{"id":"https://openalex.org/W7104375431","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1376","title":"Masked Diffusion Captioning for Visual Feature Learning","display_name":"Masked Diffusion Captioning for Visual Feature Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7104375431","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1376"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1376","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1376","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1376.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1376.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chao Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zihao Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihao Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Andrew Owens","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Owens","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":0.51238556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25247","last_page":"25263"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8285999894142151,"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":0.8285999894142151,"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":0.08799999952316284,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.014399999752640724,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6456999778747559},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6215000152587891},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3587999939918518},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.34929999709129333},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.32820001244544983},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.2971999943256378}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6456999778747559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.638700008392334},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6215000152587891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6164000034332275},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4456999897956848},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28139999508857727},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2612999975681305},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1376","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1376","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1376.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1376","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1376","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1376.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":[{"score":0.4686459004878998,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7104375431.pdf","grobid_xml":"https://content.openalex.org/works/W7104375431.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"learn":[1],"visual":[2,41,53,68,103],"features":[3,42,54,104],"by":[4,110],"captioning":[5,20],"images":[6],"with":[7,107],"an":[8],"image-conditioned":[9],"masked":[10,18,30],"diffusion":[11,19],"language":[12],"model,":[13],"a":[14,32,37,92],"formulation":[15],"we":[16],"call":[17],"(MDC).During":[21],"training,":[22,50],"text":[23],"tokens":[24],"in":[25,71,80],"each":[26,77],"image-caption":[27],"pair":[28],"are":[29,105],"at":[31],"randomly":[33],"chosen":[34],"ratio,":[35],"and":[36,97,112],"decoder":[38],"conditioned":[39],"on":[40,76],"is":[43],"trained":[44],"to":[45,58],"reconstruct":[46],"the":[47,51,64,67,81,84,101],"original":[48],"text.After":[49],"learned":[52,102],"can":[55],"be":[56],"applied":[57],"downstream":[59],"vision":[60],"tasks.Unlike":[61],"autoregressive":[62,111],"captioning,":[63],"strength":[65],"of":[66,94],"learning":[69],"signal":[70],"MDC":[72],"does":[73],"not":[74],"depend":[75],"token's":[78],"position":[79],"sequence,":[82],"reducing":[83],"need":[85],"for":[86],"auxiliary":[87],"objectives.Linear":[88],"probing":[89],"experiments":[90],"across":[91],"variety":[93],"academic-scale":[95],"models":[96],"datasets":[98],"show":[99],"that":[100],"competitive":[106],"those":[108],"produced":[109],"contrastive":[113],"approaches.":[114]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}