{"id":"https://openalex.org/W4304099262","doi":"https://doi.org/10.1145/3503161.3548283","title":"Cross-modal Semantic Alignment Pre-training for Vision-and-Language Navigation","display_name":"Cross-modal Semantic Alignment Pre-training for Vision-and-Language Navigation","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304099262","doi":"https://doi.org/10.1145/3503161.3548283"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548283","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548283","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5030444210","display_name":"Siying Wu","orcid":"https://orcid.org/0000-0002-9752-258X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siying Wu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079007635","display_name":"Xueyang Fu","orcid":"https://orcid.org/0000-0001-8036-4071"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueyang Fu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103150943","display_name":"Feng Wu","orcid":"https://orcid.org/0000-0001-7266-5579"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Wu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-Jun Zha","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.8321,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.82407174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4233","last_page":"4241"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.989799976348877,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9883999824523926,"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":0.8374698162078857},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6365205645561218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5859558582305908},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.46484464406967163},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4482005536556244},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42918941378593445},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.41170990467071533},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39078956842422485}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8374698162078857},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6365205645561218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5859558582305908},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.46484464406967163},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4482005536556244},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42918941378593445},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.41170990467071533},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39078956842422485},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548283","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548283","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.75,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2593841437","https://openalex.org/W2747329762","https://openalex.org/W2926977875","https://openalex.org/W2964339842","https://openalex.org/W2997591391","https://openalex.org/W2998356391","https://openalex.org/W3034500398","https://openalex.org/W3035232877","https://openalex.org/W3040922163","https://openalex.org/W3091588028","https://openalex.org/W3092825347","https://openalex.org/W3098358101","https://openalex.org/W3105274166","https://openalex.org/W3109097593","https://openalex.org/W3172675210","https://openalex.org/W3174887918","https://openalex.org/W3176425931","https://openalex.org/W3176495323","https://openalex.org/W3195026654","https://openalex.org/W3206064582","https://openalex.org/W3209274285","https://openalex.org/W4212774754","https://openalex.org/W6601048702"],"related_works":["https://openalex.org/W1891287906","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W2755342338","https://openalex.org/W3116076068","https://openalex.org/W2000407620","https://openalex.org/W2369308426"],"abstract_inverted_index":{"Vision-and-Language":[0,85],"Navigation":[1],"needs":[2],"an":[3],"agent":[4,118,158],"to":[5,7,32,47,90,119,124,135],"navigate":[6],"a":[8,76],"target":[9],"location":[10],"by":[11,61,66],"progressively":[12],"grounding":[13],"and":[14,23,39,58,106,170],"following":[15],"the":[16,29,34,49,53,62,92,111,117,126,137,149],"relevant":[17],"instruction":[18],"conditioning":[19],"on":[20,148,167],"its":[21],"memory":[22],"current":[24],"observation.":[25],"Existing":[26],"works":[27],"utilize":[28],"cross-modal":[30],"transformer":[31,155],"pass":[33],"message":[35],"between":[36,52],"visual":[37,122,138],"modality":[38],"textual":[40],"modality.":[41],"However,":[42],"they":[43],"are":[44],"still":[45],"limited":[46],"mining":[48],"fine-grained":[50],"matching":[51],"underlying":[54],"components":[55],"of":[56,79],"trajectories":[57],"instructions.":[59],"Inspired":[60],"significant":[63],"progress":[64],"achieved":[65],"large-scale":[67],"pre-training":[68],"methods,":[69],"in":[70],"this":[71],"paper,":[72],"we":[73,152],"propose":[74],"CSAP,":[75],"new":[77],"method":[78],"Cross-modal":[80],"Semantic":[81],"Alignment":[82],"Pre-training":[83],"for":[84],"Navigation.":[86],"It":[87],"is":[88,133],"designed":[89,134],"learn":[91],"alignment":[93],"from":[94],"trajectory-instruction":[95],"pairs":[96],"through":[97],"two":[98],"novel":[99],"tasks,":[100],"including":[101],"trajectory-conditioned":[102,112],"masked":[103,113,127],"fragment":[104,114],"modeling":[105,115,132],"contrastive":[107,130],"semantic-alignment":[108,131],"modeling.":[109],"Specifically,":[110],"encourages":[116],"extract":[120],"useful":[121],"information":[123],"reconstruct":[125],"fragment.":[128],"The":[129],"align":[136],"representation":[139],"with":[140,160],"corresponding":[141],"phrase":[142],"embeddings.":[143],"By":[144],"showing":[145],"experimental":[146],"results":[147],"benchmark":[150],"dataset,":[151],"demonstrate":[153],"that":[154],"architecture-based":[156],"navigation":[157],"pre-trained":[159],"our":[161],"proposed":[162],"CSAP":[163],"outperforms":[164],"existing":[165],"methods":[166],"both":[168],"SR":[169],"SPL":[171],"scores.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}