{"id":"https://openalex.org/W4406495693","doi":"https://doi.org/10.1109/mmul.2025.3530004","title":"Pro-MA: Progressively Margin-Based Attribution in Pretrained Vision\u2013Language Models","display_name":"Pro-MA: Progressively Margin-Based Attribution in Pretrained Vision\u2013Language Models","publication_year":2025,"publication_date":"2025-01-16","ids":{"openalex":"https://openalex.org/W4406495693","doi":"https://doi.org/10.1109/mmul.2025.3530004"},"language":"en","primary_location":{"id":"doi:10.1109/mmul.2025.3530004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2025.3530004","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 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/A5101970691","display_name":"Sisi You","orcid":"https://orcid.org/0009-0004-2173-1694"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sisi You","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0004-2173-1694","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiachang Li","orcid":"https://orcid.org/0009-0008-7869-5216"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiachang Li","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0008-7869-5216","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007962086","display_name":"Bing\u2010Kun Bao","orcid":"https://orcid.org/0000-0001-5956-831X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5956-831X","affiliations":[{"raw_affiliation_string":"College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00596661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"2","first_page":"53","last_page":"64"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9921000003814697,"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":0.9921000003814697,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9344000220298767,"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/T10028","display_name":"Topic Modeling","score":0.9190000295639038,"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":0.7831101417541504},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.718294620513916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5939110517501831},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45546138286590576},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44814133644104004},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.420772522687912},{"id":"https://openalex.org/keywords/attribution","display_name":"Attribution","score":0.4207509160041809},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3560261130332947},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3033822178840637},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09626561403274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831101417541504},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.718294620513916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5939110517501831},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45546138286590576},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44814133644104004},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.420772522687912},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.4207509160041809},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3560261130332947},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3033822178840637},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09626561403274536},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmul.2025.3530004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2025.3530004","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 MultiMedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1003530150","display_name":null,"funder_award_id":"NY222116","funder_id":"https://openalex.org/F4320323268","funder_display_name":"Nanjing University of Posts and Telecommunications"},{"id":"https://openalex.org/G5851403343","display_name":null,"funder_award_id":"62325206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G899906189","display_name":null,"funder_award_id":"62301276","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation 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/F4320323268","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2963097937","https://openalex.org/W2964159778","https://openalex.org/W2970231061","https://openalex.org/W3090449556","https://openalex.org/W3139831923","https://openalex.org/W3152884768","https://openalex.org/W3172112830","https://openalex.org/W3173787059","https://openalex.org/W4205460703","https://openalex.org/W4367721852","https://openalex.org/W4385572928","https://openalex.org/W4386072014","https://openalex.org/W4386076059","https://openalex.org/W4386076683"],"related_works":["https://openalex.org/W2035546108","https://openalex.org/W2376361520","https://openalex.org/W2133328864","https://openalex.org/W2093949997","https://openalex.org/W2570200690","https://openalex.org/W2389726244","https://openalex.org/W3030478661","https://openalex.org/W2323536476","https://openalex.org/W2104624653","https://openalex.org/W2128730003"],"abstract_inverted_index":{"Knowledge":[0],"attribution":[1,73,83,90,111,145],"focuses":[2],"on":[3,26,118,133],"analyzing":[4],"the":[5,16,72,119,122,127,134],"internal":[6],"knowledge":[7,18,89,101,144],"architecture":[8],"of":[9,121,129],"neural":[10],"networks,":[11],"aiming":[12],"to":[13,45,48,98,113],"accurately":[14],"identify":[15],"factual":[17],"stored":[19],"within":[20],"a":[21],"model.":[22],"Existing":[23],"methods":[24,40],"concentrate":[25],"pretrained":[27,34],"language":[28],"models,":[29],"with":[30],"limited":[31],"exploration":[32],"in":[33,68,91],"vision\u2013language":[35],"models":[36],"(VLMs).":[37],"However,":[38],"these":[39,77],"cannot":[41],"be":[42],"directly":[43],"applied":[44],"VLMs":[46,57],"due":[47],"different":[49],"decision-making":[50],"processes":[51],"and":[52,64,136],"integral":[53],"gradients":[54],"bias.":[55],"Specifically,":[56],"involve":[58],"extra":[59],"knowledge-irrelevant":[60],"steps":[61],"like":[62],"localization":[63],"show":[65],"high":[66],"variance":[67],"gradient":[69],"distributions":[70],"along":[71,126],"paths.":[74],"To":[75],"address":[76],"challenges,":[78],"we":[79,94,108],"propose":[80],"progressive":[81,110],"margin-based":[82],"(Pro-MA)":[84],"for":[85],"more":[86],"accurate":[87],"attribute":[88],"VLMs.":[92],"First,":[93],"employ":[95],"cross-attribute":[96],"comparison":[97],"mitigate":[99],"irrelevant":[100],"by":[102],"constructing":[103],"high-similarity":[104],"negative":[105],"samples.":[106],"Second,":[107],"utilize":[109],"scoring":[112],"quantify":[114],"neuron":[115],"contributions":[116],"based":[117],"margin":[120],"category\u2013value":[123],"loss":[124],"function":[125],"path":[128],"active":[130],"neurons.":[131],"Evaluation":[132],"OVAD":[135],"VAW":[137],"datasets":[138],"shows":[139],"that":[140],"Pro-MA":[141],"outperforms":[142],"state-of-the-art":[143],"methods.":[146]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}