{"id":"https://openalex.org/W4413146357","doi":"https://doi.org/10.1109/cvpr52734.2025.01348","title":"Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding","display_name":"Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413146357","doi":"https://doi.org/10.1109/cvpr52734.2025.01348"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-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/A5100696155","display_name":"Zining Wang","orcid":"https://orcid.org/0009-0007-3818-1037"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zining Wang","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059748327","display_name":"Tongkun Guan","orcid":"https://orcid.org/0000-0003-3346-8315"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongkun Guan","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108580404","display_name":"Pei Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei Fu","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102949976","display_name":"Chen Duan","orcid":"https://orcid.org/0000-0001-7380-6185"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Duan","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073437730","display_name":"Qianyi Jiang","orcid":"https://orcid.org/0000-0002-6006-9929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qianyi Jiang","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102907192","display_name":"Zhentao Guo","orcid":"https://orcid.org/0009-0000-0242-4059"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhentao Guo","raw_affiliation_strings":["Beijing Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110367133","display_name":"Shan Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shan Guo","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100569639","display_name":"Junfeng Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junfeng Luo","raw_affiliation_strings":["Meituan"],"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048353325","display_name":"Wei Shen","orcid":"https://orcid.org/0000-0002-1235-598X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Shen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019708391","display_name":"Xiaokang Yang","orcid":"https://orcid.org/0000-0003-4029-3322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Yang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5100696155"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3104,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84031589,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"14460","last_page":"14471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9868000149726868,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9725000262260437,"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/question-answering","display_name":"Question answering","score":0.8198167085647583},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6623977422714233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6257349848747253},{"id":"https://openalex.org/keywords/marten","display_name":"Marten","score":0.5114914178848267},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4720120131969452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40008631348609924},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3623403310775757},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3397566080093384},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.06390395760536194}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8198167085647583},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6623977422714233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6257349848747253},{"id":"https://openalex.org/C2778793789","wikidata":"https://www.wikidata.org/wiki/Q26533","display_name":"Marten","level":3,"score":0.5114914178848267},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4720120131969452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40008631348609924},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3623403310775757},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3397566080093384},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.06390395760536194},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C185933670","wikidata":"https://www.wikidata.org/wiki/Q52105","display_name":"Habitat","level":2,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2808255248","https://openalex.org/W2808660756","https://openalex.org/W2808756774","https://openalex.org/W2808279462","https://openalex.org/W2588098395","https://openalex.org/W4255292325","https://openalex.org/W2096047831","https://openalex.org/W3118422165","https://openalex.org/W2055880291","https://openalex.org/W2029762142"],"abstract_inverted_index":{"Multi-modal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"have":[5],"introduced":[6],"a":[7,27,49,60,119,147,154,183],"novel":[8,50],"dimension":[9],"to":[10,25,84,104],"document":[11],"understanding,":[12],"i.e.,":[13],"they":[14,123],"endow":[15],"large":[16],"language":[17,37],"models":[18],"with":[19,64,157],"visual":[20,35,109,130],"comprehension":[21],"capabilities;":[22],"however,":[23],"how":[24],"design":[26],"suitable":[28],"image-text":[29],"pre-training":[30],"task":[31,170],"for":[32,187],"bridging":[33],"the":[34,56,82,91,141,166,177],"and":[36,76,88,113,132,152,206],"modality":[38],"in":[39,202],"document-level":[40,173,188],"MLLMs":[41],"remains":[42],"underexplored.":[43],"In":[44],"this":[45],"study,":[46],"we":[47,145,162,180],"introduce":[48,181],"visuallanguage":[51],"alignment":[52,107],"method":[53],"that":[54,164,193],"casts":[55],"key":[57],"issue":[58],"as":[59],"Visual":[61],"Question":[62],"Answering":[63],"Mask":[65],"generation":[66,150,169],"(VQA-Mask)":[67],"task,":[68,144],"optimizing":[69],"two":[70],"tasks":[71],"simultaneously:":[72],"VQA-based":[73],"text":[74,89,131],"parsing":[75,129],"mask":[77,99,168],"generation.":[78],"The":[79,94],"former":[80],"allows":[81],"model":[83,126],"implicitly":[85],"align":[86],"images":[87,112],"at":[90,118,210],"semantic":[92],"level.":[93,121],"latter":[95],"introduces":[96],"an":[97],"additional":[98],"generator":[100],"(discarded":[101],"during":[102],"inference)":[103],"explicitly":[105],"ensure":[106],"between":[108],"texts":[110],"within":[111],"their":[114],"corresponding":[115],"image":[116],"regions":[117],"spatially-aware":[120,135],"Together,":[122],"can":[124],"prevent":[125],"hallucinations":[127],"when":[128],"effectively":[133],"promote":[134],"feature":[136],"representation":[137],"learning.":[138],"To":[139],"support":[140],"proposed":[142,167,178],"VQAMask":[143],"construct":[146],"comprehensive":[148],"image-mask":[149],"pipeline":[151],"provide":[153],"large-scale":[155],"dataset":[156],"6M":[158],"data":[159],"(MTMask6M).":[160],"Subsequently,":[161],"demonstrate":[163],"introducing":[165],"yields":[171],"competitive":[172],"understanding":[174],"performance.":[175],"Leveraging":[176],"VQAMask,":[179],"Marten,":[182],"trainingefficient":[184],"MLLM":[185],"tailored":[186],"understanding.":[189],"Extensive":[190],"experiments":[191],"show":[192],"our":[194],"Marten":[195],"consistently":[196],"achieves":[197],"significant":[198],"improvements":[199],"among":[200],"8B-MLLMs":[201],"document-centric":[203],"tasks.":[204],"Code":[205],"datasets":[207],"are":[208],"available":[209],"https://github.com/PriNing/Marten.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}