{"id":"https://openalex.org/W4416106014","doi":"https://doi.org/10.1109/iccv51701.2025.00183","title":"Synergistic Prompting for Robust Visual Recognition with Missing Modalities","display_name":"Synergistic Prompting for Robust Visual Recognition with Missing Modalities","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416106014","doi":"https://doi.org/10.1109/iccv51701.2025.00183"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.07802","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100451620","display_name":"Zhihui Zhang","orcid":"https://orcid.org/0000-0002-6081-3236"},"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":"Zhihui Zhang","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109483631","display_name":"Luanyuan Dai","orcid":"https://orcid.org/0009-0006-6235-2580"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luanyuan Dai","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086407377","display_name":"Qika Lin","orcid":"https://orcid.org/0000-0001-5650-0600"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qika Lin","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026338785","display_name":"Yunfeng Diao","orcid":"https://orcid.org/0000-0002-9455-1510"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfeng Diao","raw_affiliation_strings":["Systems Laboratory of Anhui Province, Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Systems Laboratory of Anhui Province, Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018357954","display_name":"Guangyin Jin","orcid":"https://orcid.org/0000-0002-9837-6836"},"institutions":[{"id":"https://openalex.org/I4210138469","display_name":"Innovative Defense Technologies (United States)","ror":"https://ror.org/04y7nvm17","country_code":"US","type":"company","lineage":["https://openalex.org/I4210138469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guangyin Jin","raw_affiliation_strings":["National Innovative Institute of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Innovative Institute of Defense Technology","institution_ids":["https://openalex.org/I4210138469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102776475","display_name":"Yufei Guo","orcid":"https://orcid.org/0000-0002-4920-0965"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yufei Guo","raw_affiliation_strings":["Intelligent Science & Technology Academy of CASIC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Science & Technology Academy of CASIC","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026063666","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0001-8135-8124"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["School of Computer Science, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016760086","display_name":"Xiaoshuai Hao","orcid":"https://orcid.org/0009-0007-4209-6695"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Hao","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31433628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1881","last_page":"1890"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.525600016117096,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.525600016117096,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2460000067949295,"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":0.0478999987244606,"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/modalities","display_name":"Modalities","score":0.7005000114440918},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.699400007724762},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.60589998960495},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5759999752044678},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5101000070571899},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4699999988079071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7638999819755554},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7005000114440918},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.699400007724762},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.60589998960495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5827000141143799},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5759999752044678},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5101000070571899},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4699999988079071},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46639999747276306},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29600000381469727},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2630000114440918},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.25949999690055847}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.07802","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.07802","pdf_url":"https://arxiv.org/pdf/2507.07802","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,"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.2507.07802","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.07802","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.07802","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.07802","pdf_url":"https://arxiv.org/pdf/2507.07802","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,"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":[],"awards":[{"id":"https://openalex.org/G4185968419","display_name":null,"funder_award_id":"62302139","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"multi-modal":[1,16,127],"models":[2],"have":[3],"demonstrated":[4],"remarkable":[5],"performance":[6,35,78,160],"across":[7,144,165],"various":[8],"visual":[9,97,168],"recognition":[10,98,169],"tasks":[11],"by":[12,53],"leveraging":[13],"extensive":[14],"paired":[15],"training":[17],"data.":[18],"However,":[19],"in":[20,187],"real-world":[21],"applications,":[22],"the":[23,61],"presence":[24],"of":[25],"missing":[26,100,175,189],"or":[27],"incomplete":[28],"modality":[29],"inputs":[30],"often":[31],"leads":[32],"to":[33,44,63,65,75,118,141],"significant":[34,159],"degradation.":[36],"Recent":[37],"research":[38],"has":[39],"focused":[40],"on":[41],"prompt-based":[42],"strategies":[43],"tackle":[45],"this":[46],"issue;":[47],"however,":[48],"existing":[49,163],"methods":[50,73],"are":[51,82,153],"hindered":[52],"two":[54,106],"major":[55],"limitations:":[56],"(1)":[57],"static":[58,123,137],"prompts":[59,140],"lack":[60],"flexibility":[62],"adapt":[64],"varying":[66],"missing-data":[67],"conditions,":[68],"and":[69,129,138,177,181,195],"(2)":[70],"basic":[71],"prompt-tuning":[72],"struggle":[74],"ensure":[76],"reliable":[77],"when":[79,150],"critical":[80],"modalities":[81,152],"missing.To":[83],"address":[84],"these":[85],"challenges,":[86],"we":[87],"propose":[88],"a":[89,110,131],"novel":[90],"Synergistic":[91,132],"Prompting":[92,133],"(SyP)":[93],"framework":[94],"for":[95,125],"robust":[96,147],"with":[99],"modalities.":[101],"The":[102,155],"proposed":[103,156],"SyP":[104,157],"introduces":[105],"key":[107,151],"innovations:":[108],"(I)":[109],"Dynamic":[111],"Adapter,":[112],"which":[113,135],"computes":[114],"adaptive":[115],"scaling":[116],"factors":[117],"dynamically":[119],"generate":[120],"prompts,":[121],"replacing":[122],"parameters":[124],"flexible":[126],"adaptation,":[128],"(II)":[130],"Strategy,":[134],"combines":[136],"dynamic":[139],"balance":[142],"information":[143],"modalities,":[145,190],"ensuring":[146],"reasoning":[148],"even":[149],"missing.":[154],"achieves":[158],"improvements":[161],"over":[162],"approaches":[164],"three":[166],"widely-used":[167],"datasets,":[170],"demonstrating":[171],"robustness":[172],"under":[173],"diverse":[174],"rates":[176],"conditions.":[178],"Extensive":[179],"experiments":[180],"ablation":[182],"studies":[183],"validate":[184],"its":[185,192],"effectiveness":[186],"handling":[188],"highlighting":[191],"superior":[193],"adaptability":[194],"reliability.":[196]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}