{"id":"https://openalex.org/W4415795643","doi":"https://doi.org/10.52202/079017-3530","title":"FlexCap: Describe Anything in Images in Controllable Detail","display_name":"FlexCap: Describe Anything in Images in Controllable Detail","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415795643","doi":"https://doi.org/10.52202/079017-3530"},"language":"en","primary_location":{"id":"doi:10.52202/079017-3530","doi":"https://doi.org/10.52202/079017-3530","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-3530","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.12026","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047363556","display_name":"Debidatta Dwibedi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Debidatta Dwibedi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029884559","display_name":"Vidhi Jain","orcid":"https://orcid.org/0009-0000-7960-8542","observed_orcids":["https://orcid.org/0009-0000-7960-8542"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vidhi Jain","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066924496","display_name":"Jonathan Tompson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan Tompson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057678172","display_name":"Andrew Zisserman","orcid":"https://orcid.org/0000-0002-8945-8573","observed_orcids":["https://orcid.org/0000-0002-8945-8573"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Zisserman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056410851","display_name":"Yusuf Aytar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusuf Aytar","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":0.4344,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73266491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"111172","last_page":"111198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0,"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/vision-language-models","display_name":"vision-language models","score":0.7689999938011169},{"id":"https://openalex.org/keywords/dense-captioning","display_name":"dense captioning","score":0.9079999923706055},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.7730000019073486},{"id":"https://openalex.org/keywords/image-annotation","display_name":"image annotation","score":0.4790000021457672},{"id":"https://openalex.org/keywords/visual-dialogue","display_name":"visual dialogue","score":0.9649999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5609999895095825},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4724000096321106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46779999136924744},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.28600001335144043},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2741999924182892},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.25189998745918274},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2498999983072281},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.24160000681877136},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2337000072002411}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-3530","doi":"https://doi.org/10.52202/079017-3530","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-3530","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2403.12026","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.12026","pdf_url":"https://arxiv.org/pdf/2403.12026","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2403.12026","doi":"https://doi.org/10.48550/arxiv.2403.12026","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.12026","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.12026","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.12026","pdf_url":"https://arxiv.org/pdf/2403.12026","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415795643.pdf","grobid_xml":"https://content.openalex.org/works/W4415795643.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2938704169","https://openalex.org/W2969862959","https://openalex.org/W3193402170","https://openalex.org/W3206072662","https://openalex.org/W3207493267","https://openalex.org/W4292945941","https://openalex.org/W4296406182","https://openalex.org/W4310629611","https://openalex.org/W4323572061","https://openalex.org/W4372273323","https://openalex.org/W4385965217","https://openalex.org/W4387596621","https://openalex.org/W4390873312","https://openalex.org/W7133236164"],"related_works":["https://openalex.org/W7096901211","https://openalex.org/W4414634784","https://openalex.org/W3197904250","https://openalex.org/W7100497905","https://openalex.org/W4394625850","https://openalex.org/W7154461936","https://openalex.org/W2922909102","https://openalex.org/W4396718070","https://openalex.org/W4390873086","https://openalex.org/W7169668147"],"abstract_inverted_index":{"We":[0,57],"introduce":[1],"FlexCap,":[2],"a":[3,90,96],"vision-language":[4],"model":[5,93],"that":[6],"generates":[7],"region-specific":[8],"descriptions":[9,29,49,84],"of":[10,46],"varying":[11,51],"lengths.":[12],"FlexCap":[13],"is":[14],"trained":[15],"to":[16,35,89,94],"produce":[17],"length-conditioned":[18],"captions":[19],"for":[20,115],"input":[21,88],"boxes,":[22],"enabling":[23],"control":[24],"over":[25],"information":[26],"density,":[27],"with":[28,50],"ranging":[30],"from":[31,53],"concise":[32],"object":[33,120],"labels":[34],"detailed":[36],"captions.":[37],"To":[38],"achieve":[39],"this,":[40],"we":[41,79],"create":[42,95],"large-scale":[43],"training":[44],"datasets":[45],"image":[47,118],"region":[48],"lengths":[52],"captioned":[54],"web":[55],"images.":[56],"demonstrate":[58],"FlexCap's":[59,82,113],"effectiveness":[60],"in":[61,69],"several":[62],"applications:":[63],"first,":[64],"it":[65],"achieves":[66],"strong":[67],"performance":[68,105],"dense":[70],"captioning":[71],"tasks":[72,116],"on":[73,106],"the":[74],"Visual":[75],"Genome":[76],"dataset.":[77],"Second,":[78],"show":[80],"how":[81],"localized":[83],"can":[85],"serve":[86],"as":[87],"large":[91],"language":[92],"visual":[97,124],"question":[98],"answering":[99],"(VQA)":[100],"system,":[101],"achieving":[102],"state-of-the-art":[103],"zero-shot":[104],"multiple":[107],"VQA":[108],"benchmarks.":[109],"Our":[110],"experiments":[111],"illustrate":[112],"utility":[114],"including":[117],"labeling,":[119],"attribute":[121],"recognition,":[122],"and":[123],"dialog.":[125],"Project":[126],"webpage:":[127],"https://flex-cap.github.io":[128],".":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-11-03T00:00:00"}