{"id":"https://openalex.org/W4408354313","doi":"https://doi.org/10.1109/icassp49660.2025.10888443","title":"Improving Open-Ended Referring Expression Comprehension via Dual-Language Constraints","display_name":"Improving Open-Ended Referring Expression Comprehension via Dual-Language Constraints","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354313","doi":"https://doi.org/10.1109/icassp49660.2025.10888443"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5042036249","display_name":"Chenglong Lei","orcid":"https://orcid.org/0009-0002-8021-289X"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Lei","raw_affiliation_strings":["Hunan University,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,Changsha,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749334","display_name":"Chao Yang","orcid":"https://orcid.org/0000-0003-0406-7598"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Yang","raw_affiliation_strings":["Hunan University,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,Changsha,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047894672","display_name":"Jianbo Zheng","orcid":"https://orcid.org/0000-0002-7304-1271"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianbo Zheng","raw_affiliation_strings":["Hunan University,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,Changsha,China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9599000215530396,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9599000215530396,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9473000168800354,"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/T10028","display_name":"Topic Modeling","score":0.9247000217437744,"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":0.7173439860343933},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6451616287231445},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5619635581970215},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.5506234169006348},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5004246234893799},{"id":"https://openalex.org/keywords/dual-language","display_name":"Dual language","score":0.43644893169403076},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43593528866767883},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.38559582829475403},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3303977847099304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7173439860343933},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6451616287231445},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5619635581970215},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.5506234169006348},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5004246234893799},{"id":"https://openalex.org/C2992540719","wikidata":"https://www.wikidata.org/wiki/Q5310213","display_name":"Dual language","level":2,"score":0.43644893169403076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43593528866767883},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.38559582829475403},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3303977847099304},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1933349210","https://openalex.org/W2194775991","https://openalex.org/W2251512949","https://openalex.org/W2489434015","https://openalex.org/W2606473278","https://openalex.org/W2952524542","https://openalex.org/W2962749469","https://openalex.org/W2963783181","https://openalex.org/W2963800628","https://openalex.org/W2964022527","https://openalex.org/W2964345792","https://openalex.org/W2984121207","https://openalex.org/W2987734933","https://openalex.org/W3034837210","https://openalex.org/W3035268124","https://openalex.org/W3096609285","https://openalex.org/W3110435696","https://openalex.org/W3159619744","https://openalex.org/W3173364567","https://openalex.org/W3213106580","https://openalex.org/W4214490042","https://openalex.org/W4312351586","https://openalex.org/W4312956471","https://openalex.org/W4313145013","https://openalex.org/W4382464354","https://openalex.org/W4386071652","https://openalex.org/W4386076636","https://openalex.org/W4392543666","https://openalex.org/W4404612908","https://openalex.org/W6766673545","https://openalex.org/W6791353385","https://openalex.org/W6797397777","https://openalex.org/W6839220867","https://openalex.org/W6851167519"],"related_works":["https://openalex.org/W2742579949","https://openalex.org/W4385978307","https://openalex.org/W2373862202","https://openalex.org/W2388232445","https://openalex.org/W2221456461","https://openalex.org/W4406992406","https://openalex.org/W4403542013","https://openalex.org/W4307244554","https://openalex.org/W2323798523","https://openalex.org/W4399694420"],"abstract_inverted_index":{"Open-ended":[0],"referring":[1,61,77,104],"expression":[2,78,105],"comprehension":[3],"focuses":[4],"on":[5,130],"locating":[6],"the":[7,20,23,28,76,80,92,103,107,131,135],"text":[8,29],"query":[9,114],"within":[10],"an":[11],"image":[12,81,97,108],"via":[13],"scene":[14,25,38,57,73],"knowledge,":[15,26],"requiring":[16],"complex":[17],"reasoning":[18,66,88],"across":[19],"triplet":[21],"of":[22,137],"image,":[24],"and":[27,59,67,79,89,109],"query.":[30],"However,":[31],"most":[32],"existing":[33,144],"methods":[34],"struggle":[35],"to":[36,95,118,122],"integrate":[37],"knowledge":[39,58,74],"while":[40],"performing":[41],"a":[42,52,113,119,124],"single-object":[43],"prediction.":[44,127],"To":[45],"address":[46],"this":[47],"issue,":[48],"we":[49,70,100],"propose":[50],"VG-DLC,":[51],"model":[53],"that":[54,141],"progressively":[55],"uses":[56],"open-ended":[60,93],"expressions":[62],"as":[63,112],"constraints":[64],"for":[65],"grounding.":[68],"Specifically,":[69],"first":[71],"align":[72,102],"with":[75,106],"in":[82],"sequence,":[83],"which":[84],"supports":[85],"effective":[86],"relational":[87],"implicitly":[90],"constrains":[91],"content":[94],"corresponding":[96],"regions.":[98],"Next,":[99],"explicitly":[101],"employ":[110],"it":[111,117],"vector,":[115],"constraining":[116],"unique":[120],"region":[121],"achieve":[123],"single":[125],"end-to-end":[126,145],"Extensive":[128],"experiments":[129],"SK-VG":[132],"dataset":[133],"validate":[134],"effectiveness":[136],"our":[138],"method,":[139],"demonstrating":[140],"VG-DLC":[142],"outperforms":[143],"approaches.":[146]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}