{"id":"https://openalex.org/W4403780489","doi":"https://doi.org/10.1145/3664647.3681525","title":"Virtual Visual-Guided Domain-Shadow Fusion via Modal Exchanging for Domain-Specific Multi-Modal Neural Machine Translation","display_name":"Virtual Visual-Guided Domain-Shadow Fusion via Modal Exchanging for Domain-Specific Multi-Modal Neural Machine Translation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780489","doi":"https://doi.org/10.1145/3664647.3681525"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681525","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5103084343","display_name":"Zhenyu Hou","orcid":"https://orcid.org/0009-0005-1904-880X"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenyu Hou","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103004657","display_name":"Junjun Guo","orcid":"https://orcid.org/0000-0002-3522-7120"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjun Guo","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I10660446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103084343"],"corresponding_institution_ids":["https://openalex.org/I10660446"],"apc_list":null,"apc_paid":null,"fwci":0.695,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7644163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4227","last_page":"4235"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9977999925613403,"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/T10028","display_name":"Topic Modeling","score":0.9939000010490417,"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/modal","display_name":"Modal","score":0.7654796838760376},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7166306972503662},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5940444469451904},{"id":"https://openalex.org/keywords/shadow","display_name":"Shadow (psychology)","score":0.4820731282234192},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4356614053249359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4246664047241211},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36961811780929565},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11786273121833801}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7654796838760376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7166306972503662},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5940444469451904},{"id":"https://openalex.org/C117797892","wikidata":"https://www.wikidata.org/wiki/Q286363","display_name":"Shadow (psychology)","level":2,"score":0.4820731282234192},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4356614053249359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4246664047241211},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36961811780929565},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11786273121833801},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681525","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":35,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1690739335","https://openalex.org/W2133459682","https://openalex.org/W2194775991","https://openalex.org/W2294370754","https://openalex.org/W2889903020","https://openalex.org/W3034773362","https://openalex.org/W3034871396","https://openalex.org/W3091093673","https://openalex.org/W3119746927","https://openalex.org/W3168900788","https://openalex.org/W3174102142","https://openalex.org/W3176395632","https://openalex.org/W3176459575","https://openalex.org/W3207410886","https://openalex.org/W4205509257","https://openalex.org/W4206119104","https://openalex.org/W4206588072","https://openalex.org/W4221155857","https://openalex.org/W4281571140","https://openalex.org/W4285241608","https://openalex.org/W4298326888","https://openalex.org/W4307646385","https://openalex.org/W4312471667","https://openalex.org/W4321483876","https://openalex.org/W4377211416","https://openalex.org/W4385486374","https://openalex.org/W4385569940","https://openalex.org/W4385572230","https://openalex.org/W4385573026","https://openalex.org/W4385573757","https://openalex.org/W4389523842","https://openalex.org/W4390938901","https://openalex.org/W4391065171","https://openalex.org/W4393147243"],"related_works":["https://openalex.org/W2893218741","https://openalex.org/W4392589133","https://openalex.org/W2558319350","https://openalex.org/W1492594177","https://openalex.org/W1842742976","https://openalex.org/W2803235238","https://openalex.org/W3112085556","https://openalex.org/W399661440","https://openalex.org/W4392585872","https://openalex.org/W410356389"],"abstract_inverted_index":{"Incorporating":[0],"domain-specific":[1,13,66,86],"visual":[2,97,108,118,170],"information":[3],"into":[4],"text":[5,111,159],"poses":[6],"one":[7],"of":[8,115,166,213],"the":[9,36,41,113,164,174,195,209],"critical":[10],"challenges":[11],"for":[12,85,125,128],"multi-modal":[14,26,30,71,100],"neural":[15,31],"machine":[16,32,82,122,201],"translation":[17,33,83,123,202],"(DMNMT).":[18],"While":[19],"most":[20],"existing":[21],"DMNMT":[22],"methods":[23,198],"often":[24],"borrow":[25],"fusion":[27,72,101],"frameworks":[28],"from":[29],"(MNMT)":[34],"in":[35,51,81,199],"general":[37,45],"domain,":[38],"they":[39],"overlook":[40],"domain":[42,54,107,129,142,156,177],"gaps":[43],"between":[44,176],"and":[46,110,148,158,179,211],"specific":[47,53],"domains.":[48],"Visual-to-textual":[49],"interaction":[50],"a":[52,79,95,135,167],"frequently":[55],"exhibits":[56],"multi-focus":[57],"characteristics,":[58],"making":[59],"it":[60],"difficult":[61],"to":[62,78,103,139,172],"consistently":[63],"focus":[64],"on":[65,185,223],"multi-visual":[67],"details":[68,109],"using":[69],"traditional":[70],"frameworks.":[73],"This":[74],"challenge":[75],"can":[76],"lead":[77],"decrease":[80],"performance":[84,124],"terms.":[87,130],"To":[88],"tackle":[89],"this":[90,92],"problem,":[91],"paper":[93],"presents":[94],"virtual":[96,117,169],"scene-guided":[98],"domain-shadow":[99],"mechanism":[102],"simultaneously":[104],"integrate":[105],"multi-grained":[106],"with":[112,163],"guidance":[114,165],"modality-agnostic":[116,168],"scene,":[119],"thereby":[120],"enhancing":[121],"DMNMT,":[126],"especially":[127],"Specifically,":[131],"we":[132,152],"first":[133],"adopt":[134],"modality-mixing":[136],"selection-voting":[137],"strategy":[138],"generate":[140],"modality-mixed":[141,155],"representations":[143,157],"through":[144],"layer-by-layer":[145],"intra-modality":[146],"selection":[147],"inter-modality":[149],"exchanging.":[150],"Then,":[151],"gradually":[153],"aggregate":[154],"across":[160,216],"modality":[161],"boundaries":[162],"scene":[171],"enhance":[173],"collaboration":[175],"characteristics":[178],"textual":[180],"semantics.":[181],"The":[182,204],"experimental":[183],"results":[184],"three":[186],"benchmark":[187],"datasets":[188],"demonstrate":[189],"that":[190],"our":[191,214],"proposed":[192],"approach":[193,215],"outperforms":[194],"state-of-the-art":[196],"(SOTA)":[197],"all":[200],"tasks.":[203],"in-depth":[205],"analysis":[206],"further":[207],"highlights":[208],"robustness":[210],"generalizability":[212],"various":[217],"scenarios.":[218],"Our":[219],"code":[220],"is":[221],"available":[222],"https://github.com/HZY2023/VVDF.":[224]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}