{"id":"https://openalex.org/W4403780696","doi":"https://doi.org/10.1145/3664647.3681218","title":"Bilateral Adaptive Cross-Modal Fusion Prompt Learning for CLIP","display_name":"Bilateral Adaptive Cross-Modal Fusion Prompt Learning for CLIP","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780696","doi":"https://doi.org/10.1145/3664647.3681218"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681218","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681218","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":"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/A5102850945","display_name":"Qiang Wang","orcid":"https://orcid.org/0000-0002-5875-7511"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Wang","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5875-7511","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101967246","display_name":"Ke Yan","orcid":"https://orcid.org/0000-0003-3424-4866"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Yan","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3424-4866","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086397952","display_name":"Shouhong Ding","orcid":"https://orcid.org/0000-0002-3175-3553"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouhong Ding","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3175-3553","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9001","last_page":"9009"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9943000078201294,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9943000078201294,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9878000020980835,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9835000038146973,"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/modal","display_name":"Modal","score":0.7073938250541687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6627947092056274},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.48041701316833496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3749317526817322},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08186429738998413}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7073938250541687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6627947092056274},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.48041701316833496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3749317526817322},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08186429738998413},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681218","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681218","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":22,"referenced_works":["https://openalex.org/W1977295328","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2155904486","https://openalex.org/W2533598788","https://openalex.org/W2793547936","https://openalex.org/W2964194231","https://openalex.org/W3037492894","https://openalex.org/W3177096435","https://openalex.org/W3198377975","https://openalex.org/W4212774754","https://openalex.org/W4226058394","https://openalex.org/W4312310776","https://openalex.org/W4312651322","https://openalex.org/W4312747482","https://openalex.org/W4312773012","https://openalex.org/W4386065556","https://openalex.org/W4386071547","https://openalex.org/W4386075561","https://openalex.org/W4387969137","https://openalex.org/W4390873326"],"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/W4396696052"],"abstract_inverted_index":{"In":[0],"the":[1,14,18,29,37,46,49,57,63,67,77,85,96,100,118,150,158,172,192,208],"realm":[2],"of":[3,21,48,59,82,87,99,175,191,212],"CLIP":[4,30,83,119],"adaptation":[5,64],"through":[6],"prompt":[7,69,120],"learning,":[8],"it":[9],"is":[10,43],"important":[11],"to":[12,31,76,94,148,207],"emphasize":[13],"pivotal":[15],"role":[16],"that":[17,36,169],"proper":[19,38,197],"alignment":[20,39,198],"visual":[22,78,104],"and":[23,105,145,160,188,215],"textual":[24,106],"representations":[25],"plays":[26],"when":[27],"adapting":[28],"downstream":[32,41,201],"tasks.":[33,202],"We":[34,203],"propose":[35,113,137,165],"for":[40,56,117,141,199],"tasks":[42],"determined":[44],"by":[45,231],"flexibility":[47],"interaction":[50,102,152],"between":[51,103,153],"cross-modal":[52,89,176],"information,":[53],"which":[54,131],"compensates":[55],"absence":[58],"contrastive":[60],"loss":[61],"during":[62],"process.":[65],"However,":[66],"current":[68],"learning":[70,121],"methods,":[71],"such":[72],"as":[73],"isolated":[74],"modifications":[75],"or":[79,84],"language":[80],"branches":[81],"employment":[86],"uni-directional":[88],"fusion,":[90],"are":[91],"not":[92],"sufficient":[93],"explore":[95],"full":[97],"potential":[98],"mutual":[101,151],"modalities.":[107],"To":[108],"overcome":[109],"this":[110],"limitation,":[111],"we":[112,136,164],"a":[114,185,226],"new":[115],"paradigm":[116],"community,":[122],"named":[123],"Bilateral":[124],"Adaptive":[125],"Cross-Modal":[126],"Fusion":[127],"Prompt":[128],"Learning":[129],"(Bloom),":[130],"includes":[132],"two":[133,182,193],"enhancements.":[134],"First,":[135],"using":[138],"projection":[139],"functions":[140,147],"bi-directional":[142],"modality":[143],"transformation":[144],"fusion":[146],"encourage":[149],"corresponding":[154],"layers":[155],"within":[156],"both":[157],"image":[159,220],"text":[161],"encoders.":[162],"Second,":[163],"an":[166],"adaptive":[167],"manner":[168],"automatically":[170],"searches":[171],"optimal":[173],"combination":[174],"information":[177],"at":[178],"each":[179],"layer.":[180],"These":[181],"improvements":[183],"ensure":[184],"more":[186],"efficient":[187],"flexible":[189],"integration":[190],"modalities,":[194],"thereby":[195],"achieving":[196],"specific":[200],"put":[204],"our":[205],"method":[206],"test":[209],"in":[210],"terms":[211],"base-to-novel,":[213],"cross-dataset,":[214],"cross-domain":[216],"evaluations":[217],"on":[218],"15":[219],"classification":[221],"datasets.":[222],"The":[223],"results":[224],"demonstrate":[225],"significant":[227],"performance":[228],"enhancement":[229],"achieved":[230],"Bloom.":[232]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}