{"id":"https://openalex.org/W4416034743","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.573","title":"On the Perception Bottleneck of VLMs for Chart Understanding","display_name":"On the Perception Bottleneck of VLMs for Chart Understanding","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034743","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.573"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.573","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.573","pdf_url":"https://aclanthology.org/2025.findings-emnlp.573.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.573.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087431853","display_name":"Junteng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junteng Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010414688","display_name":"Weihao Zeng","orcid":"https://orcid.org/0009-0004-8226-6036"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weihao Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103264194","display_name":"Xiwen Zhang","orcid":"https://orcid.org/0000-0002-9894-9358"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiwen Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100713695","display_name":"Yijun Wang","orcid":"https://orcid.org/0000-0002-8161-2150"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yijun Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074064317","display_name":"Zifei Shan","orcid":"https://orcid.org/0000-0002-8283-6498"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zifei Shan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100740106","display_name":"Junxian He","orcid":"https://orcid.org/0000-0001-7951-9697"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junxian He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30376766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10829","last_page":"10841"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.367000013589859,"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":0.367000013589859,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.3343000113964081,"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/T10028","display_name":"Topic Modeling","score":0.0406000018119812,"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/bottleneck","display_name":"Bottleneck","score":0.923799991607666},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.7218999862670898},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7031999826431274},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.586899995803833},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5579000115394592},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46209999918937683},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.3944000005722046},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.32179999351501465}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.923799991607666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7497000098228455},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.7218999862670898},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7031999826431274},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.586899995803833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5709999799728394},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5579000115394592},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46209999918937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4334999918937683},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3944000005722046},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3465000092983246},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31290000677108765},{"id":"https://openalex.org/C190812933","wikidata":"https://www.wikidata.org/wiki/Q28923","display_name":"Chart","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.573","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.573","pdf_url":"https://aclanthology.org/2025.findings-emnlp.573.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-168944","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-168944","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.573","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.573","pdf_url":"https://aclanthology.org/2025.findings-emnlp.573.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034743.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Chart":[0],"understanding":[1],"requires":[2],"models":[3,29],"to":[4,63,77,149,177],"effectively":[5,123],"analyze":[6],"and":[7,14,68,140,171],"reason":[8],"about":[9],"numerical":[10],"data,":[11],"textual":[12],"elements,":[13],"complex":[15],"visual":[16,59,85,98,147],"components.":[17],"Our":[18],"observations":[19],"reveal":[20],"that":[21,92,163],"the":[22,53,58,65,69,73,79,83,94,113,125,130,146,151,168,173],"perception":[23,45,169],"capabilities":[24],"of":[25,128,175],"existing":[26],"large":[27],"vision-language":[28],"(LVLMs)":[30],"constitute":[31],"a":[32,134,156],"critical":[33,135],"bottleneck":[34,46,154,170],"in":[35],"this":[36,39,44],"process.":[37],"In":[38],"study,":[40],"we":[41,90,143],"delve":[42],"into":[43,50],"by":[47,108],"decomposing":[48],"it":[49],"two":[51],"components:":[52],"vision":[54,131,152],"encoder":[55,132,148,153],"bottleneck,":[56,71,136],"where":[57,72],"representation":[60],"may":[61],"fail":[62],"encapsulate":[64],"correct":[66],"information,":[67],"extraction":[70,126],"language":[74],"model":[75],"struggles":[76],"extract":[78],"necessary":[80],"information":[81,95],"from":[82],"provided":[84],"representations.":[86],"Through":[87],"comprehensive":[88],"experiments,":[89],"find":[91],"(1)":[93],"embedded":[96],"within":[97],"representations":[99],"is":[100,105,181],"substantially":[101],"richer":[102],"than":[103],"what":[104],"typically":[106],"captured":[107],"linear":[109],"extractors,":[110],"such":[111],"as":[112],"widely":[114],"used":[115],"retrieval":[116],"accuracy":[117],"metric;":[118],"(2)":[119],"While":[120],"instruction":[121],"tuning":[122],"enhances":[124],"capability":[127],"LVLMs,":[129],"remains":[133],"demanding":[137],"focused":[138],"attention":[139],"improvement.":[141],"Therefore,":[142],"further":[144],"enhance":[145],"mitigate":[150],"under":[155],"contrastive":[157],"learning":[158],"framework.":[159],"Empirical":[160],"results":[161],"demonstrate":[162],"our":[164],"approach":[165],"significantly":[166],"mitigates":[167],"improves":[172],"ability":[174],"LVLMs":[176],"comprehend":[178],"charts.":[179],"Code":[180],"publicly":[182],"available":[183],"at":[184],"https://github.com/hkust-nlp/Vision4Chart.":[185]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-11-08T00:00:00"}