{"id":"https://openalex.org/W7128997155","doi":"https://doi.org/10.1109/tip.2026.3663039","title":"MTRAG: Multi-Target Referring and Grounding via Hybrid Semantic-Spatial Integration","display_name":"MTRAG: Multi-Target Referring and Grounding via Hybrid Semantic-Spatial Integration","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7128997155","doi":"https://doi.org/10.1109/tip.2026.3663039","pmid":"https://pubmed.ncbi.nlm.nih.gov/41697816"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3663039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3663039","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5126169696","display_name":"Yili Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112595","display_name":"Research Institute of Petroleum Exploration and Development","ror":"https://ror.org/02awe6g05","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210112595","https://openalex.org/I98227222"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yili Ren","raw_affiliation_strings":["Research Institute of Petroleum Exploration & Development, CNPC, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute of Petroleum Exploration & Development, CNPC, Beijing, China","institution_ids":["https://openalex.org/I4210112595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126085984","display_name":"Jinyang Du","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyang Du","raw_affiliation_strings":["School of Astronautics, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-3201-0832","affiliations":[{"raw_affiliation_string":"School of Astronautics, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126145093","display_name":"Xi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112595","display_name":"Research Institute of Petroleum Exploration and Development","ror":"https://ror.org/02awe6g05","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210112595","https://openalex.org/I98227222"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Liu","raw_affiliation_strings":["Research Institute of Petroleum Exploration & Development, CNPC, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute of Petroleum Exploration & Development, CNPC, Beijing, China","institution_ids":["https://openalex.org/I4210112595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114150575","display_name":"Qianxiao Su","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112595","display_name":"Research Institute of Petroleum Exploration and Development","ror":"https://ror.org/02awe6g05","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210112595","https://openalex.org/I98227222"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianxiao Su","raw_affiliation_strings":["Research Institute of Petroleum Exploration & Development, CNPC, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute of Petroleum Exploration & Development, CNPC, Beijing, China","institution_ids":["https://openalex.org/I4210112595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082404485","display_name":"Yue Deng","orcid":"https://orcid.org/0000-0003-2871-8922"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Deng","raw_affiliation_strings":["Zhongguancun Academy, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2871-8922","affiliations":[{"raw_affiliation_string":"Zhongguancun Academy, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126123298","display_name":"Hongjue Li","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjue Li","raw_affiliation_strings":["School of Astronautics, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0504-2555","affiliations":[{"raw_affiliation_string":"School of Astronautics, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19728054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"2167","last_page":"2181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T10036","display_name":"Advanced Neural Network Applications","score":0.0010999999940395355,"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/T10028","display_name":"Topic Modeling","score":0.0008999999845400453,"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/ground","display_name":"Ground","score":0.7106000185012817},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5059999823570251},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.45339998602867126},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.42489999532699585},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3970000147819519},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3926999866962433},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.38909998536109924},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.374099999666214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7599999904632568},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.7106000185012817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5080999732017517},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.45339998602867126},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42489999532699585},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.29100000858306885},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28220000863075256},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2694000005722046},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2603999972343445},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3663039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3663039","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:41697816","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41697816","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1148451794","display_name":null,"funder_award_id":"2025ZD1401501","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G3569455252","display_name":null,"funder_award_id":"02012503","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G645526940","display_name":null,"funder_award_id":"62325101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6644097784","display_name":null,"funder_award_id":"62405014","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8646810384","display_name":null,"funder_award_id":"42372175","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/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fine-grained":[0],"visual":[1],"referring":[2,48,133,146,171],"and":[3,11,49,74,95,131,134,141,169,172,189],"grounding":[4,50,90,94,114,135,173],"are":[5],"critical":[6],"for":[7,92,155],"enhancing":[8,117],"scene":[9],"understanding":[10],"enabling":[12],"various":[13],"real-world":[14],"vision-language":[15],"applications.":[16],"Although":[17],"recent":[18],"studies":[19],"have":[20],"extended":[21],"multimodal":[22],"large":[23],"language":[24],"models":[25],"(MLLMs)":[26],"to":[27,70,101],"these":[28],"tasks,":[29,166,191],"they":[30],"still":[31],"face":[32],"significant":[33],"challenges":[34],"in":[35],"fine-grained":[36],"multi-target":[37,47,132,145,159,170],"scenarios.":[38],"To":[39],"address":[40],"this,":[41],"we":[42,57,87,123],"propose":[43],"MTRAG,":[44],"a":[45,59,66,89,97,127,153],"pixel-level":[46,93],"framework":[51],"that":[52,64,180],"leverages":[53],"semantic-spatial":[54,119],"collaboration.":[55],"Specifically,":[56],"introduce":[58,88],"Channel":[60],"Extension":[61],"Mechanism":[62],"(CEM)":[63],"enables":[65],"global":[67,72],"image":[68],"encoder":[69],"extract":[71],"semantics":[73],"multi-region":[75],"representations":[76],"while":[77,192],"retaining":[78],"background":[79],"context,":[80],"without":[81],"extra":[82],"region":[83],"feature":[84],"extractors.":[85],"Moreover,":[86],"branch":[91,108],"design":[96],"Hybrid":[98],"Adapter":[99],"(HA)":[100],"fuse":[102],"semantic":[103],"features":[104],"from":[105,112,138],"the":[106,113,118],"MLLM":[107],"with":[109],"spatial":[110],"information":[111],"branch,":[115],"thereby":[116],"alignment.":[120],"For":[121],"training,":[122],"meticulously":[124],"curate":[125],"MTRAG-D,":[126],"dataset":[128],"comprising":[129],"single-":[130,168],"samples":[136],"derived":[137],"existing":[139],"datasets":[140],"newly":[142],"synthesized":[143],"free-form":[144],"instruction-following":[147],"data.":[148],"We":[149],"also":[150],"present":[151],"MTR-Bench,":[152],"benchmark":[154],"systematic":[156],"evaluation":[157],"of":[158],"referring.":[160],"Extensive":[161],"experiments":[162],"across":[163],"five":[164],"core":[165],"including":[167],"as":[174,176],"well":[175],"image-level":[177,195],"captioning,":[178],"show":[179],"MTRAG":[181],"consistently":[182],"outperforms":[183],"strong":[184],"baselines":[185],"on":[186],"both":[187],"multi-":[188],"single-target":[190],"maintaining":[193],"competitive":[194],"understanding.":[196],"The":[197],"code":[198],"is":[199],"available":[200],"at":[201],"https://github.com/deng-ai-lab/MTRAG.":[202]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-17T00:00:00"}