{"id":"https://openalex.org/W4403582532","doi":"https://doi.org/10.1145/3627673.3679740","title":"Learning Cross-modal Knowledge Reasoning and Heuristic-prompt for Visual-language Navigation","display_name":"Learning Cross-modal Knowledge Reasoning and Heuristic-prompt for Visual-language Navigation","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403582532","doi":"https://doi.org/10.1145/3627673.3679740"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","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/A5110514367","display_name":"Dongming Zhou","orcid":"https://orcid.org/0000-0002-5669-1408"},"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":true,"raw_author_name":"Dongming Zhou","raw_affiliation_strings":["School of Computer Science, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006200583","display_name":"Zhengbin Pang","orcid":"https://orcid.org/0000-0003-2046-5043"},"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":"Zhengbin Pang","raw_affiliation_strings":["School of Computer Science, National University of Defence Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, National University of Defence Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109869303","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-4641-620X"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["School of Computer and Electronic Information, Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Electronic Information, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110514367"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18630577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3453","last_page":"3462"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","score":0.9965999722480774,"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":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.7642781734466553},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7024297714233398},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6744863390922546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.516026496887207},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3288787603378296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7642781734466553},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7024297714233398},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6744863390922546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.516026496887207},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3288787603378296},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2964935470","https://openalex.org/W2999905431","https://openalex.org/W3034500398","https://openalex.org/W3035232877","https://openalex.org/W3044438666","https://openalex.org/W3162602085","https://openalex.org/W3172675210","https://openalex.org/W3176495323","https://openalex.org/W3192009892","https://openalex.org/W3195026654","https://openalex.org/W3217557337","https://openalex.org/W4225122363","https://openalex.org/W4226052928","https://openalex.org/W4310068405","https://openalex.org/W4312238277","https://openalex.org/W4312618696","https://openalex.org/W4375929110","https://openalex.org/W4376166839","https://openalex.org/W4379929708","https://openalex.org/W4382240593","https://openalex.org/W4383108296","https://openalex.org/W4388209508","https://openalex.org/W4388343189","https://openalex.org/W4390645445","https://openalex.org/W4390645544","https://openalex.org/W4390871755","https://openalex.org/W4390871940","https://openalex.org/W4390872901","https://openalex.org/W4390873167","https://openalex.org/W4390874349","https://openalex.org/W4402754062"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Visual":[0],"language":[1,47],"navigation":[2],"is":[3,151],"an":[4],"exciting":[5],"and":[6,20,31,52,67,73,97,148,170,173],"challenging":[7],"multi-modal":[8],"task.":[9],"Most":[10],"existing":[11],"research":[12],"focuses":[13],"on":[14,83,167],"the":[15,25,65,77,88,105,154,158,164,168,174,185],"fusion":[16],"of":[17,27,61,157,187],"visual":[18,46],"features":[19,30,72,102],"semantic":[21,32,143],"space,":[22],"which":[23],"ignoring":[24],"importance":[26],"local":[28,62],"highlight":[29],"knowledge":[33,75,85],"alignment":[34,138,159],"in":[35,64,100,109,194],"images":[36],"for":[37],"agent":[38],"navigation.":[39],"Therefore,":[40],"this":[41],"paper":[42,162],"proposes":[43],"a":[44,114,127,134],"novel":[45],"model":[48,89,117],"combining":[49],"Knowledge-augmented":[50],"Reasoning":[51],"Soft-Prompt":[53],"(KRSP)":[54],"learning.":[55],"First,":[56],"we":[57,132],"perform":[58],"fine-grained":[59],"processing":[60],"regions":[63],"image":[66,71],"to":[68,76,86,103,119],"map":[69],"context":[70],"text":[74],"same":[78],"common":[79],"sub-space.":[80],"We":[81,112],"focus":[82],"regional":[84],"increase":[87],"reasoning":[90],"ability.":[91],"Next,":[92],"soft-prompt":[93],"learning":[94],"aligns":[95],"keywords":[96],"sub-visual":[98,146],"information":[99,147],"instruction":[101,129,149],"solve":[104],"path":[106],"mismatch":[107],"problem":[108],"coarse-grained":[110],"instructions.":[111],"use":[113],"large-scale":[115],"pre-training":[116],"CoCoOp":[118],"collect":[120],"highly":[121],"matched":[122],"soft":[123],"action":[124],"prompts":[125],"into":[126],"unified":[128],"set.":[130],"Finally,":[131],"propose":[133],"general":[135],"cross-modal":[136],"feature":[137],"loss":[139],"function.":[140,160],"The":[141],"potential":[142],"correlation":[144],"between":[145],"space":[150],"closer":[152],"through":[153],"penalty":[155],"mechanism":[156],"This":[161],"verifies":[163],"method":[165],"effectiveness":[166],"R2R":[169],"REVERIE":[171],"datasets,":[172],"experimental":[175],"results":[176],"show":[177],"that":[178],"KRSP":[179,186],"achieves":[180],"state-of-the-art":[181],"performance.":[182],"Among":[183],"them,":[184],"SPL":[188],"evaluation":[189],"metric":[190],"increased":[191],"by":[192],"4.5%":[193],"unseen":[195],"scenarios.":[196]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}