{"id":"https://openalex.org/W4304084163","doi":"https://doi.org/10.1145/3503161.3548320","title":"CAliC: Accurate and Efficient Image-Text Retrieval via Contrastive Alignment and Visual Contexts Modeling","display_name":"CAliC: Accurate and Efficient Image-Text Retrieval via Contrastive Alignment and Visual Contexts Modeling","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304084163","doi":"https://doi.org/10.1145/3503161.3548320"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548320","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548320","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":"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/A5101765091","display_name":"Hongyu Gao","orcid":"https://orcid.org/0000-0002-0769-9577"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongyu Gao","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101989915","display_name":"Chao Zhu","orcid":"https://orcid.org/0000-0001-5486-7492"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhu","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088499239","display_name":"Mengyin Liu","orcid":"https://orcid.org/0000-0002-9719-8417"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyin Liu","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037284650","display_name":"Weibo Gu","orcid":null},"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":"Weibo Gu","raw_affiliation_strings":["Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070033770","display_name":"Hongfa Wang","orcid":"https://orcid.org/0000-0001-8230-9471"},"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":"Hongfa Wang","raw_affiliation_strings":["Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431792","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-3865-8145"},"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":"Wei Liu","raw_affiliation_strings":["Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074514262","display_name":"Xu-Cheng Yin","orcid":"https://orcid.org/0000-0003-0023-0220"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu-cheng Yin","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101765091"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":0.4797,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73206901,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4957","last_page":"4966"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9990000128746033,"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":0.9983999729156494,"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":0.847437858581543},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6616197228431702},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6602681875228882},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6245809197425842},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5560817718505859},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.5033475756645203},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4959782063961029},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.47404858469963074},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45216524600982666},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3936556577682495},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35083329677581787},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3198402523994446}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.847437858581543},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6616197228431702},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6602681875228882},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6245809197425842},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5560817718505859},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.5033475756645203},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4959782063961029},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.47404858469963074},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45216524600982666},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3936556577682495},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35083329677581787},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3198402523994446},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548320","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548320","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":[],"awards":[{"id":"https://openalex.org/G2291578371","display_name":null,"funder_award_id":"62072032, 62076024","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2379300237","display_name":null,"funder_award_id":"2020AAA09701","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8772010899","display_name":null,"funder_award_id":"62125601","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W2277195237","https://openalex.org/W2560674852","https://openalex.org/W2604272474","https://openalex.org/W2747329762","https://openalex.org/W2883311563","https://openalex.org/W2970231061","https://openalex.org/W2998356391","https://openalex.org/W3092820619","https://openalex.org/W3177224328"],"related_works":["https://openalex.org/W2063218608","https://openalex.org/W4386105885","https://openalex.org/W2071180033","https://openalex.org/W2184288218","https://openalex.org/W2947282851","https://openalex.org/W2374066281","https://openalex.org/W4387423606","https://openalex.org/W2147874738","https://openalex.org/W2036058638","https://openalex.org/W2513891871"],"abstract_inverted_index":{"Image-text":[0],"retrieval":[1,40,52,59,73,143,179,232,244,248],"is":[2,121,164],"an":[3,137],"essential":[4],"task":[5,200],"of":[6,85,156,189,224],"information":[7,58,212],"retrieval,":[8],"in":[9,56,91],"which":[10,176,228],"the":[11,14,25,33,37,50,57,62,72,83,86,105,116,125,153,157,160,178,182,186,190,205,210,222],"models":[12,35],"with":[13,24,115,166],"Vision-and-Language":[15],"Pretraining(VLP)":[16],"are":[17,77,98,111],"able":[18],"to":[19,61,82,113,128,170,203],"achieve":[20,36],"ideal":[21],"accuracy":[22,74,180,233],"compared":[23],"ones":[26],"without":[27],"VLP.":[28],"Among":[29],"different":[30],"VLP":[31,64,93],"approaches,":[32],"single-stream":[34,63],"overall":[38],"best":[39],"accuracy,":[41],"but":[42],"slower":[43],"inference":[44,183,238],"speed.":[45,184],"Recently,":[46],"researchers":[47],"have":[48],"introduced":[49],"two-stage":[51,141],"setting":[53],"commonly":[54],"used":[55],"field":[60],"model":[65,144],"for":[66,124],"a":[67,195,230,236],"better":[68,208],"accuracy/efficiency":[69],"trade-off.":[70],"However,":[71],"and":[75,119,139,148,181,213,240,252],"efficiency":[76],"still":[78],"unsatisfactory":[79],"mainly":[80],"due":[81],"limitations":[84],"patch-based":[87],"visual":[88,102,106,130,149,161,174,197,211],"unimodal":[89,96,162],"encoder":[90,127,163,207],"these":[92,133],"models.":[94],"The":[95],"encoders":[97],"trained":[99],"on":[100,246],"pure":[101],"data,":[103],"so":[104],"features":[107,118],"extracted":[108],"by":[109],"them":[110],"difficult":[112,123],"align":[114],"textual":[117],"it":[120],"also":[122],"multi-modal":[126,206],"understand":[129,209],"information.":[131],"Under":[132],"circumstances,":[134],"we":[135,193],"propose":[136],"accurate":[138,216],"efficient":[140],"image-text":[142,247],"via":[145],"Contrastive":[146],"Alignment":[147],"Contexts":[150],"modeling(CAliC).":[151],"In":[152,185],"first":[154],"stage":[155,188],"proposed":[158,191,226],"model,":[159,192],"pretrained":[165],"cross-modal":[167],"contrastive":[168],"learning":[169],"extract":[171],"easily":[172],"aligned":[173],"features,":[175],"improves":[177],"second":[187],"introduce":[194],"new":[196],"contexts":[198],"modeling":[199],"during":[201],"pretraining":[202],"help":[204],"get":[214],"more":[215],"predictions.":[217],"Extensive":[218],"experimental":[219],"evaluation":[220],"validates":[221],"effectiveness":[223],"our":[225],"approach,":[227],"achieves":[229],"higher":[231],"while":[234],"keeping":[235],"faster":[237],"speed,":[239],"outperforms":[241],"existing":[242],"state-of-the-art":[243],"methods":[245],"tasks":[249],"over":[250],"Flickr30K":[251],"COCO":[253],"benchmarks.":[254]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}