{"id":"https://openalex.org/W4405717848","doi":"https://doi.org/10.1109/tmm.2024.3521744","title":"Alignment-Guided Self-Supervised Learning for Diagram Question Answering","display_name":"Alignment-Guided Self-Supervised Learning for Diagram Question Answering","publication_year":2024,"publication_date":"2024-12-23","ids":{"openalex":"https://openalex.org/W4405717848","doi":"https://doi.org/10.1109/tmm.2024.3521744"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3521744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521744","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5060605201","display_name":"Shaowei Wang","orcid":"https://orcid.org/0000-0002-5536-6515"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaowei Wang","raw_affiliation_strings":["State Key Laboratory of Communication Content Cognition, Xi'an Jiaotong University, Xi'an, China","State Key Laboratory of Communication Content Cognition, and also with the School of Computer Science and Technology, Xi'an Jiaotong University, China"],"raw_orcid":"https://orcid.org/0000-0002-5536-6515","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Communication Content Cognition, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"State Key Laboratory of Communication Content Cognition, and also with the School of Computer Science and Technology, Xi'an Jiaotong University, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384144","display_name":"Lingling Zhang","orcid":"https://orcid.org/0000-0001-8136-8795"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingling Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Xian Jiaotong University, Xi'an, China","School of Computer Science and Technology, Xian Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0001-8136-8795","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xian Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xian Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenjun Wu","orcid":"https://orcid.org/0000-0002-9377-9062"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Wu","raw_affiliation_strings":["Ministry of Education, Key Laboratory of Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, China","Key Laboratory of Intelligent Networks and Network Security (Xi'an Jiaotong University), Ministry of Education, China"],"raw_orcid":"https://orcid.org/0000-0002-9377-9062","affiliations":[{"raw_affiliation_string":"Ministry of Education, Key Laboratory of Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Networks and Network Security (Xi'an Jiaotong University), Ministry of Education, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062913166","display_name":"Tao Qin","orcid":"https://orcid.org/0000-0003-4874-2567"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qin","raw_affiliation_strings":["School of Computer Science and Technology, Xian Jiaotong University, Xi'an, China","School of Computer Science and Technology, Xian Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0003-4874-2567","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xian Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xian Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042400141","display_name":"X. M. Zhang","orcid":"https://orcid.org/0009-0008-7658-0116"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Zhang","raw_affiliation_strings":["Ministry of Education, Key Laboratory of Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, China","Key Laboratory of Intelligent Networks and Network Security (Xi'an Jiaotong University), Ministry of Education, China"],"raw_orcid":"https://orcid.org/0009-0008-7658-0116","affiliations":[{"raw_affiliation_string":"Ministry of Education, Key Laboratory of Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Networks and Network Security (Xi'an Jiaotong University), Ministry of Education, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100361891","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-6004-0675"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["School of Computer Science and Technology, Xian Jiaotong University, Xi'an, China","School of Computer Science and Technology, Xian Jiaotong University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-6004-0675","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xian Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xian Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":0.2301,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66977055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":94},"biblio":{"volume":"27","issue":null,"first_page":"2141","last_page":"2154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.984000027179718,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.984000027179718,"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"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9821000099182129,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.98089998960495,"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/computer-science","display_name":"Computer