{"id":"https://openalex.org/W3205869909","doi":"https://doi.org/10.1145/3474085.3475629","title":"Bottom-Up and Bidirectional Alignment for Referring Expression Comprehension","display_name":"Bottom-Up and Bidirectional Alignment for Referring Expression Comprehension","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3205869909","doi":"https://doi.org/10.1145/3474085.3475629","mag":"3205869909"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475629","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th 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/A5029641017","display_name":"Liuwu Li","orcid":"https://orcid.org/0000-0002-6237-5380"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liuwu Li","raw_affiliation_strings":["South China University of Technology & Ministry of Education of China, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology & Ministry of Education of China, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045310029","display_name":"Yuqi Bu","orcid":"https://orcid.org/0000-0002-2158-8750"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqi Bu","raw_affiliation_strings":["South China University of Technology & Ministry of Education of China, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology & Ministry of Education of China, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089123257","display_name":"Yi Cai","orcid":"https://orcid.org/0000-0002-1767-789X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Cai","raw_affiliation_strings":["South China University of Technology & Ministry of Education of China, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology & Ministry of Education of China, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9703,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.77882615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5167","last_page":"5175"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9945999979972839,"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/T11439","display_name":"Video Analysis and Summarization","score":0.989799976348877,"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":0.7787727117538452},{"id":"https://openalex.org/keywords/referent","display_name":"Referent","score":0.6995529532432556},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.66829913854599},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.6549328565597534},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5955533981323242},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5567427277565002},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5320395231246948},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.4783030152320862},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4611290991306305},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4448883533477783},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32502222061157227},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09919947385787964},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09376010298728943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7787727117538452},{"id":"https://openalex.org/C2777096784","wikidata":"https://www.wikidata.org/wiki/Q3826351","display_name":"Referent","level":2,"score":0.6995529532432556},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.66829913854599},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.6549328565597534},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5955533981323242},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5567427277565002},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5320395231246948},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4783030152320862},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4611290991306305},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4448883533477783},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32502222061157227},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09919947385787964},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09376010298728943},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475629","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2247513039","https://openalex.org/W2251512949","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2606473278","https://openalex.org/W2952524542","https://openalex.org/W2963109634","https://openalex.org/W2963783181","https://openalex.org/W2963914122","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2986803748","https://openalex.org/W2987734933","https://openalex.org/W3034772468","https://openalex.org/W3035097537","https://openalex.org/W3098232790"],"related_works":["https://openalex.org/W2143938773","https://openalex.org/W2366781357","https://openalex.org/W2931688134","https://openalex.org/W2493878481","https://openalex.org/W1968508462","https://openalex.org/W2377919138","https://openalex.org/W2167817468","https://openalex.org/W2057848526","https://openalex.org/W2373862202","https://openalex.org/W2388232445"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,50,86,123],"propose":[4,87,125],"a":[5,22,34,88,126],"one-stage":[6,172],"approach":[7,131,161],"to":[8,21,79,105,132,140],"improve":[9],"referring":[10,31,72],"expression":[11],"comprehension":[12],"(REC)":[13],"which":[14,175],"aims":[15],"at":[16],"grounding":[17],"the":[18,52,56,65,81,98,119,142,171,177],"referent":[19],"according":[20],"natural":[23],"language":[24,53],"expression.":[25,73],"We":[26],"observe":[27],"that":[28,159],"humans":[29],"understand":[30],"expressions":[32],"through":[33],"fine-to-coarse":[35],"bottom-up":[36,89,143],"way,":[37],"and":[38,45,55,78,90,108,115,156,167],"bidirectionally":[39,109],"obtain":[40],"vision-language":[41,111],"information":[42,112],"between":[43,113],"image":[44,114],"text.":[46,116],"Inspired":[47],"by":[48,75],"this,":[49],"define":[51],"granularity":[54],"vision":[57],"granularity.":[58],"Otherwise,":[59],"existing":[60,84],"methods":[61],"do":[62],"not":[63],"follow":[64],"mentioned":[66],"way":[67],"of":[68,83,121,151,179],"human":[69],"understanding":[70],"in":[71],"Motivated":[74],"our":[76,160,180],"observation":[77],"address":[80],"limitations":[82],"methods,":[85],"bidirectional":[91],"alignment":[92,100,144],"(BBA)":[93],"framework.":[94,145],"Our":[95],"method":[96],"constructs":[97],"cross-modal":[99],"starting":[101],"from":[102],"fine-grained":[103],"representation":[104,107],"coarse-grained":[106],"obtains":[110,162],"Based":[117],"on":[118,147],"structure":[120],"BBA,":[122],"further":[124],"progressive":[127],"visual":[128,134],"attribute":[129],"decomposing":[130],"decompose":[133],"proposals":[135],"into":[136],"several":[137],"independent":[138],"spaces":[139],"enhance":[141],"Experiments":[146],"five":[148],"benchmark":[149],"datasets":[150],"RefCOCO,":[152],"RefCOCO+,":[153],"ReferItGame,":[154],"RefCOCOg":[155],"Flick30K":[157],"show":[158],"+2.16%,":[163],"+4.47%,":[164],"+2.85%,":[165],"+3.44%,":[166],"+2.91%":[168],"improvements":[169],"over":[170],"SOTA":[173],"approaches,":[174],"validates":[176],"effectiveness":[178],"approach.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}