{"id":"https://openalex.org/W4387968057","doi":"https://doi.org/10.1145/3581783.3611826","title":"COPA : Efficient Vision-Language Pre-training through Collaborative Object- and Patch-Text Alignment","display_name":"COPA : Efficient Vision-Language Pre-training through Collaborative Object- and Patch-Text Alignment","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968057","doi":"https://doi.org/10.1145/3581783.3611826"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611826","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/A5074446389","display_name":"Chaoya Jiang","orcid":"https://orcid.org/0009-0009-7282-159X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chaoya Jiang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-7282-159X","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066544410","display_name":"Haiyang Xu","orcid":"https://orcid.org/0000-0001-9442-5912"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyang Xu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9442-5912","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101538186","display_name":"Wei Ye","orcid":"https://orcid.org/0000-0002-9331-4716"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Ye","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9331-4716","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005965903","display_name":"Qinghao Ye","orcid":"https://orcid.org/0000-0002-7977-5540"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghao Ye","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7977-5540","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100734065","display_name":"Chenliang Li","orcid":"https://orcid.org/0000-0001-9077-3928"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenliang Li","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9077-3928","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452477","display_name":"Ming Yan","orcid":"https://orcid.org/0000-0003-4959-8878"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Yan","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4959-8878","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081108106","display_name":"Bin Bi","orcid":"https://orcid.org/0000-0003-2207-9146"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Bi","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2207-9146","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101435571","display_name":"Shikun Zhang","orcid":"https://orcid.org/0000-0002-8576-2674"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shikun Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8576-2674","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101488344","display_name":"Fei Huang","orcid":"https://orcid.org/0000-0002-3709-5053"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Huang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3709-5053","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100329266","display_name":"Ji Zhang","orcid":"https://orcid.org/0000-0002-3835-7975"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Zhang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3835-7975","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5074446389"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.1775,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81352614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4480","last_page":"4491"},"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":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9965999722480774,"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":0.8312826156616211},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6282165050506592},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6243672966957092},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5488916635513306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5446668267250061},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5142064094543457},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5077008008956909},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4835329055786133},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.467298299074173},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.458700567483902},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4469892382621765},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38722115755081177},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2820490002632141},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.12275749444961548}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8312826156616211},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6282165050506592},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6243672966957092},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5488916635513306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5446668267250061},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5142064094543457},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5077008008956909},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4835329055786133},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.467298299074173},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.458700567483902},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4469892382621765},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38722115755081177},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2820490002632141},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.12275749444961548},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611826","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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":20,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1905882502","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2560730294","https://openalex.org/W2563399268","https://openalex.org/W2568262903","https://openalex.org/W2963037989","https://openalex.org/W2963084599","https://openalex.org/W3035682985","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3159619744","https://openalex.org/W3173220247","https://openalex.org/W3173909648","https://openalex.org/W4312784228","https://openalex.org/W4385574358","https://openalex.org/W6600137863","https://openalex.org/W6600234944","https://openalex.org/W6600339457"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2097707447","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093","https://openalex.org/W4387272257"],"abstract_inverted_index":{"Vision-Language":[0],"Pre-training":[1],"(VLP)":[2],"methods":[3],"based":[4],"on":[5,138,165],"object":[6,52,86,111],"detection":[7,112],"enjoy":[8],"the":[9,18,106,133],"rich":[10],"knowledge":[11],"of":[12,20,110,141,151],"fine-grained":[13],"object-text":[14],"alignment":[15,40,58],"but":[16],"at":[17],"cost":[19,109],"computationally":[21],"expensive":[22],"inference.":[23],"Recent":[24],"Visual-Transformer":[25],"(ViT)-based":[26],"approaches":[27],"circumvent":[28],"this":[29],"issue":[30],"while":[31,159],"struggling":[32],"with":[33,96,168],"long":[34],"visual":[35],"sequences":[36,128],"without":[37],"detailed":[38],"cross-modal":[39],"information.":[41],"This":[42],"paper":[43],"introduces":[44],"a":[45,55,70,78,139,149],"ViT-based":[46],"VLP":[47,99,157],"technique":[48],"that":[49,119,145],"efficiently":[50],"incorporates":[51],"information":[53],"through":[54],"novel":[56],"patch-text":[57],"mechanism.":[59],"Specifically,":[60],"we":[61,92],"convert":[62],"object-level":[63],"signals":[64],"into":[65],"patch-level":[66],"ones":[67],"and":[68,113,129,172],"devise":[69],"Patch-Text":[71],"Alignment":[72],"pre-training":[73],"task":[74],"(PTA)":[75],"to":[76,155],"learn":[77],"text-aware":[79],"patch":[80,117,127],"detector.":[81],"By":[82],"using":[83],"off-the-shelf":[84],"delicate":[85],"annotations":[87],"in":[88,101],"5%":[89],"training":[90],"images,":[91],"jointly":[93],"train":[94],"PTA":[95],"other":[97],"conventional":[98],"objectives":[100],"an":[102,115],"end-to-end":[103],"manner,":[104],"bypassing":[105],"high":[107],"computational":[108],"yielding":[114],"effective":[116],"detector":[118],"accurately":[120],"detects":[121],"text-relevant":[122],"patches,":[123],"thus":[124],"considerably":[125],"reducing":[126],"accelerating":[130],"computation":[131],"within":[132],"ViT":[134],"backbone.":[135],"Our":[136],"experiments":[137],"variety":[140],"widely-used":[142],"benchmarks":[143],"reveal":[144],"our":[146],"method":[147],"achieves":[148],"speedup":[150],"nearly":[152],"88%":[153],"compared":[154],"prior":[156],"models":[158],"maintaining":[160],"competitive":[161],"or":[162],"superior":[163],"performance":[164],"downstream":[166],"tasks":[167],"similar":[169],"model":[170],"size":[171],"data":[173],"scale.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}