science","score":0.8203110694885254},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6356117129325867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46665000915527344},{"id":"https://openalex.org/keywords/diagram","display_name":"Diagram","score":0.4105035662651062},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3758825361728668},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37229880690574646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36251819133758545},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12814515829086304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8203110694885254},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6356117129325867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46665000915527344},{"id":"https://openalex.org/C186399060","wikidata":"https://www.wikidata.org/wiki/Q959962","display_name":"Diagram","level":2,"score":0.4105035662651062},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3758825361728668},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37229880690574646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36251819133758545},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12814515829086304}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3521744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521744","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2105825574","https://openalex.org/W2121406004","https://openalex.org/W2158619747","https://openalex.org/W2194775991","https://openalex.org/W2307512708","https://openalex.org/W2321533354","https://openalex.org/W2746097825","https://openalex.org/W2768591600","https://openalex.org/W2883725317","https://openalex.org/W2887967003","https://openalex.org/W2962763265","https://openalex.org/W2962959437","https://openalex.org/W2963037989","https://openalex.org/W2963150162","https://openalex.org/W2963420272","https://openalex.org/W2963717374","https://openalex.org/W2964051877","https://openalex.org/W2966369713","https://openalex.org/W2966683369","https://openalex.org/W3034475678","https://openalex.org/W3034649151","https://openalex.org/W3035449864","https://openalex.org/W3094071022","https://openalex.org/W3106278732","https://openalex.org/W3134816589","https://openalex.org/W3156800342","https://openalex.org/W3168417280","https://openalex.org/W3168963360","https://openalex.org/W3206675006","https://openalex.org/W3206987730","https://openalex.org/W3208028119","https://openalex.org/W3213610319","https://openalex.org/W3215907972","https://openalex.org/W4220983034","https://openalex.org/W4225105060","https://openalex.org/W4282936652","https://openalex.org/W4385245566","https://openalex.org/W4402727764","https://openalex.org/W6631190155","https://openalex.org/W6675774669","https://openalex.org/W6676133286","https://openalex.org/W6752083267","https://openalex.org/W6754048563","https://openalex.org/W6766673545","https://openalex.org/W6779977557","https://openalex.org/W6780226713","https://openalex.org/W6885071273"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359","https://openalex.org/W2115758952"],"abstract_inverted_index":{"Diagram":[0],"question":[1],"answering":[2,8],"(DQA),":[3],"which":[4],"is":[5,40,194],"defined":[6],"as":[7,55,57],"natural":[9],"language":[10],"questions":[11],"according":[12],"to":[13,161,178,197,201],"the":[14,30,45,58,69,81,86,92,104,135,155,159,166,172,180,186,191,195,202,208,232],"visual":[15,49],"diagram":[16,131,160,175,203],"context,":[17],"has":[18,22],"attracted":[19],"attention":[20,117],"and":[21,51,124,163,230,237],"recently":[23],"become":[24],"a":[25],"new":[26],"benchmark":[27],"for":[28,80,98,130],"evaluating":[29],"complex":[31,59],"reasoning":[32,38],"ability":[33],"of":[34,44,47,65,72,147,174,182,188,217],"models.":[35],"However,":[36],"this":[37,89],"task":[39],"extremely":[41],"challenging":[42],"because":[43],"inclusion":[46],"abstract":[48],"objects":[50,157],"specialized":[52],"textual":[53],"terms,":[54],"well":[56],"relationships":[60],"between":[61],"them.":[62],"The":[63,215],"rarity":[64],"data":[66,177,183],"caused":[67],"by":[68],"high":[70],"cost":[71],"annotation":[73],"also":[74,169],"makes":[75],"large-scale":[76],"deep":[77],"models":[78],"invalid":[79],"DQA":[82,99],"task.":[83,205],"To":[84,185],"address":[85,179],"above":[87],"challenges,":[88],"paper":[90],"proposes":[91,115],"cross-modal":[93,127],"alignment-guided":[94],"self-supervised":[95,140,238],"learning":[96,109,141],"model":[97,106,137,193,210,223],"(CAS-DQA).":[100],"Unlike":[101],"previous":[102],"works,":[103],"CAS-DQA":[105,136,192,209],"focuses":[107],"on":[108,121,211,227],"internal":[110,233],"visual-textual":[111,148],"object":[112,122,149,234],"relationships,":[113],"innovatively":[114],"an":[116],"mechanism":[118],"module":[119,236],"based":[120],"alignment,":[123],"effectively":[125,170],"integrates":[126],"knowledge":[128],"units":[129],"understanding.":[132],"In":[133],"addition,":[134],"constructs":[138],"two":[139,152],"(SSL)":[142],"tasks":[143,153,239],"via":[144],"intermediate":[145],"results":[146,216],"alignment.":[150],"These":[151],"exploit":[154],"unnoticed":[156],"inside":[158],"fully":[162],"completely":[164],"understand":[165],"diagram.":[167],"They":[168],"increase":[171],"amount":[173],"question-answering":[176,204],"challenge":[181],"scarcity.":[184],"best":[187],"our":[189,222],"knowledge,":[190],"first":[196],"extend":[198],"SSL":[199],"strategies":[200],"We":[206],"evaluate":[207],"three":[212],"different":[213,228],"datasets.":[214],"extensive":[218],"experiments":[219],"show":[220],"that":[221,231],"significantly":[224],"outperforms":[225],"baselines":[226],"scenarios":[229],"alignment":[235],"produce":[240],"excellent":[241],"results.":[242]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}