{"id":"https://openalex.org/W4392904512","doi":"https://doi.org/10.1109/icassp48485.2024.10446504","title":"DAP: Domain-Aware Prompt Learning for Vision-and-Language Navigation","display_name":"DAP: Domain-Aware Prompt Learning for Vision-and-Language Navigation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904512","doi":"https://doi.org/10.1109/icassp48485.2024.10446504"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100418152","display_name":"Ting Liu","orcid":"https://orcid.org/0000-0002-8468-4926"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Liu","raw_affiliation_strings":["National University of Defense Technology,College of Systems Engineering,Changsha,China","College of Systems Engineering, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Systems Engineering,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053458494","display_name":"Yue Hu","orcid":"https://orcid.org/0000-0002-8115-7020"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Hu","raw_affiliation_strings":["National University of Defense Technology,College of Systems Engineering,Changsha,China","College of Systems Engineering, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Systems Engineering,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017356141","display_name":"Wansen Wu","orcid":"https://orcid.org/0000-0002-0467-3830"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wansen Wu","raw_affiliation_strings":["National University of Defense Technology,College of Systems Engineering,Changsha,China","College of Systems Engineering, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Systems Engineering,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047292560","display_name":"You-Kai Wang","orcid":"https://orcid.org/0000-0001-8034-5516"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youkai Wang","raw_affiliation_strings":["National University of Defense Technology,College of Systems Engineering,Changsha,China","College of Systems Engineering, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Systems Engineering,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000248352","display_name":"Kai Xu","orcid":"https://orcid.org/0000-0002-9054-0216"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Xu","raw_affiliation_strings":["National University of Defense Technology,College of Systems Engineering,Changsha,China","College of Systems Engineering, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Systems Engineering,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100610160","display_name":"Quanjun Yin","orcid":"https://orcid.org/0000-0002-1207-8660"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quanjun Yin","raw_affiliation_strings":["National University of Defense Technology,College of Systems Engineering,Changsha,China","College of Systems Engineering, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Systems Engineering,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":2.8637,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9312271,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2615","last_page":"2619"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965000152587891,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9843000173568726,"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":0.8563651442527771},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6583715677261353},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6395201683044434},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6391584277153015},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6038259863853455},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6003494262695312},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5663256049156189},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49552762508392334},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4639577269554138},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44077765941619873},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.41873079538345337},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4172019362449646},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3941173851490021},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37305355072021484},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1747114658355713}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8563651442527771},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6583715677261353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6395201683044434},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6391584277153015},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6038259863853455},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6003494262695312},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5663256049156189},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49552762508392334},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4639577269554138},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44077765941619873},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.41873079538345337},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4172019362449646},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3941173851490021},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37305355072021484},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1747114658355713},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2884565639","https://openalex.org/W2926977875","https://openalex.org/W2964935470","https://openalex.org/W2974759213","https://openalex.org/W2987914945","https://openalex.org/W3034500398","https://openalex.org/W3034578524","https://openalex.org/W3035232877","https://openalex.org/W3091588028","https://openalex.org/W3109097593","https://openalex.org/W3165915253","https://openalex.org/W3172675210","https://openalex.org/W3204250462","https://openalex.org/W3205276578","https://openalex.org/W3206064582","https://openalex.org/W4221167472","https://openalex.org/W4225310486","https://openalex.org/W4292779060","https://openalex.org/W4312238277","https://openalex.org/W4312618696","https://openalex.org/W4383567564","https://openalex.org/W4389217140","https://openalex.org/W4390872682","https://openalex.org/W4392909058","https://openalex.org/W6753516098","https://openalex.org/W6757724268","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6802347785","https://openalex.org/W6858881649"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W3124914020","https://openalex.org/W4390516098","https://openalex.org/W2141033859","https://openalex.org/W2156434174","https://openalex.org/W2071701083","https://openalex.org/W2383687187","https://openalex.org/W2181948922","https://openalex.org/W2081517010","https://openalex.org/W2121496884"],"abstract_inverted_index":{"Following":[0],"language":[1],"instructions":[2],"to":[3,86,161],"navigate":[4],"in":[5,26,76,119,127,144],"unseen":[6],"environments":[7],"is":[8],"a":[9,40,55,81,100,128],"challenging":[10],"task":[11],"for":[12,46,91],"autonomous":[13],"embodied":[14],"agents.":[15],"With":[16],"strong":[17],"representation":[18],"capabilities,":[19],"pretrained":[20,67,129,142],"vision-and-language":[21],"models":[22,68],"are":[23,32],"widely":[24],"used":[25,45],"VLN.":[27],"However,":[28],"most":[29],"of":[30,102,109,123,140,158],"them":[31],"trained":[33],"on":[34,150],"web-crawled":[35],"generalpurpose":[36],"datasets,":[37],"which":[38],"incurs":[39],"considerable":[41],"domain":[42],"gap":[43],"when":[44],"VLN":[47,77],"tasks.":[48],"To":[49],"address":[50],"the":[51,66,107,110,120,124,137,141,156],"problem,":[52],"we":[53,97,114],"propose":[54],"novel":[56],"and":[57,72,153],"model-agnostic":[58],"Domain-Aware":[59],"Prompt":[60],"learning":[61],"(DAP)":[62],"framework.":[63],"For":[64],"equipping":[65],"with":[69,106],"specific":[70],"object-level":[71],"scene-level":[73],"cross-modal":[74],"alignment":[75],"tasks,":[78],"DAP":[79,131,159],"applies":[80],"low-cost":[82],"prompt":[83],"tuning":[84],"paradigm":[85],"learn":[87],"soft":[88,116],"visual":[89,117,125,134,138],"prompts":[90,118],"extracting":[92],"in-domain":[93,103,133],"image":[94],"semantics.":[95],"Specifically,":[96],"first":[98],"generate":[99],"set":[101],"image-text":[104],"pairs":[105],"help":[108],"CLIP":[111],"model.":[112,130],"Then":[113],"introduce":[115],"input":[121],"space":[122],"encoder":[126,139],"injects":[132],"knowledge":[135],"into":[136],"model":[143],"an":[145],"efficient":[146],"way.":[147],"Experimental":[148],"results":[149],"both":[151],"R2R":[152],"REVERIE":[154],"show":[155],"superiority":[157],"compared":[160],"existing":[162],"state-of-the-art":[163],"methods.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}
