{"id":"https://openalex.org/W7154592740","doi":"https://doi.org/10.1109/tcsvt.2026.3684576","title":"Text-Guided Vision Token Reduction With Low-Rank Adaptation for Efficient Visual Grounding","display_name":"Text-Guided Vision Token Reduction With Low-Rank Adaptation for Efficient Visual Grounding","publication_year":2026,"publication_date":"2026-04-16","ids":{"openalex":"https://openalex.org/W7154592740","doi":"https://doi.org/10.1109/tcsvt.2026.3684576"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3684576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3684576","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5046443025","display_name":"Liangtao Shi","orcid":"https://orcid.org/0009-0003-5934-8837"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangtao Shi","raw_affiliation_strings":["Hefei University of Technology"],"raw_orcid":"https://orcid.org/0009-0003-5934-8837","affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114244599","display_name":"Ting Liu","orcid":"https://orcid.org/0000-0003-2597-3020"},"institutions":[{"id":"https://openalex.org/I118612203","display_name":"Hunan Police Academy","ror":"https://ror.org/02gh10772","country_code":"CN","type":"education","lineage":["https://openalex.org/I118612203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Liu","raw_affiliation_strings":["Hunan Police College"],"raw_orcid":"https://orcid.org/0000-0003-2597-3020","affiliations":[{"raw_affiliation_string":"Hunan Police College","institution_ids":["https://openalex.org/I118612203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102596873","display_name":"Jinxia Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxia Xie","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100773117","display_name":"Ning Li","orcid":"https://orcid.org/0009-0006-3867-6753"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Li","raw_affiliation_strings":["Guangxi Normal University"],"raw_orcid":"https://orcid.org/0009-0006-3867-6753","affiliations":[{"raw_affiliation_string":"Guangxi Normal University","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058101262","display_name":"Bineng Zhong","orcid":"https://orcid.org/0000-0003-3423-1539"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bineng Zhong","raw_affiliation_strings":["Guangxi Normal University"],"raw_orcid":"https://orcid.org/0000-0003-3423-1539","affiliations":[{"raw_affiliation_string":"Guangxi Normal University","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051332325","display_name":"Richang Hong","orcid":"https://orcid.org/0000-0001-5461-3986"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richang Hong","raw_affiliation_strings":["Hefei University of Technology"],"raw_orcid":"https://orcid.org/0000-0001-5461-3986","affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.41758639,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"8","first_page":"11391","last_page":"11401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3292999863624573,"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":0.3292999863624573,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.12380000203847885,"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/T11019","display_name":"Image Enhancement Techniques","score":0.0820000022649765,"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/adaptation","display_name":"Adaptation (eye)","score":0.5375999808311462},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5292999744415283},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.498199999332428},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.35989999771118164},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.3447999954223633},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.33169999718666077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.746399998664856},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6638000011444092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6416000127792358},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5375999808311462},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5292999744415283},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3142000138759613},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3684576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3684576","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5586753922","display_name":null,"funder_award_id":"U23B2031","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2489434015","https