{"id":"https://openalex.org/W7118336737","doi":"https://doi.org/10.3390/mti10010006","title":"HISF: Hierarchical Interactive Semantic Fusion for Multimodal Prompt Learning","display_name":"HISF: Hierarchical Interactive Semantic Fusion for Multimodal Prompt Learning","publication_year":2026,"publication_date":"2026-01-06","ids":{"openalex":"https://openalex.org/W7118336737","doi":"https://doi.org/10.3390/mti10010006"},"language":"en","primary_location":{"id":"doi:10.3390/mti10010006","is_oa":true,"landing_page_url":"https://doi.org/10.3390/mti10010006","pdf_url":"https://www.mdpi.com/2414-4088/10/1/6/pdf?version=1767705880","source":{"id":"https://openalex.org/S4210226272","display_name":"Multimodal Technologies and Interaction","issn_l":"2414-4088","issn":["2414-4088"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimodal Technologies and Interaction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2414-4088/10/1/6/pdf?version=1767705880","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122295222","display_name":"Haohan Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haohan Feng","raw_affiliation_strings":["State Key Laboratory of Media Convergence and Communication, School of Information and Communication Engineering, Communication University of China, Beijing 100024, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, School of Information and Communication Engineering, Communication University of China, Beijing 100024, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100369903","display_name":"Chen Li","orcid":"https://orcid.org/0000-0003-0527-0547"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chen Li","raw_affiliation_strings":["State Key Laboratory of Media Convergence and Communication, School of Information and Communication Engineering, Communication University of China, Beijing 100024, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, School of Information and Communication Engineering, Communication University of China, Beijing 100024, China","institution_ids":["https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100369903","https://openalex.org/A5122295222"],"corresponding_institution_ids":["https://openalex.org/I75689368"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04077901,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"1","first_page":"6","last_page":"6"},"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":0.7516999840736389,"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":0.7516999840736389,"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":0.17470000684261322,"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":0.019500000402331352,"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/robustness","display_name":"Robustness (evolution)","score":0.48579999804496765},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4368000030517578},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4207000136375427},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4154999852180481},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3813000023365021},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.3801000118255615},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.33889999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7789000272750854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6057000160217285},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.48579999804496765},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4154999852180481},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.382099986076355},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3481999933719635},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.26840001344680786},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/mti10010006","is_oa":true,"landing_page_url":"https://doi.org/10.3390/mti10010006","pdf_url":"https://www.mdpi.com/2414-4088/10/1/6/pdf?version=1767705880","source":{"id":"https://openalex.org/S4210226272","display_name":"Multimodal Technologies and Interaction","issn_l":"2414-4088","issn":["2414-4088"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimodal Technologies and Interaction","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:3fa8117734484149a982eca20ee63f1b","is_oa":true,"landing_page_url":"https://doaj.org/article/3fa8117734484149a982eca20ee63f1b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Multimodal Technologies and Interaction, Vol 10, Iss 1, p 6 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/mti10010006","is_oa":true,"landing_page_url":"https://doi.org/10.3390/mti10010006","pdf_url":"https://www.mdpi.com/2414-4088/10/1/6/pdf?version=1767705880","source":{"id":"https://openalex.org/S4210226272","display_name":"Multimodal Technologies and Interaction","issn_l":"2414-4088","issn":["2414-4088"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimodal Technologies and Interaction","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7118336737.pdf","grobid_xml":"https://content.openalex.org/works/W7118336737.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"vision-language":[1,245],"pre-training":[2],"models,":[3],"like":[4],"CLIP,":[5],"have":[6],"been":[7],"shown":[8],"to":[9,156,185,217],"generalize":[10],"well":[11,120],"across":[12,168],"a":[13,27,85,113,116,145,150,227,237],"variety":[14],"of":[15,59,98,112,202],"multitask":[16],"modalities.":[17],"Nonetheless,":[18],"their":[19,75,207],"generalization":[20],"for":[21,48,66,92,231,243],"downstream":[22],"tasks":[23],"is":[24,45,226],"limited.":[25],"As":[26],"lightweight":[28,239],"adaptation":[29],"approach,":[30],"prompt":[31,94,233],"learning":[32,234],"could":[33],"allow":[34],"task":[35],"transfer":[36,194],"by":[37,181],"optimizing":[38],"only":[39],"several":[40],"learnable":[41],"vectors":[42],"and":[43,62,70,105,149,188,206,213,235,240],"thus":[44],"more":[46,238],"flexible":[47],"pre-trained":[49,246],"models.":[50,247],"However,":[51],"current":[52],"methods":[53,187],"mainly":[54],"concentrate":[55],"on":[56],"the":[57,128,133,178,200,223],"design":[58],"unimodal":[60],"prompts":[61],"ignore":[63],"effective":[64],"means":[65],"multimodal":[67,93,232],"semantic":[68,130,162,214],"fusion":[69,131],"label":[71],"alignment,":[72],"which":[73],"limits":[74],"representation":[76],"power.":[77],"To":[78],"tackle":[79],"these":[80],"problems,":[81],"this":[82],"paper":[83],"designs":[84],"Hierarchical":[86],"Interactive":[87],"Semantic":[88,151],"Fusion":[89],"(HISF)":[90],"framework":[91],"learning.":[95],"On":[96],"top":[97],"frozen":[99],"CLIP":[100],"backbones,":[101],"HISF":[102,176,225],"injects":[103],"visual":[104],"textual":[106],"signals":[107],"simultaneously":[108],"in":[109,164,192],"intermediate":[110],"layers":[111],"Transformer":[114],"through":[115],"cross-attention":[117],"mechanism":[118],"as":[119,121],"fitting":[122],"category":[123,158],"embeddings.":[124],"This":[125],"architecture":[126],"realizes":[127],"hierarchical":[129,209,229],"at":[132,140],"modality":[134],"level":[135],"with":[136],"structural":[137],"consistency":[138,159],"kept":[139],"each":[141,203],"layer.":[142],"In":[143,221],"addition,":[144],"Label":[146],"Embedding":[147],"Constraint":[148],"Alignment":[152],"Loss":[153],"are":[154],"proposed":[155,204,224],"promote":[157],"while":[160],"alleviating":[161],"drift":[163],"training.":[165],"Extensive":[166],"experiments":[167],"11":[169],"few-shot":[170],"image":[171],"classification":[172],"benchmarks":[173],"show":[174],"that":[175],"improves":[177],"average":[179],"accuracy":[180],"around":[182],"0.7%":[183],"compared":[184],"state-of-the-art":[186],"has":[189],"remarkable":[190],"robustness":[191],"cross-domain":[193],"tasks.":[195],"Ablation":[196],"studies":[197],"also":[198],"verify":[199],"effectiveness":[201],"part":[205],"combination:":[208],"structure,":[210],"cross-modal":[211],"attention,":[212],"alignment":[215],"collaborate":[216],"enrich":[218],"representational":[219],"capacity.":[220],"conclusion,":[222],"new":[228],"view":[230],"provides":[236],"generalizable":[241],"paradigm":[242],"adapting":[244]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-01-08T00:00:00"}