{"id":"https://openalex.org/W4304080723","doi":"https://doi.org/10.1145/3503161.3548417","title":"Towards Further Comprehension on Referring Expression with Rationale","display_name":"Towards Further Comprehension on Referring Expression with Rationale","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304080723","doi":"https://doi.org/10.1145/3503161.3548417"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548417","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548417","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/A5064453711","display_name":"Rengang Li","orcid":"https://orcid.org/0000-0002-4297-4335"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rengang Li","raw_affiliation_strings":["Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102813072","display_name":"Baoyu Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoyu Fan","raw_affiliation_strings":["Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101616811","display_name":"Xiaochuan Li","orcid":"https://orcid.org/0000-0001-6143-0854"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochuan Li","raw_affiliation_strings":["Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101549172","display_name":"Runze Zhang","orcid":"https://orcid.org/0009-0003-6318-3342"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runze Zhang","raw_affiliation_strings":["Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055656398","display_name":"Zhenhua Guo","orcid":"https://orcid.org/0000-0002-1303-6681"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Guo","raw_affiliation_strings":["Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101715291","display_name":"Kun Zhao","orcid":"https://orcid.org/0000-0002-8483-2511"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Zhao","raw_affiliation_strings":["Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101568187","display_name":"Yaqian Zhao","orcid":"https://orcid.org/0000-0002-9170-0090"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaqian Zhao","raw_affiliation_strings":["Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074821242","display_name":"Weifeng Gong","orcid":"https://orcid.org/0009-0005-0213-8008"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Gong","raw_affiliation_strings":["Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043582248","display_name":"Endong Wang","orcid":"https://orcid.org/0000-0002-7715-0045"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Endong Wang","raw_affiliation_strings":["Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Inspur Electronic Information Industry Co.,Ltd. & State Key Laboratory of High-end Server & Storage Technology, Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5064453711"],"corresponding_institution_ids":["https://openalex.org/I4210144143"],"apc_list":null,"apc_paid":null,"fwci":0.1199,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.41622701,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4336","last_page":"4344"},"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":0.9916999936103821,"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":0.9904000163078308,"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/expression","display_name":"Expression (computer science)","score":0.8175588250160217},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7943707704544067},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7531371712684631},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7315727472305298},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.6957629323005676},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6830477714538574},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6461809277534485},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6263561248779297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5747705698013306},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5572975873947144},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4977398216724396},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39050036668777466},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33950525522232056},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3252909183502197},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08217817544937134},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06346315145492554}],"concepts":[{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.8175588250160217},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943707704544067},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7531371712684631},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7315727472305298},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.6957629323005676},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6830477714538574},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6461809277534485},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6263561248779297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5747705698013306},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5572975873947144},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4977398216724396},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39050036668777466},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33950525522232056},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3252909183502197},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08217817544937134},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06346315145492554},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548417","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548417","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/G2758318753","display_name":null,"funder_award_id":"2021ZD0113004","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W21629204","https://openalex.org/W1256890642","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2561715562","https://openalex.org/W2604769036","https://openalex.org/W2885909793","https://openalex.org/W2901988662","https://openalex.org/W2907143950","https://openalex.org/W2946086442","https://openalex.org/W2963109634","https://openalex.org/W2963735856","https://openalex.org/W2964002344","https://openalex.org/W2964345792","https://openalex.org/W3034727271","https://openalex.org/W3090449556","https://openalex.org/W3093355642","https://openalex.org/W3093407505","https://openalex.org/W3096609285","https://openalex.org/W3110435696","https://openalex.org/W3112077297","https://openalex.org/W3159619744","https://openalex.org/W3174004334","https://openalex.org/W3174965650","https://openalex.org/W3207204435","https://openalex.org/W3209108897","https://openalex.org/W4220667080"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2373862202","https://openalex.org/W2388232445"],"abstract_inverted_index":{"Referring":[0,107],"Expression":[1,108],"Comprehension":[2,105],"(REC)":[3],"is":[4,17],"one":[5],"important":[6],"research":[7],"branch":[8],"in":[9,23,29],"visual":[10,127,214],"grounding,":[11],"where":[12],"the":[13,24,30,58,61,70,121,131,139,144,157,189,192,211],"goal":[14],"of":[15,32,60,73,133,191,213],"REC":[16,42],"to":[18,34,68,88,93,180,203],"localize":[19],"a":[20,37,99,150,176],"relevant":[21],"object":[22,51,141],"image,":[25],"given":[26],"an":[27,90],"expression":[28,124],"form":[31],"text":[33,46,123],"exactly":[35],"describe":[36],"specific":[38],"object.":[39],"However,":[40],"existing":[41],"tasks":[43],"aim":[44],"at":[45],"content":[47],"filtering":[48],"and":[49,77,97,167,209],"image":[50],"locating,":[52],"which":[53],"are":[54],"evaluated":[55],"based":[56,125,142,155],"on":[57,86,106,116,126,143,156],"precision":[59],"detection":[62],"boxes.":[63],"This":[64],"may":[65],"lead":[66],"models":[67],"skip":[69],"learning":[71],"process":[72],"multimodal":[74],"comprehension":[75],"directly":[76],"achieve":[78,181],"good":[79],"performance.":[80],"In":[81,110],"this":[82,111,134,164,197,207],"paper,":[83],"we":[84,113,148,174],"work":[85,198],"how":[87],"enable":[89],"artificial":[91],"agent":[92],"understand":[94],"RE":[95],"further":[96],"propose":[98],"more":[100,201],"comprehensive":[101],"task,":[102,112],"called":[103],"Further":[104],"(FREC).":[109],"mainly":[114],"focus":[115],"three":[117],"sub-tasks:":[118],"1)":[119],"correcting":[120],"erroneous":[122],"information;":[128],"2)":[129],"generating":[130],"rationale":[132],"input":[135],"expression;":[136],"3)":[137],"localizing":[138],"proper":[140],"corrected":[145],"expression.":[146],"Accordingly,":[147],"make":[149,168],"new":[151,165],"dataset":[152],"named":[153],"Further-RefCOCOs":[154],"RefCOCO,":[158],"RefCOCO+,":[159],"RefCOCOg":[160],"benchmark":[161],"datasets":[162],"for":[163],"task":[166],"it":[169],"publicly":[170],"available.":[171],"After":[172],"that,":[173],"design":[175],"novel":[177],"end-to-end":[178],"pipeline":[179],"these":[182],"sub-tasks":[183],"simultaneously.":[184],"The":[185],"experimental":[186],"results":[187],"demonstrate":[188],"validity":[190],"proposed":[193],"pipeline.":[194],"We":[195],"believe":[196],"will":[199],"motivate":[200],"researchers":[202],"explore":[204],"along":[205],"with":[206],"direction,":[208],"promote":[210],"development":[212],"grounding.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}