{"id":"https://openalex.org/W4408355228","doi":"https://doi.org/10.1109/icassp49660.2025.10888064","title":"Enhancing Vision-Language Tracking by Effectively Converting Textual Cues into Visual Cues","display_name":"Enhancing Vision-Language Tracking by Effectively Converting Textual Cues into Visual Cues","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355228","doi":"https://doi.org/10.1109/icassp49660.2025.10888064"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888064","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":"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/A5088002825","display_name":"Xiaokun Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaokun Feng","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077385545","display_name":"Dailing Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dailing Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050320530","display_name":"Shiyu Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shiyu Hu","raw_affiliation_strings":["Nanyang Technological University,School of Physical and Mathematical Sciences,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Physical and Mathematical Sciences,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102674051","display_name":"Xuchen Li","orcid":"https://orcid.org/0009-0009-2565-8857"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuchen Li","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101480388","display_name":"Meiqi Wu","orcid":"https://orcid.org/0009-0007-3155-4013"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meiqi Wu","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066905801","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0002-5230-6285"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047010855","display_name":"Xiaotang Chen","orcid":"https://orcid.org/0000-0002-3362-1431"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaotang Chen","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028693655","display_name":"Kaiqi Huang","orcid":"https://orcid.org/0000-0002-2677-9273"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiqi Huang","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5088002825"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":2.1734,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84216077,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.8859000205993652,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.8859000205993652,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sensory-cue","display_name":"Sensory cue","score":0.7104562520980835},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7016373872756958},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6165242195129395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5328009128570557},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4925094544887543},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4877079427242279},{"id":"https://openalex.org/keywords/cue-dependent-forgetting","display_name":"Cue-dependent forgetting","score":0.42594775557518005},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3856753706932068},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.17883804440498352},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16253769397735596}],"concepts":[{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.7104562520980835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7016373872756958},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6165242195129395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5328009128570557},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4925094544887543},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4877079427242279},{"id":"https://openalex.org/C94905562","wikidata":"https://www.wikidata.org/wiki/Q5192551","display_name":"Cue-dependent forgetting","level":2,"score":0.42594775557518005},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3856753706932068},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.17883804440498352},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16253769397735596},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888064","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"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":37,"referenced_works":["https://openalex.org/W2089961441","https://openalex.org/W2747053578","https://openalex.org/W2891033863","https://openalex.org/W3010072143","https://openalex.org/W3106542916","https://openalex.org/W3173871266","https://openalex.org/W3181069167","https://openalex.org/W4213433014","https://openalex.org/W4214490042","https://openalex.org/W4292828074","https://openalex.org/W4312751983","https://openalex.org/W4312956471","https://openalex.org/W4321766229","https://openalex.org/W4381735302","https://openalex.org/W4385245566","https://openalex.org/W4385569741","https://openalex.org/W4386075643","https://openalex.org/W4387731016","https://openalex.org/W4387969322","https://openalex.org/W4389272328","https://openalex.org/W4390193015","https://openalex.org/W4390889789","https://openalex.org/W4392902794","https://openalex.org/W4393147957","https://openalex.org/W4396505919","https://openalex.org/W4402704627","https://openalex.org/W4402716476","https://openalex.org/W4402728032","https://openalex.org/W4402753915","https://openalex.org/W4402754150","https://openalex.org/W4402916152","https://openalex.org/W4404612908","https://openalex.org/W6755207826","https://openalex.org/W6771096273","https://openalex.org/W6839144149","https://openalex.org/W6870712020","https://openalex.org/W6874936447"],"related_works":["https://openalex.org/W2883194850","https://openalex.org/W4226067995","https://openalex.org/W2073738997","https://openalex.org/W2741747843","https://openalex.org/W3181765726","https://openalex.org/W2123569203","https://openalex.org/W2158358583","https://openalex.org/W4251654301","https://openalex.org/W2004403995","https://openalex.org/W2736115503"],"abstract_inverted_index":{"Vision-Language":[0],"Tracking":[1],"(VLT)":[2],"aims":[3],"to":[4,40,82,120],"localize":[5],"a":[6,12,52,87],"target":[7,97],"in":[8],"video":[9],"sequences":[10],"using":[11],"visual":[13,75],"template":[14],"and":[15,139],"language":[16],"description.":[17],"While":[18],"textual":[19,71,88,94],"cues":[20,72,95],"enhance":[21],"tracking":[22,122],"potential,":[23],"current":[24],"datasets":[25],"typically":[26],"contain":[27],"much":[28],"more":[29,123],"image":[30,119],"data":[31],"than":[32],"text,":[33],"limiting":[34],"the":[35,42,60,102,106,109,117,131,141],"ability":[36],"of":[37,65,133,143],"VLT":[38],"methods":[39],"align":[41],"two":[43],"modalities":[44],"effectively.":[45,124],"To":[46],"address":[47],"this":[48],"imbalance,":[49],"we":[50,85],"propose":[51],"novel":[53],"plug-and-play":[54],"method":[55,145],"named":[56],"CTVLT":[57,69],"that":[58,92],"leverages":[59],"strong":[61],"text-image":[62],"alignment":[63],"capabilities":[64],"foundation":[66],"grounding":[67],"models.":[68],"converts":[70],"into":[73,96],"interpretable":[74],"heatmaps,":[76,99],"which":[77],"are":[78],"easier":[79],"for":[80,146],"trackers":[81],"process.":[83],"Specifically,":[84],"design":[86],"cue":[89],"mapping":[90],"module":[91,112],"transforms":[93],"distribution":[98],"visually":[100],"representing":[101],"location":[103],"described":[104],"by":[105],"text.":[107],"Additionally,":[108],"heatmap":[110],"guidance":[111],"fuses":[113],"these":[114],"heatmaps":[115],"with":[116],"search":[118],"guide":[121],"Extensive":[125],"experiments":[126],"on":[127],"mainstream":[128],"benchmarks":[129],"demonstrate":[130],"effectiveness":[132],"our":[134,144],"approach,":[135],"achieving":[136],"state-of-the-art":[137],"performance":[138],"validating":[140],"utility":[142],"enhanced":[147],"VLT.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}