{"id":"https://openalex.org/W4403617341","doi":"https://doi.org/10.1145/3664647.3681256","title":"Visual Grounding with Multi-modal Conditional Adaptation","display_name":"Visual Grounding with Multi-modal Conditional Adaptation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403617341","doi":"https://doi.org/10.1145/3664647.3681256"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681256","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681256","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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.04999","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053695187","display_name":"Ruilin Yao","orcid":"https://orcid.org/0009-0002-6654-2294"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruilin Yao","raw_affiliation_strings":["Wuhan University of Technology &amp; Shanghai Artificial Intelligence Laboratory, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology &amp; Shanghai Artificial Intelligence Laboratory, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I196699116","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011707621","display_name":"Shengwu Xiong","orcid":"https://orcid.org/0000-0002-4006-7029"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengwu Xiong","raw_affiliation_strings":["Wuhan University of Technology &amp; Sanya Science and Education Innovation Park of Wuhan University of Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology &amp; Sanya Science and Education Innovation Park of Wuhan University of Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005399031","display_name":"Yichen Zhao","orcid":"https://orcid.org/0000-0001-7552-3453"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichen Zhao","raw_affiliation_strings":["Sanya Science and Education Innovation Park of Wuhan University of Technology &amp; Wuhan University of Technology, Sanya, Hainan, China"],"affiliations":[{"raw_affiliation_string":"Sanya Science and Education Innovation Park of Wuhan University of Technology &amp; Wuhan University of Technology, Sanya, Hainan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101967703","display_name":"Yi Rong","orcid":"https://orcid.org/0000-0003-4867-6811"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Rong","raw_affiliation_strings":["Wuhan University of Technology &amp; Sanya Science and Education Innovation Park of Wuhan University of Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology &amp; Sanya Science and Education Innovation Park of Wuhan University of Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I196699116"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053695187"],"corresponding_institution_ids":["https://openalex.org/I196699116","https://openalex.org/I4391012619"],"apc_list":null,"apc_paid":null,"fwci":3.3977,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.93791193,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3877","last_page":"3886"},"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":0.9945999979972839,"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":0.9886999726295471,"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":0.8237720727920532},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6243912577629089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5724323987960815},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5580339431762695},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4975908100605011},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49580010771751404},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4926493763923645},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.47439029812812805},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.45534548163414},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4504266679286957},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.44504570960998535},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44059619307518005},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40550506114959717},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3726309537887573},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08542925119400024}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8237720727920532},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6243912577629089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5724323987960815},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5580339431762695},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4975908100605011},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49580010771751404},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4926493763923645},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.47439029812812805},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.45534548163414},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4504266679286957},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.44504570960998535},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44059619307518005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40550506114959717},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3726309537887573},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08542925119400024},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3681256","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681256","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"},{"id":"pmh:oai:arXiv.org:2409.04999","