{"id":"https://openalex.org/W4387969094","doi":"https://doi.org/10.1145/3581783.3612584","title":"LUNA: Language as Continuing Anchors for Referring Expression Comprehension","display_name":"LUNA: Language as Continuing Anchors for Referring Expression Comprehension","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969094","doi":"https://doi.org/10.1145/3581783.3612584"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612584","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612584","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612584","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612584","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071972923","display_name":"Yaoyuan Liang","orcid":"https://orcid.org/0009-0002-6708-458X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yaoyuan Liang","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0002-6708-458X","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102788842","display_name":"Zhao Yang","orcid":"https://orcid.org/0000-0003-4376-0109"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhao Yang","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-4376-0109","affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101926293","display_name":"Yansong Tang","orcid":"https://orcid.org/0000-0002-1534-4549"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yansong Tang","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-1534-4549","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021386418","display_name":"Jiashuo Fan","orcid":"https://orcid.org/0009-0003-8087-3409"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiashuo Fan","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0003-8087-3409","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101820102","display_name":"Ziran Li","orcid":"https://orcid.org/0009-0007-0620-3561"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziran Li","raw_affiliation_strings":["Meituan Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-0620-3561","affiliations":[{"raw_affiliation_string":"Meituan Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingang Wang","orcid":"https://orcid.org/0000-0001-5758-0083"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingang Wang","raw_affiliation_strings":["Meituan Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5758-0083","affiliations":[{"raw_affiliation_string":"Meituan Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042899882","display_name":"Philip H. S. Torr","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip H.S. Torr","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0006-0259-5732","affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088293566","display_name":"Shao\u2010Lun Huang","orcid":"https://orcid.org/0000-0003-2827-4022"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shao-Lun Huang","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2827-4022","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5071972923"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.942,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77674819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5174","last_page":"5184"},"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/T10028","display_name":"Topic Modeling","score":0.9944000244140625,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9937999844551086,"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":0.8450062274932861},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.8084074854850769},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5519306063652039},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5096735954284668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4371992349624634},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4321785271167755},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.415168821811676},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34389668703079224},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17180410027503967},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13511726260185242},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10325270891189575},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08762374520301819}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8450062274932861},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.8084074854850769},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5519306063652039},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5096735954284668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4371992349624634},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4321785271167755},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.415168821811676},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34389668703079224},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17180410027503967},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13511726260185242},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10325270891189575},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08762374520301819},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"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":2,"locations":[{"id":"doi:10.1145/3581783.3612584","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612584","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612584","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:9d5a842c-a315-4114-9ce2-8dde1652ed3c","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"Conference item"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612584","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612584","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612584","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"awards":[{"id":"https://openalex.org/G6505763180","display_name":null,"funder_award_id":"EP/W002981/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320320005","display_name":"Royal Academy of Engineering","ror":"https://ror.org/0526snb40"},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387969094.pdf","grobid_xml":"https://content.openalex.org/works/W4387969094.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W1566289585","https://openalex.org/W1773149199","https://openalex.org/W1895577753","https://openalex.org/W2006147162","https://openalex.org/W2064675550","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2606473278","https://openalex.org/W2952524542","https://openalex.org/W2962766617","https://openalex.org/W2963783181","https://openalex.org/W2986755220","https://openalex.org/W2987734933","https://openalex.org/W2997591391","https://openalex.org/W3003205975","https://openalex.org/W3034772468","https://openalex.org/W3035097537","https://openalex.org/W3096609285","https://openalex.org/W3110435696","https://openalex.org/W3159619744","https://openalex.org/W3167762716","https://openalex.org/W4214627427","https://openalex.org/W4309181071","https://openalex.org/W4313145013"],"related_works":["https://openalex.org/W2580650124","https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W3142333283","https://openalex.org/W3122088529","https://openalex.org/W3041320102","https://openalex.org/W2111669074","https://openalex.org/W2085259108","https://openalex.org/W3123087812","https://openalex.org/W2063076820"],"abstract_inverted_index":{"Referring":[0],"expression":[1,96],"comprehension":[2],"aims":[3],"to":[4,16,63,175],"localize":[5],"a":[6,68,83,98,114,129,151,167],"natural":[7],"language":[8,59],"description":[9],"in":[10,20,67,82,113,166,188],"an":[11,90],"image.":[12],"Using":[13],"location":[14,76,111],"priors":[15,77],"help":[17],"reduce":[18],"inaccuracies":[19],"cross-modal":[21],"alignments":[22],"is":[23,125],"the":[24,27,43,94,122,140,144,149,156,163,189,198],"state":[25],"of":[26,158,200],"art":[28],"for":[29,45,131],"CNN-based":[30],"methods":[31,196],"tackling":[32],"this":[33,40,52,104],"problem.":[34],"Recent":[35],"Transformer-based":[36,84],"models":[37],"cast":[38],"aside":[39],"idea,":[41],"making":[42],"case":[44],"steering":[46],"away":[47],"from":[48,93],"hand-designed":[49],"components.":[50],"In":[51,148],"work,":[53],"we":[54,186],"propose":[55],"LUNA,":[56],"which":[57,181],"uses":[58,103],"as":[60,110,128,185],"continuing":[61],"anchors":[62],"guide":[64],"box":[65,92,124,173],"prediction":[66,165],"Transformer":[69,116],"decoder,":[70],"and":[71,101,106,135,204],"thus":[72],"show":[73],"that":[74],"language-guided":[75],"can":[78],"be":[79,176],"effectively":[80],"exploited":[81],"architecture.":[85],"Our":[86,191],"method":[87,192],"first":[88,126],"initializes":[89],"anchor":[91,105,123],"input":[95],"via":[97],"small":[99],"\"proto-decoder,''":[100],"then":[102,136],"its":[107],"refined":[108,146],"successors":[109],"guidance":[112],"modified":[115],"decoder.":[117],"At":[118],"each":[119],"decoder":[120],"layer,":[121],"used":[127],"query":[130],"gathering":[132],"multi-modal":[133],"context,":[134],"updated":[137],"based":[138],"on":[139,178,197],"gathered":[141],"context":[142],"(producing":[143],"next,":[145],"anchor).":[147],"end,":[150],"lightweight":[152],"assessment":[153],"pathway":[154],"evaluates":[155],"quality":[157],"all":[159],"produced":[160],"anchors,":[161,180],"yielding":[162],"final":[164],"dynamic":[168],"way.":[169],"This":[170],"approach":[171],"allows":[172],"decoding":[174],"conditioned":[177],"learned":[179],"facilitates":[182],"accurate":[183],"grounding,":[184],"shown":[187],"experiments.":[190],"outperforms":[193],"existing":[194],"state-of-the-art":[195],"datasets":[199],"ReferIt":[201],"Game,":[202],"RefCOCO/+/g,":[203],"Flickr30K":[205],"Entities.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}