{"id":"https://openalex.org/W4406983459","doi":"https://doi.org/10.1109/tmm.2025.3535345","title":"Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive Position Correction for Visual Grounding","display_name":"Phrase Decoupling Cross-Modal Hierarchical Matching and Progressive Position Correction for Visual Grounding","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406983459","doi":"https://doi.org/10.1109/tmm.2025.3535345"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3535345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535345","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/A5102220089","display_name":"Minghong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghong Xie","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0001-9051-9612","affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mengzhao Wang","orcid":"https://orcid.org/0009-0003-5717-5290"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengzhao Wang","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":"https://orcid.org/0009-0003-5717-5290","affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080535168","display_name":"Huafeng Li","orcid":"https://orcid.org/0000-0003-2462-6174"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huafeng Li","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0003-2462-6174","affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005210261","display_name":"Yafei Zhang","orcid":"https://orcid.org/0000-0003-2347-5642"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yafei Zhang","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0003-2347-5642","affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067600725","display_name":"Dapeng Tao","orcid":"https://orcid.org/0000-0003-0783-5273"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dapeng Tao","raw_affiliation_strings":["FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0003-0783-5273","affiliations":[{"raw_affiliation_string":"FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhengtao Yu","orcid":"https://orcid.org/0000-0002-4012-461X"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengtao Yu","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0002-4012-461X","affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8276,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.92970382,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"27","issue":null,"first_page":"3979","last_page":"3991"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9775999784469604,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9775999784469604,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9642999768257141,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9516000151634216,"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":0.7940409183502197},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.7543693780899048},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7219762206077576},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6867017149925232},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49804139137268066},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.45882272720336914},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4584559500217438},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.367901474237442},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3670174777507782},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0880897045135498}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940409183502197},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.7543693780899048},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7219762206077576},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6867017149925232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49804139137268066},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.45882272720336914},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4584559500217438},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.367901474237442},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3670174777507782},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0880897045135498},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3535345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535345","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":[],"awards":[{"id":"https://openalex.org/G6545507832","display_name":null,"funder_award_id":"62276120","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2006147162","https://openalex.org/W2194775991","https://openalex.org/W2251512949","https://openalex.org/W2463955103","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2770129969","https://openalex.org/W2946086442","https://openalex.org/W2949817882","https://openalex.org/W2952524542","https://openalex.org/W2955014993","https://openalex.org/W2960655175","https://openalex.org/W2962766617","https://openalex.org/W2963109634","https://openalex.org/W2963150697","https://openalex.org/W2963341956","https://openalex.org/W2964345792","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2987734933","https://openalex.org/W3006154882","https://openalex.org/W3034772468","https://openalex.org/W3035097537","https://openalex.org/W3093017735","https://openalex.org/W3093314701","https://openalex.org/W3110435696","https://openalex.org/W3138516171","https://openalex.org/W3151130473","https://openalex.org/W3163747765","https://openalex.org/W3173364567","https://openalex.org/W3174004334","https://openalex.org/W3174965650","https://openalex.org/W3186269967","https://openalex.org/W3192448690","https://openalex.org/W3203354307","https://openalex.org/W3207127495","https://openalex.org/W4210820868","https://openalex.org/W4214490042","https://openalex.org/W4221155360","https://openalex.org/W4282968790","https://openalex.org/W4283029876","https://openalex.org/W4285216227","https://openalex.org/W4292828275","https://openalex.org/W4309181071","https://openalex.org/W4309368547","https://openalex.org/W4312341105","https://openalex.org/W4312351586","https://openalex.org/W4312438583","https://openalex.org/W4312906427","https://openalex.org/W4312922092","https://openalex.org/W4313145013","https://openalex.org/W4313184803","https://openalex.org/W4318954130","https://openalex.org/W4322707256","https://openalex.org/W4323897056","https://openalex.org/W4384820618","https://openalex.org/W4385245566","https://openalex.org/W4386065596","https://openalex.org/W4386075498","https://openalex.org/W4386076027","https://openalex.org/W4387272106","https://openalex.org/W4387623721","https://openalex.org/W4387969094","https://openalex.org/W4387969812","https://openalex.org/W4387986753","https://openalex.org/W4390872671","https://openalex.org/W4391070219","https://openalex.org/W6750227808","https://openalex.org/W6752788575","https://openalex.org/W6757817989","https://openalex.org/W6791353385","https://openalex.org/W6849846199"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W4313561376","https://openalex.org/W3103825105","https://openalex.org/W3027880158","https://openalex.org/W3207533102","https://openalex.org/W2021787609","https://openalex.org/W1617565119","https://openalex.org/W160381218","https://openalex.org/W2512958550","https://openalex.org/W1537063595"],"abstract_inverted_index":{"Visual":[0,57],"grounding":[1,18],"has":[2,19],"attracted":[3],"wide":[4],"attention":[5],"thanks":[6],"to":[7,108,164],"its":[8,169,185],"broad":[9],"application":[10],"in":[11,87,117,171],"various":[12],"visual":[13,17],"language":[14],"tasks.":[15],"Although":[16],"made":[20],"significant":[21],"research":[22],"progress,":[23],"existing":[24],"methods":[25],"ignore":[26],"the":[27,31,80,104,113,118,127,132,136,139,143,150,159,165,190,194],"promotion":[28],"effect":[29],"of":[30,82,131,138,142,161],"association":[32,83,151],"between":[33,84,152],"text":[34,71,140],"and":[35,53,69,72,125,157,168,184],"image":[36,73],"features":[37,153,162],"at":[38,154],"different":[39,85,155,180],"hierarchies":[40,86,156],"on":[41,103,179],"cross-modal":[42,88],"matching.":[43,89],"This":[44,120,147],"paper":[45],"proposes":[46],"a":[47,63,70,92],"Phrase":[48],"Decoupling":[49],"Cross-Modal":[50],"Hierarchical":[51],"Matching":[52],"Progressive":[54],"Position":[55],"Correction":[56],"Grounding":[58],"method.":[59],"It":[60],"first":[61],"generates":[62],"mask":[64],"through":[65,182],"decoupled":[66],"sentence":[67],"phrases,":[68],"hierarchical":[74,105],"matching":[75,106],"mechanism":[76,107],"is":[77,100,177,187],"constructed,":[78],"highlighting":[79],"role":[81,160],"In":[90],"addition,":[91],"corresponding":[93],"target":[94,114,133,144,166,172],"object":[95,115,134,145,167],"position":[96,130,170],"progressive":[97],"correction":[98],"strategy":[99],"defined":[101],"based":[102],"achieve":[109],"accurate":[110],"positioning":[111],"for":[112],"described":[116],"text.":[119],"method":[121,176],"can":[122],"continuously":[123],"optimize":[124],"adjust":[126],"bounding":[128],"box":[129],"as":[135],"certainty":[137],"description":[141],"improves.":[146],"design":[148],"explores":[149],"highlights":[158],"related":[163],"positioning.":[173],"The":[174],"proposed":[175],"validated":[178],"datasets":[181],"experiments,":[183],"superiority":[186],"verified":[188],"by":[189],"performance":[191],"comparison":[192],"with":[193],"state-of-the-art":[195],"methods.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
