{"id":"https://openalex.org/W4412403842","doi":"https://doi.org/10.1109/tcsvt.2025.3588769","title":"Generative Augmentation Hashing for Few-Shot Cross-Modal Retrieval","display_name":"Generative Augmentation Hashing for Few-Shot Cross-Modal Retrieval","publication_year":2025,"publication_date":"2025-07-14","ids":{"openalex":"https://openalex.org/W4412403842","doi":"https://doi.org/10.1109/tcsvt.2025.3588769"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3588769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3588769","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Transactions on Circuits and Systems for Video Technology","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/A5101901063","display_name":"Fengling Li","orcid":"https://orcid.org/0000-0002-3432-6215"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Fengling Li","raw_affiliation_strings":["Australian Artificial Intelligence Institute, Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, Australia","Faculty of Engineering and Information Technology, Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3432-6215","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"Faculty of Engineering and Information Technology, Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zequn Wang","orcid":"https://orcid.org/0009-0005-0037-3098"},"institutions":[{"id":"https://openalex.org/I28006308","display_name":"Shandong Normal University","ror":"https://ror.org/01wy3h363","country_code":"CN","type":"education","lineage":["https://openalex.org/I28006308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zequn Wang","raw_affiliation_strings":["School of Information Science and Engineering, Shandong Normal University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0005-0037-3098","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shandong Normal University, Jinan, China","institution_ids":["https://openalex.org/I28006308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014809128","display_name":"Tianshi Wang","orcid":"https://orcid.org/0000-0002-8013-5188"},"institutions":[{"id":"https://openalex.org/I28006308","display_name":"Shandong Normal University","ror":"https://ror.org/01wy3h363","country_code":"CN","type":"education","lineage":["https://openalex.org/I28006308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianshi Wang","raw_affiliation_strings":["School of Information Science and Engineering, Shandong Normal University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-8013-5188","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shandong Normal University, Jinan, China","institution_ids":["https://openalex.org/I28006308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108048954","display_name":"Lei Zhu","orcid":"https://orcid.org/0000-0002-2993-7142"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhu","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2993-7142","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034967388","display_name":"Xiaojun Chang","orcid":"https://orcid.org/0000-0002-7778-8807"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaojun Chang","raw_affiliation_strings":["Australian Artificial Intelligence Institute, Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, Australia","Faculty of Engineering and Information Technology, Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7778-8807","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"Faculty of Engineering and Information Technology, Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101901063"],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":1.1332,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79877623,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"35","issue":"12","first_page":"12861","last_page":"12873"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9793999791145325,"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/hash-function","display_name":"Hash function","score":0.6941605806350708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6878923177719116},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5653193593025208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5356466770172119},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.428875207901001},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3491503596305847}],"concepts":[{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6941605806350708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6878923177719116},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5653193593025208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5356466770172119},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.428875207901001},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3491503596305847},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3588769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3588769","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2462498745","display_name":null,"funder_award_id":"62172263","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2007972815","https://openalex.org/W2155803963","https://openalex.org/W2266728343","https://openalex.org/W2733636222","https://openalex.org/W2773502880","https://openalex.org/W2953037339","https://openalex.org/W2963187862","https://openalex.org/W2963350370","https://openalex.org/W2982905682","https://openalex.org/W2998508940","https://openalex.org/W2999606372","https://openalex.org/W3033799362","https://openalex.org/W3072820880","https://openalex.org/W3193135654","https://openalex.org/W3195103026","https://openalex.org/W3197132226","https://openalex.org/W4285242239","https://openalex.org/W4285288078","https://openalex.org/W4312477797","https://openalex.org/W4312938578","https://openalex.org/W4323022360","https://openalex.org/W4380303571","https://openalex.org/W4382240042","https://openalex.org/W4383503840","https://openalex.org/W4385819665","https://openalex.org/W4386065510","https://openalex.org/W4390659080","https://openalex.org/W4393160343","https://openalex.org/W4393160488","https://openalex.org/W4399377345","https://openalex.org/W4402263774","https://openalex.org/W4402704596","https://openalex.org/W4406387563","https://openalex.org/W4406728241","https://openalex.org/W4406857563"],"related_works":["https://openalex.org/W2380075625","https://openalex.org/W4390718435","https://openalex.org/W4390549206","https://openalex.org/W3137171911","https://openalex.org/W4379540039","https://openalex.org/W4237784285","https://openalex.org/W2374712251","https://openalex.org/W2159024673","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Deep":[0],"cross-modal":[1,22,92,103,138,162],"hashing":[2,40],"has":[3],"demonstrated":[4],"strong":[5],"performance":[6],"in":[7,13,99,160,167],"large-scale":[8],"retrieval":[9,168],"but":[10],"remains":[11],"challenging":[12],"few-shot":[14,161],"scenarios":[15],"due":[16],"to":[17,41,68,112],"limited":[18],"data":[19],"and":[20,38,132,140,173],"weak":[21],"alignment.":[23],"We":[24],"propose":[25],"Generative":[26],"Augmentation":[27],"Hashing":[28],"(GAH),":[29],"a":[30,48,86],"new":[31],"framework":[32],"that":[33,89,155],"synergizes":[34],"Visual-Language":[35],"Models":[36],"(VLMs)":[37],"generation-driven":[39],"address":[42],"these":[43],"limitations.":[44],"GAH":[45,121,156],"first":[46],"introduces":[47],"cycle":[49,88],"generative":[50],"augmentation":[51],"mechanism:":[52],"VLMs":[53],"generate":[54],"descriptive":[55],"textual":[56,81],"captions":[57],"for":[58],"images,":[59],"which,":[60],"combined":[61],"with":[62,109],"label":[63],"semantics,":[64],"guide":[65],"diffusion":[66],"models":[67],"synthesize":[69],"semantically":[70],"aligned":[71],"images":[72,77],"via":[73],"inconsistency":[74],"filtering.":[75],"These":[76],"then":[78],"regenerate":[79],"coherent":[80],"descriptions":[82],"through":[83],"VLMs,":[84],"forming":[85],"self-reinforcing":[87],"iteratively":[90],"expands":[91],"data.":[93],"To":[94],"resolve":[95],"the":[96],"diversity-alignment":[97],"trade-off":[98],"augmentation,":[100],"we":[101],"design":[102],"perturbation":[104],"enhancement,":[105],"injecting":[106],"synchronized":[107],"perturbations":[108],"controlled":[110],"noise":[111],"preserve":[113],"inter-modal":[114],"semantic":[115],"relationships":[116],"while":[117],"enhancing":[118],"robustness.":[119],"Finally,":[120],"employs":[122],"dual-level":[123],"adversarial":[124,128],"hash":[125,142],"learning,":[126],"where":[127],"alignment":[129],"of":[130],"modality-specific":[131],"shared":[133],"latent":[134],"spaces":[135],"optimizes":[136],"both":[137],"consistency":[139],"discriminative":[141],"code":[143],"generation,":[144],"effectively":[145],"bridging":[146],"heterogeneous":[147],"gaps.":[148],"Extensive":[149],"experiments":[150],"on":[151],"benchmark":[152],"datasets":[153,174],"show":[154],"outperforms":[157],"state-of-the-art":[158],"methods":[159],"retrieval,":[163],"achieving":[164],"significant":[165],"improvements":[166],"accuracy.":[169],"Our":[170],"source":[171],"codes":[172],"are":[175],"available":[176],"at":[177],"https://github.com/xiaolaohuuu/GAH.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-10T02:45:41.426853","created_date":"2025-10-10T00:00:00"}