://openalex.org/W2946086442","https://openalex.org/W2950697717","https://openalex.org/W2962766617","https://openalex.org/W2963109634","https://openalex.org/W2963351448","https://openalex.org/W2964284374","https://openalex.org/W2984121207","https://openalex.org/W2987734933","https://openalex.org/W3096719817","https://openalex.org/W3110435696","https://openalex.org/W3192448690","https://openalex.org/W3207127495","https://openalex.org/W4210820868","https://openalex.org/W4214490042","https://openalex.org/W4309181071","https://openalex.org/W4312351586","https://openalex.org/W4312651322","https://openalex.org/W4312751983","https://openalex.org/W4320036901","https://openalex.org/W4360993849","https://openalex.org/W4382119472","https://openalex.org/W4384820618","https://openalex.org/W4386071687","https://openalex.org/W4386076636","https://openalex.org/W4386212341","https://openalex.org/W4387272106","https://openalex.org/W4387623721","https://openalex.org/W4387986753","https://openalex.org/W4388266798","https://openalex.org/W4389331817","https://openalex.org/W4389352357","https://openalex.org/W4389890864","https://openalex.org/W4393159185","https://openalex.org/W4395064954","https://openalex.org/W4396505863","https://openalex.org/W4399205998","https://openalex.org/W4400679250","https://openalex.org/W4402704627","https://openalex.org/W4402716271","https://openalex.org/W4402728160","https://openalex.org/W4402979572","https://openalex.org/W4403917938","https://openalex.org/W4404562751","https://openalex.org/W4404783315","https://openalex.org/W4407449407","https://openalex.org/W4408564121","https://openalex.org/W4409128969","https://openalex.org/W4409346410","https://openalex.org/W4409366756","https://openalex.org/W4412984943","https://openalex.org/W4415444078","https://openalex.org/W4415540593","https://openalex.org/W4415795571","https://openalex.org/W4415800512","https://openalex.org/W4416011362","https://openalex.org/W7133219196"],"related_works":[],"abstract_inverted_index":{"Transformer-based":[0],"pretrained":[1],"models":[2,189],"have":[3,27],"advanced":[4],"Visual":[5],"Grounding":[6],"(VG)":[7],"significantly,":[8],"but":[9],"their":[10],"scaling":[11],"up":[12],"has":[13],"caused":[14],"soaring":[15],"training":[16,29],"and":[17,78,86,92,115,158,188],"inference":[18,34],"costs.":[19],"While":[20],"efforts":[21],"adapting":[22],"Parameter-Efficient":[23],"Fine-Tuning":[24],"to":[25,31,76,111],"VG":[26,104],"cut":[28],"expenses":[30],"some":[32],"extent,":[33],"costs":[35,42],"are":[36,190],"over-looked,":[37],"stemming":[38],"from":[39],"Transformer\u2019s":[40],"computation":[41],"growing":[43],"quadratically":[44],"with":[45,98,183],"input":[46],"token":[47,58,85,110,118],"length.":[48],"To":[49],"address":[50],"the":[51,80,95,116,134,141,148,155,180],"above":[52],"challenge,":[53],"we":[54],"propose":[55],"a":[56,63,107],"text-guided":[57],"prune":[59],"method":[60],"based":[61],"on":[62,120,166],"one-stream":[64],"architecture":[65],"for":[66],"VG,":[67,77],"named":[68],"OneSVG.":[69],"Specifically,":[70],"OneSVG":[71,145,173],"transfers":[72],"low-rank":[73],"adaptation":[74],"LoRA":[75],"calculates":[79],"relevance":[81],"between":[82],"each":[83],"vision":[84,96,122,130,162],"text":[87],"semantics":[88],"in":[89,144],"multiple":[90],"stages,":[91],"gradually":[93],"prunes":[94],"tokens":[97,123,131],"low":[99],"relevance.":[100],"In":[101],"addition,":[102],"traditional":[103],"methods":[105],"use":[106],"single":[108],"[REG]":[109,117],"predict":[112],"bounding":[113],"boxes,":[114],"relies":[119],"complete":[121,161],"during":[124],"training,":[125],"pruning":[126],"large":[127],"number":[128],"of":[129,138,151],"will":[132],"disrupt":[133],"spatial":[135],"orientation":[136],"information":[137],"images.":[139],"Therefore,":[140],"prediction":[142],"head":[143],"first":[146],"restores":[147],"square":[149],"structure":[150],"images":[152],"by":[153],"padding":[154],"missing":[156],"area,":[157],"then":[159],"accepts":[160],"tokens.":[163,186],"Experimental":[164],"results":[165],"three":[167],"widely-used":[168],"benchmarks":[169],"demonstrate":[170],"that":[171],"our":[172],"achieves":[174],"state-of-the-art":[175],"real-time":[176],"speed":[177],"while":[178],"maintaining":[179],"best":[181],"accuracy":[182],"only":[184],"34.3%":[185],"Codes":[187],"available":[191],"at":[192],"https://github.com/ltShi/OneSVG.":[193]},"counts_by_year":[],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-04-17T00:00:00"}