{"id":"https://openalex.org/W4402678995","doi":"https://doi.org/10.1145/3688801","title":"CrossFormer: Cross-Modal Representation Learning via Heterogeneous Graph Transformer","display_name":"CrossFormer: Cross-Modal Representation Learning via Heterogeneous Graph Transformer","publication_year":2024,"publication_date":"2024-09-20","ids":{"openalex":"https://openalex.org/W4402678995","doi":"https://doi.org/10.1145/3688801"},"language":"en","primary_location":{"id":"doi:10.1145/3688801","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3688801","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5007130603","display_name":"Xiao Liang","orcid":"https://orcid.org/0009-0006-0504-4506"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Liang","raw_affiliation_strings":["School of Electronic Engineering, Xidian University, Xi\u2019an, China","School of Electronic Engineering, Xidian University, China"],"raw_orcid":"https://orcid.org/0009-0006-0504-4506","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi\u2019an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057526429","display_name":"Erkun Yang","orcid":"https://orcid.org/0000-0002-0855-1646"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Erkun Yang","raw_affiliation_strings":["School of Electronic Engineering, Xidian University, Xi\u2019an, China","School of Electronic Engineering, Xidian University, China"],"raw_orcid":"https://orcid.org/0000-0002-0855-1646","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi\u2019an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015874725","display_name":"Cheng Deng","orcid":"https://orcid.org/0000-0003-2620-3247"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Deng","raw_affiliation_strings":["School of Electronic Engineering, Xidian University, Xi\u2019an, China","School of Electronic Engineering, Xidian University, China"],"raw_orcid":"https://orcid.org/0000-0003-2620-3247","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi\u2019an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035747364","display_name":"Yanhua Yang","orcid":"https://orcid.org/0000-0002-7916-3683"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhua Yang","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, Xi\u2019an, China","School of Computer Science and Technology, Xidian University, China"],"raw_orcid":"https://orcid.org/0000-0002-7916-3683","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi\u2019an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":3.1617,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.93377128,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"20","issue":"12","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9991000294685364,"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":0.9976000189781189,"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":0.8595951795578003},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6094090938568115},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5191113948822021},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47986048460006714},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4159906208515167},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37516283988952637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3743847608566284},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07754731178283691}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8595951795578003},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6094090938568115},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5191113948822021},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47986048460006714},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4159906208515167},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37516283988952637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3743847608566284},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07754731178283691},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3688801","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3688801","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2168253669","display_name":null,"funder_award_id":"62132016, 62171343, and 62071361","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3509175749","display_name":null,"funder_award_id":"ZDRC2102","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4095989662","display_name":null,"funder_award_id":"8091B022149, 8091B02072404","funder_id":"https://openalex.org/F4320321106","funder_display_name":"Ministry of Education of the People's Republic of China"},{"id":"https://openalex.org/G5540677682","display_name":null,"funder_award_id":"2023YFC3305600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321106","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1930223417","https://openalex.org/W1949478088","https://openalex.org/W2049137142","https://openalex.org/W2155803963","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2266728343","https://openalex.org/W2463955103","https://openalex.org/W2525778437","https://openalex.org/W2560730294","https://openalex.org/W2737892366","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2890531016","https://openalex.org/W2963101956","https://openalex.org/W2963389687","https://openalex.org/W2964121744","https://openalex.org/W2964158883","https://openalex.org/W2968124245","https://openalex.org/W2970231061","https://openalex.org/W2982065678","https://openalex.org/W2998166190","https://openalex.org/W2998356391","https://openalex.org/W3006683596","https://openalex.org/W3014611590","https://openalex.org/W3037516378","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3094502228","https://openalex.org/W3113055207","https://openalex.org/W3133825286","https://openalex.org/W3173220247","https://openalex.org/W3173909648","https://openalex.org/W3174626361","https://openalex.org/W3198494235","https://openalex.org/W3201519611","https://openalex.org/W3209760397","https://openalex.org/W3211394146","https://openalex.org/W4206314411","https://openalex.org/W4220923545","https://openalex.org/W4225432580","https://openalex.org/W4225650823","https://openalex.org/W4287324206","https://openalex.org/W4297631514","https://openalex.org/W4321786075","https://openalex.org/W4379382581","https://openalex.org/W4385583963"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2795079307","https://openalex.org/W2714992399","https://openalex.org/W2793058541"],"abstract_inverted_index":{"Transformers":[0],"have":[1],"been":[2],"recognized":[3],"as":[4,65,138],"powerful":[5],"tools":[6],"for":[7,126],"various":[8,206],"cross-modal":[9,24,42,91,128,207],"tasks":[10,208],"due":[11],"to":[12,16,76,102,141,173],"their":[13],"superior":[14],"ability":[15],"perform":[17,90],"representation":[18,129],"learning":[19],"through":[20],"self-attention.":[21],"Existing":[22],"transformer-based":[23],"models":[25],"can":[26,47],"be":[27],"categorized":[28],"into":[29],"single-stream":[30],"and":[31,51,110,145,194,199],"dual-stream":[32,127,150,181],"ones.":[33],"By":[34],"performing":[35],"fine-grained":[36,105,143,197],"interaction":[37,92,147],"with":[38,158],"self-attention":[39,182],"on":[40,93,148,185,205],"the":[41,45,59,68,83,94,104,170,175,186,190,210],"concatenated":[43],"features,":[44],"former":[46],"simultaneously":[48],"learn":[49],"intra-":[50,109,144,198],"inter-modal":[52,146,200],"correlations.":[53],"However,":[54],"this":[55,117],"simple":[56],"concatenation":[57],"treats":[58],"inputs":[60,84],"of":[61,85,107,212],"different":[62,86],"modalities":[63,72,87,193],"equally;":[64],"a":[66,77,100,113,135,139,149,159,164,180],"result,":[67],"heterogeneous":[69,123,136,160,171,187],"differences":[70],"between":[71,192],"are":[73],"ignored,":[74],"leading":[75],"modality":[78],"gap.":[79],"The":[80],"latter":[81],"process":[82],"separately,":[88],"then":[89,162],"subsequently":[95],"fused":[96],"networks,":[97],"resulting":[98],"in":[99,112],"failure":[101],"integrate":[103],"correlations":[106],"both":[108],"inter-modality":[111],"uniform":[114],"module.":[115],"To":[116],"end,":[118],"we":[119,153],"propose":[120],"an":[121],"effective":[122],"graph":[124,137,172],"transformer":[125],"learning,":[130],"named":[131],"CrossFormer,":[132],"which":[133],"constructs":[134],"bridge":[140],"achieve":[142],"network.":[151],"Specifically,":[152],"first":[154],"represent":[155],"multi-modal":[156],"data":[157],"graph,":[161,188],"develop":[163],"dual-positional":[165],"encoding":[166],"strategy":[167],"that":[168],"enables":[169],"obtain":[174],"relative":[176],"positional":[177],"information.":[178],"Finally,":[179],"is":[183],"performed":[184],"bridging":[189],"gap":[191],"effectively":[195],"capturing":[196],"interactions":[201],"simultaneously.":[202],"Extensive":[203],"experiments":[204],"demonstrate":[209],"superiority":[211],"our":[213],"method.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}