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.04999","pdf_url":"https://arxiv.org/pdf/2409.04999","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.04999","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.04999","pdf_url":"https://arxiv.org/pdf/2409.04999","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2802911279","display_name":null,"funder_award_id":"Young","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G373300205","display_name":null,"funder_award_id":"62306219","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4653825012","display_name":null,"funder_award_id":"62176194","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6356431383","display_name":null,"funder_award_id":"2022ZD0160604","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6488686889","display_name":null,"funder_award_id":"SCKJ-JYRC-2022-76","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7169761342","display_name":null,"funder_award_id":"2023BAB083","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7777819896","display_name":null,"funder_award_id":"-2022","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320331088","display_name":"Natural Science Foundation for Young Scientists of Shanxi Province","ror":null},{"id":"https://openalex.org/F4320335581","display_name":"Young Scientists Fund","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403617341.pdf","grobid_xml":"https://content.openalex.org/works/W4403617341.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2251512949","https://openalex.org/W2946086442","https://openalex.org/W2952524542","https://openalex.org/W2962764817","https://openalex.org/W2962766617","https://openalex.org/W2963109634","https://openalex.org/W2964345792","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2987734933","https://openalex.org/W3034772468","https://openalex.org/W3093314701","https://openalex.org/W3096609285","https://openalex.org/W3138516171","https://openalex.org/W3159619744","https://openalex.org/W3166140588","https://openalex.org/W3173364567","https://openalex.org/W3198675127","https://openalex.org/W3207127495","https://openalex.org/W4200631575","https://openalex.org/W4214490042","https://openalex.org/W4282005462","https://openalex.org/W4282919422","https://openalex.org/W4287122891","https://openalex.org/W4312351586","https://openalex.org/W4312884055","https://openalex.org/W4312906427","https://openalex.org/W4312956471","https://openalex.org/W4313145013","https://openalex.org/W4382458695","https://openalex.org/W4386066126","https://openalex.org/W4386076636","https://openalex.org/W4387969094"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2040545019","https://openalex.org/W2787352659","https://openalex.org/W1970611213","https://openalex.org/W4206560911"],"abstract_inverted_index":{"Visual":[0],"grounding":[1,51,180],"is":[2,212],"the":[3,65,75,84,125,161,166,174,178,202],"task":[4,73],"of":[5,155,177,206],"locating":[6,58],"objects":[7,59],"specified":[8],"by":[9],"natural":[10],"language":[11],"expressions.":[12],"Existing":[13,68],"methods":[14,69],"extend":[15],"generic":[16],"object":[17],"detection":[18,88],"frameworks":[19],"to":[20,98,128,146,164,173],"tackle":[21],"this":[22,72,100,115],"task.":[23],"They":[24],"typically":[25],"extract":[26],"visual":[27,34,50,77,81,96,126,175,179],"and":[28,35,110,170,195,204],"textual":[29,36,108],"features":[30,41,82],"separately":[31],"using":[32],"independent":[33,76],"encoders,":[37],"then":[38],"fuse":[39],"these":[40],"in":[42],"a":[43,153],"multi-modal":[44,148],"decoder":[45],"for":[46,83],"final":[47],"prediction.":[48],"However,":[49],"presents":[52],"unique":[53],"challenges.":[54],"It":[55],"often":[56],"involves":[57],"with":[60,71],"different":[61,144],"text":[62],"descriptions":[63],"within":[64],"same":[66,85],"image.":[67],"struggle":[70],"because":[74],"encoder":[78,127,176],"produces":[79],"identical":[80],"image,":[86],"limiting":[87],"performance.":[89],"Some":[90],"recently":[91],"approaches":[92],"propose":[93],"various":[94],"language-guided":[95],"encoders":[97],"address":[99],"issue,":[101],"but":[102],"they":[103],"mostly":[104],"rely":[105],"solely":[106],"on":[107,184],"information":[109,142],"require":[111],"sophisticated":[112],"designs.":[113],"In":[114],"paper,":[116],"we":[117,139,151],"introduce":[118],"Multi-modal":[119],"Conditional":[120],"Adaptation":[121],"(MMCA),":[122],"which":[123,158],"enables":[124],"adaptively":[129],"update":[130,168],"weights,":[131],"directing":[132],"its":[133],"focus":[134],"towards":[135],"text-relevant":[136],"regions.":[137],"Specifically,":[138],"first":[140],"integrate":[141],"from":[143,160],"modalities":[145],"obtain":[147],"embeddings.":[149],"Then":[150],"utilize":[152],"set":[154],"weighting":[156],"coefficients,":[157],"generated":[159],"multimodal":[162],"embeddings,":[163],"reorganize":[165],"weight":[167],"matrices":[169],"apply":[171],"them":[172],"model.":[181],"Extensive":[182],"experiments":[183,199],"four":[185],"widely":[186],"used":[187],"datasets":[188],"demonstrate":[189,201],"that":[190],"MMCA":[191],"achieves":[192],"significant":[193],"improvements":[194],"state-of-the-art":[196],"results.":[197],"Ablation":[198],"further":[200],"lightweight":[203],"efficiency":[205],"our":[207],"method.":[208],"Our":[209],"source":[210],"code":[211],"available":[213],"at:":[214],"https://github.com/Mr-Bigworth/MMCA.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}
