{"id":"https://openalex.org/W4386590759","doi":"https://doi.org/10.1109/tmm.2023.3314153","title":"A Survivor in the Era of Large-Scale Pretraining: An Empirical Study of One-Stage Referring Expression Comprehension","display_name":"A Survivor in the Era of Large-Scale Pretraining: An Empirical Study of One-Stage Referring Expression Comprehension","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386590759","doi":"https://doi.org/10.1109/tmm.2023.3314153"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3314153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3314153","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5102997988","display_name":"Gen Luo","orcid":"https://orcid.org/0000-0001-5334-1843"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gen Luo","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Fujian, China","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5334-1843","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Fujian, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091531008","display_name":"Yiyi Zhou","orcid":"https://orcid.org/0000-0002-5110-4526"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyi Zhou","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0002-5110-4526","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047090194","display_name":"Jiamu Sun","orcid":"https://orcid.org/0000-0003-2929-552X"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamu Sun","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0003-2929-552X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059926864","display_name":"Xiaoshuai Sun","orcid":"https://orcid.org/0000-0003-3912-9306"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Sun","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0003-3912-9306","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Fujian, China","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9163-2932","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Fujian, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0636,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79431202,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"26","issue":null,"first_page":"3689","last_page":"3700"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9986000061035156,"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":0.9986000061035156,"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":0.988099992275238,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9365000128746033,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.714496910572052},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.6284432411193848},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.522993803024292},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.48866918683052063},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.480642706155777},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.453498899936676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4288238286972046},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4199422597885132},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33812856674194336},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1566520631313324},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1418887972831726},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08509805798530579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.714496910572052},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.6284432411193848},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.522993803024292},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.48866918683052063},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.480642706155777},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.453498899936676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4288238286972046},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4199422597885132},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33812856674194336},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1566520631313324},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1418887972831726},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08509805798530579},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3314153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3314153","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1271955826","display_name":"\u57fa\u4e8e\u5f31\u76d1\u7763\u5b66\u4e60\u7684\u673a\u8f7d\u5730/\u6d77\u5c0f\u76ee\u6807\u68c0\u6d4b\u7814\u7a76","funder_award_id":"62072387","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1787173488","display_name":"\u9762\u5411\u6df1\u5ea6\u5b66\u4e60\u7684\u5bf9\u6297\u653b\u9632\u6280\u672f\u7814\u7a76","funder_award_id":"62072389","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2785666877","display_name":null,"funder_award_id":"62002305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3568142893","display_name":null,"funder_award_id":"62272401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5284885812","display_name":null,"funder_award_id":"62176222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6075090814","display_name":null,"funder_award_id":"62025603","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"},{"id":"https://openalex.org/G6727647225","display_name":null,"funder_award_id":"62176226","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G717600273","display_name":null,"funder_award_id":"U22B2051","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7272499820","display_name":null,"funder_award_id":"U21B2037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