention-footprint":[86],"similarities":[87],"yield":[88],"cross-modal":[89],"structural":[90],"priors":[91],"for":[92],"non-uniform":[93],"L1":[94],"penalization;":[95],"(iii)":[96],"joint":[98],"ADMM":[99],"formulation":[100],"estimates":[102],"class-specific":[105],"precision":[106],"components":[107],"within":[108],"single":[110],"convex":[111],"objective,":[112],"avoiding":[113],"need":[115],"to":[116],"first":[117],"estimate":[118],"then":[120],"decompose":[121],"separate":[122],"class-wise":[123],"graphs.":[124],"The":[125],"learned":[126],"topologies":[129],"directly":[130],"support":[131],"parameter-free,":[133],"precision-based":[134],"classification":[135,173],"rule":[136],"lightweight":[139],"topology-aware":[140],"segmentation":[141,179],"head.":[142],"Extensive":[143],"experiments":[144],"on":[145,185],"eight":[146],"benchmarks":[147],"demonstrate":[148],"achieves":[151],"competitive":[152],"or":[153],"superior":[154],"performance":[155],"compared":[156],"with":[157,198],"strong":[158],"feature-based":[159],"task-specific":[161],"baselines.":[162],"Under":[163],"matched":[165],"controlled":[166,183],"protocol,":[167],"it":[168],"attains":[169],"highest":[171,178],"average":[172],"accuracy":[174],"(91.97%)":[175],"mIoU":[180],"among":[181],"baselines":[184],"VOC":[186],"(74.75%)":[187],"ADE20K":[189],"(64.01%),":[190],"while":[191],"also":[192],"explicit":[194],"graphs":[197],"common-specific":[199],"decomposition.":[200]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}