{"id":"https://openalex.org/W4415428941","doi":"https://doi.org/10.3233/faia250850","title":"Multimodal Semantic Decoupled Prompt for Zero-Shot Referring Expression Comprehension","display_name":"Multimodal Semantic Decoupled Prompt for Zero-Shot Referring Expression Comprehension","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428941","doi":"https://doi.org/10.3233/faia250850"},"language":null,"primary_location":{"id":"doi:10.3233/faia250850","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250850","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia250850","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100319905","display_name":"Yuxuan Zhang","orcid":"https://orcid.org/0000-0002-3760-1083"},"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":true,"raw_author_name":"Yuxuan Zhang","raw_affiliation_strings":["Nanjing University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113283190","display_name":"Longfei Huang","orcid":null},"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":"Longfei Huang","raw_affiliation_strings":["Nanjing University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100397623","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5245-3584"},"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":"Yang Yang","raw_affiliation_strings":["Nanjing University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100319905"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50926932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9914000034332275,"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/T10028","display_name":"Topic Modeling","score":0.9914000034332275,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.986299991607666,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9805999994277954,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.630299985408783},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5787000060081482},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5634999871253967},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.483599990606308},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3955000042915344},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.37880000472068787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692999839782715},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.630299985408783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5846999883651733},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5787000060081482},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5634999871253967},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5315999984741211},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.483599990606308},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3955000042915344},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.32899999618530273},{"id":"https://openalex.org/C67277372","wikidata":"https://www.wikidata.org/wiki/Q7449085","display_name":"Semantic role labeling","level":3,"score":0.321399986743927},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia250850","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250850","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia250850","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250850","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"Vision-Language":[1],"Models":[2],"(VLMs)":[3],"have":[4],"demonstrated":[5],"impressive":[6],"zero-shot":[7,30],"performance":[8],"in":[9,26,42],"sample-level":[10],"downstream":[11],"tasks":[12],"(e.g.,":[13],"image":[14,44],"classification),":[15],"driven":[16],"by":[17],"their":[18],"powerful":[19],"generalization":[20],"ability.":[21],"However,":[22],"they":[23],"still":[24],"struggle":[25],"instance-level":[27,75,120],"tasks,":[28],"e.g.,":[29],"Referring":[31],"Expression":[32],"Comprehension":[33],"(REC),":[34],"which":[35],"requires":[36],"precisely":[37],"locating":[38],"the":[39,89,96,100,112,119,131],"target":[40],"instance":[41],"an":[43],"based":[45],"on":[46,126],"a":[47,62,82,107],"provided":[48],"text":[49],"caption.":[50],"To":[51],"address":[52],"this":[53],"issue,":[54],"we":[55,79,105],"propose":[56,81],"Multimodal":[57],"Semantic":[58],"Decoupled":[59],"Prompting":[60],"(MSDP),":[61],"simple":[63],"yet":[64],"effective":[65],"prompt":[66,110],"engineering":[67],"approach":[68,133],"that":[69,116,130],"contains":[70],"both":[71],"textual-":[72],"and":[73],"visual-focused":[74],"understanding":[76,102,114,121],"prompting.":[77],"Specifically,":[78],"first":[80],"novel":[83],"textual":[84,101],"restructure":[85],"strategy":[86],"to":[87],"eliminate":[88],"impact":[90],"of":[91,123],"task-irrelevant":[92],"semantic":[93],"information,":[94],"steering":[95],"model\u2019s":[97],"attention":[98],"at":[99,111,142],"level.":[103],"Meanwhile,":[104],"design":[106],"united":[108],"visual":[109,113],"level":[115],"maximally":[117],"activates":[118],"capabilities":[122],"VLMs.":[124],"Experiments":[125],"several":[127],"benchmarks":[128],"reveal":[129],"proposed":[132],"outperforms":[134],"state-of-the-art":[135],"(SOTA)":[136],"methods.":[137],"The":[138],"code":[139],"is":[140],"available":[141],"repository.":[143]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}