7779606772","display_name":null,"funder_award_id":"62176223","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8406165135","display_name":"\u9762\u5411\u56fe\u654f\u611f\u6df1\u5ea6\u5b66\u4e60\u7684\u7ed3\u6784\u5316\u8d85\u56fe\u7814\u7a76","funder_award_id":"62072386","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2146502635","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2571175805","https://openalex.org/W2583360688","https://openalex.org/W2606473278","https://openalex.org/W2606746036","https://openalex.org/W2745461083","https://openalex.org/W2746314669","https://openalex.org/W2779827764","https://openalex.org/W2886641317","https://openalex.org/W2904910963","https://openalex.org/W2912792574","https://openalex.org/W2952524542","https://openalex.org/W2962766617","https://openalex.org/W2963109634","https://openalex.org/W2963351448","https://openalex.org/W2963656855","https://openalex.org/W2963735856","https://openalex.org/W2963855133","https://openalex.org/W2964022527","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2966683369","https://openalex.org/W2983358816","https://openalex.org/W2984121207","https://openalex.org/W2986803748","https://openalex.org/W2987734933","https://openalex.org/W2989868392","https://openalex.org/W2992308087","https://openalex.org/W2998508940","https://openalex.org/W3035097537","https://openalex.org/W3035497460","https://openalex.org/W3035682985","https://openalex.org/W3042011474","https://openalex.org/W3090449556","https://openalex.org/W3093025045","https://openalex.org/W3094502228","https://openalex.org/W3110435696","https://openalex.org/W3112077297","https://openalex.org/W3138516171","https://openalex.org/W3159619744","https://openalex.org/W3173909648","https://openalex.org/W3174004334","https://openalex.org/W3174965650","https://openalex.org/W3182736162","https://openalex.org/W3184439416","https://openalex.org/W3192448690","https://openalex.org/W3203354307","https://openalex.org/W3206582857","https://openalex.org/W4210820868","https://openalex.org/W4214490042","https://openalex.org/W4224304134","https://openalex.org/W4283029876","https://openalex.org/W4293584584","https://openalex.org/W4304891068","https://openalex.org/W4309181071","https://openalex.org/W4312351586","https://openalex.org/W4313068342","https://openalex.org/W4313184803","https://openalex.org/W4385245566","https://openalex.org/W4386065815","https://openalex.org/W4386075493","https://openalex.org/W6637373629","https://openalex.org/W6676497082","https://openalex.org/W6681435938","https://openalex.org/W6685230081","https://openalex.org/W6733814495","https://openalex.org/W6743428213","https://openalex.org/W6745136726","https://openalex.org/W6750227808","https://openalex.org/W6755207826","https://openalex.org/W6758645304","https://openalex.org/W6766904570","https://openalex.org/W6768021236","https://openalex.org/W6779473860","https://openalex.org/W6789753369","https://openalex.org/W6798838024","https://openalex.org/W6839015040"],"related_works":["https://openalex.org/W2329386257","https://openalex.org/W2503350049","https://openalex.org/W2397616145","https://openalex.org/W2616627668","https://openalex.org/W2397320258","https://openalex.org/W3137121595","https://openalex.org/W4324058133","https://openalex.org/W648618910","https://openalex.org/W2373862202","https://openalex.org/W2388232445"],"abstract_inverted_index":{"One-stage":[0],"Referring":[1],"Expression":[2],"Comprehension":[3],"(REC)":[4],"is":[5],"a":[6,42,65,127,164],"task":[7,39],"that":[8,105,150],"requires":[9],"accurate":[10],"alignment":[11],"between":[12],"text":[13],"descriptions":[14],"and":[15,69,117,156,172],"visual":[16],"content.":[17],"In":[18,142],"recent":[19],"years,":[20],"numerous":[21],"efforts":[22],"have":[23],"been":[24],"devoted":[25],"to":[26,82,111,144],"cross-modal":[27],"learning":[28],"for":[29],"REC,":[30],"while":[31],"the":[32,73,102,175],"influence":[33],"of":[34,76,166,178],"other":[35],"factors":[36,104],"in":[37,54,109,180],"this":[38,47,55],"still":[40],"lacks":[41],"systematic":[43],"study.":[44],"To":[45],"fill":[46],"gap,":[48],"we":[49,58,86,124,147],"conduct":[50,87],"an":[51],"empirical":[52],"study":[53],"article.":[56],"Concretely,":[57],"ablate":[59],"42":[60],"candidate":[61],"designs/settings":[62],"based":[63],"on":[64,92,121,139],"common":[66],"REC":[67,78,94,107,179],"framework,":[68],"these":[70,122,140,145],"candidates":[71],"cover":[72],"entire":[74],"process":[75],"one-stage":[77],"from":[79],"network":[80],"design":[81],"model":[83,131],"training.":[84],"Afterwards,":[85],"over":[88],"100":[89],"experimental":[90,99],"trials":[91],"three":[93],"benchmark":[95],"datasets.":[96],"The":[97],"extensive":[98],"results":[100],"reveal":[101],"key":[103],"affect":[106],"performance":[108,138,162],"addition":[110,143],"multi-modal":[112],"fusion,":[113],"e.g.,":[114,170],"multi-scale":[115],"features":[116],"data":[118],"augmentation.":[119],"Based":[120],"findings,":[123],"further":[125],"propose":[126],"simple":[128],"yet":[129],"strong":[130],"called":[132],"SimREC,":[133],"which":[134],"achieves":[135],"new":[136],"state-of-the-art":[137],"benchmarks.":[141],"progresses,":[146],"also":[148],"find":[149],"with":[151],"much":[152],"less":[153],"training":[154],"overhead":[155],"parameters,":[157],"SimREC":[158],"can":[159],"achieve":[160],"better":[161],"than":[163],"set":[165],"large-scale":[167],"pre-trained":[168],"models,":[169],"UNITER":[171],"VILLA,":[173],"portraying":[174],"special":[176],"role":[177],"existing":[181],"V&L":[182],"research.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}