{"id":"https://openalex.org/W4391306752","doi":"https://doi.org/10.1109/vcip59821.2023.10402690","title":"Noise-Augmented Missing Modality Aware Prompt Based Learning for Robust Visual Recognition","display_name":"Noise-Augmented Missing Modality Aware Prompt Based Learning for Robust Visual Recognition","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4391306752","doi":"https://doi.org/10.1109/vcip59821.2023.10402690"},"language":"en","primary_location":{"id":"doi:10.1109/vcip59821.2023.10402690","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vcip59821.2023.10402690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Visual Communications and Image Processing (VCIP)","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/A5063980282","display_name":"Yooseung Wang","orcid":"https://orcid.org/0000-0002-2341-0251"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yooseung Wang","raw_affiliation_strings":["KAIST,School of Electrical Engineering,Daejeon,Republic of Korea","School of Electrical Engineering, KAIST, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084565386","display_name":"Jaehyuk Jang","orcid":"https://orcid.org/0000-0002-7133-9592"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehyuk Jang","raw_affiliation_strings":["KAIST,School of Electrical Engineering,Daejeon,Republic of Korea","School of Electrical Engineering, KAIST, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069759184","display_name":"Changick Kim","orcid":"https://orcid.org/0000-0001-9323-8488"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Changick Kim","raw_affiliation_strings":["KAIST,School of Electrical Engineering,Daejeon,Republic of Korea","School of Electrical Engineering, KAIST, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,School of Electrical Engineering,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063980282"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28458012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9370999932289124,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9370999932289124,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.9300000071525574,"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/computer-science","display_name":"Computer science","score":0.7437697052955627},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7421650290489197},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5947243571281433},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5384320020675659},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4990873336791992},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41721513867378235},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3747475743293762},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.18824133276939392}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7437697052955627},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7421650290489197},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5947243571281433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5384320020675659},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4990873336791992},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41721513867378235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3747475743293762},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.18824133276939392}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip59821.2023.10402690","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vcip59821.2023.10402690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2277195237","https://openalex.org/W2962931510","https://openalex.org/W2990138404","https://openalex.org/W4225922988","https://openalex.org/W4285241172","https://openalex.org/W4297841641","https://openalex.org/W4312651322","https://openalex.org/W4313164293","https://openalex.org/W4386057714","https://openalex.org/W4386071700","https://openalex.org/W4386075949","https://openalex.org/W6733328719","https://openalex.org/W6776929863","https://openalex.org/W6778883912","https://openalex.org/W6789753369","https://openalex.org/W6798805250","https://openalex.org/W6810168380","https://openalex.org/W6811187361"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W3144423903","https://openalex.org/W2377397762","https://openalex.org/W2361654993","https://openalex.org/W2392886218"],"abstract_inverted_index":{"Multimodal":[0],"learning":[1,97],"is":[2],"essential":[3],"for":[4],"understanding":[5],"interactions":[6],"between":[7],"different":[8,115],"input":[9],"domains.":[10],"However,":[11],"dealing":[12],"with":[13,44,71],"various":[14,99],"modalities":[15],"often":[16],"leads":[17],"to":[18],"a":[19,33,64],"high":[20],"number":[21],"of":[22,108],"network":[23,52],"parameters":[24,46],"and":[25,53],"extended":[26],"training":[27],"time.":[28],"To":[29],"tackle":[30],"these":[31],"challenges,":[32],"recent":[34],"approach":[35,70],"called":[36],"\"missing":[37],"modality":[38,56,67,89,95,111],"aware":[39,57,68,90,112],"prompting\"":[40],"enhances":[41],"model":[42],"robustness":[43],"minimal":[45],"by":[47,80],"freezing":[48],"the":[49,72,77,106],"transformer-based":[50],"backbone":[51],"introducing":[54],"missing":[55,66,88,94,110],"prompts.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"propose":[63],"robust":[65,87,109],"prompting":[69],"same":[73],"parameter":[74],"numbers":[75],"as":[76],"naive":[78],"prompts":[79,91,113],"adding":[81],"noise.":[82],"Our":[83],"experiments":[84],"demonstrate":[85],"that":[86],"outperform":[92],"state-of-the-art":[93],"prompt-based":[96],"in":[98],"scenarios.":[100],"Additionally,":[101],"our":[102],"ablation":[103],"study":[104],"verifies":[105],"effectiveness":[107],"across":[114],"signal-to-noise":[116],"ratios.":[117]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}