{"id":"https://openalex.org/W4292828074","doi":"https://doi.org/10.1109/cvprw56347.2022.00540","title":"Cross-modal Target Retrieval for Tracking by Natural Language","display_name":"Cross-modal Target Retrieval for Tracking by Natural Language","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W4292828074","doi":"https://doi.org/10.1109/cvprw56347.2022.00540"},"language":"en","primary_location":{"id":"doi:10.1109/cvprw56347.2022.00540","doi":"https://doi.org/10.1109/cvprw56347.2022.00540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw56347.2022.00540","pdf_url":null,"source":{"id":"https://openalex.org/S4363607748","display_name":"IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5100630215","display_name":"Yihao Li","orcid":"https://orcid.org/0009-0001-3318-0429","observed_orcids":["https://orcid.org/0009-0001-3318-0429"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihao Li","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048818071","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0002-3197-8103","observed_orcids":["https://orcid.org/0000-0002-3197-8103","https://orcid.org/0009-0002-6350-2844"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070529355","display_name":"Zhongpeng Cai","orcid":"https://orcid.org/0000-0002-2540-3215","observed_orcids":["https://orcid.org/0000-0002-2540-3215"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongpeng Cai","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101708528","display_name":"Yuwen Pan","orcid":"https://orcid.org/0000-0003-2219-0717","observed_orcids":["https://orcid.org/0000-0003-2219-0717"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwen Pan","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":4.1978,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.95902857,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4927","last_page":"4936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9814000129699707,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9814000129699707,"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":0.0038999998942017555,"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":0.002400000113993883,"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/cross-modal-retrieval","display_name":"cross-modal retrieval","score":0.8640000224113464},{"id":"https://openalex.org/keywords/visual-tracking","display_name":"visual object tracking","score":0.6800000071525574},{"id":"https://openalex.org/keywords/cross-attention","display_name":"cross-attention","score":0.8989999890327454},{"id":"https://openalex.org/keywords/proposal-selection","display_name":"proposal selection","score":0.7850000262260437},{"id":"https://openalex.org/keywords/appearance-variation","display_name":"appearance variation","score":0.45100000500679016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.850289523601532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5927971005439758},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5771751403808594},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5472100973129272},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.47184017300605774},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46189677715301514},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.4152725636959076},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.33792564272880554},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3223830461502075},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11272639036178589},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1050860583782196}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvprw56347.2022.00540","doi":"https://doi.org/10.1109/cvprw56347.2022.00540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw56347.2022.00540","pdf_url":null,"source":{"id":"https://openalex.org/S4363607748","display_name":"IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1924770834","https://openalex.org/W1955514522","https://openalex.org/W2106277773","https://openalex.org/W2470394683","https://openalex.org/W2476034201","https://openalex.org/W2565639579","https://openalex.org/W2626778328","https://openalex.org/W2747053578","https://openalex.org/W2774267535","https://openalex.org/W2799058067","https://openalex.org/W2886904239","https://openalex.org/W2891033863","https://openalex.org/W2896457183","https://openalex.org/W2900474539","https://openalex.org/W2954672622","https://openalex.org/W2962964995","https://openalex.org/W2963467339","https://openalex.org/W2963534981","https://openalex.org/W2968124245","https://openalex.org/W2970231061","https://openalex.org/W2970608575","https://openalex.org/W2975501350","https://openalex.org/W2981851019","https://openalex.org/W2985509612","https://openalex.org/W2987734933","https://openalex.org/W2993231436","https://openalex.org/W2998356391","https://openalex.org/W3010072143","https://openalex.org/W3010277541","https://openalex.org/W3035265375","https://openalex.org/W3049478012","https://openalex.org/W3094502228","https://openalex.org/W3106542916","https://openalex.org/W3110846182","https://openalex.org/W3116952214","https://openalex.org/W3133524129","https://openalex.org/W3142630836","https://openalex.org/W3144314306","https://openalex.org/W3156978626","https://openalex.org/W3173871266","https://openalex.org/W3173909648","https://openalex.org/W3174812960","https://openalex.org/W3175823695","https://openalex.org/W3175888430","https://openalex.org/W3181069167","https://openalex.org/W3195373975","https://openalex.org/W3204484221","https://openalex.org/W4210278717"],"related_works":["https://openalex.org/W4409683198","https://openalex.org/W2747053578","https://openalex.org/W4294723943","https://openalex.org/W4393399176","https://openalex.org/W4416380338","https://openalex.org/W3010072143","https://openalex.org/W4381735302","https://openalex.org/W4417267315","https://openalex.org/W3181069167","https://openalex.org/W7166726148"],"abstract_inverted_index":{"Tracking":[0],"by":[1,22],"natural":[2],"language":[3,30],"specification":[4,31],"in":[5,12,26,138],"a":[6,9,33,59,70,79],"video":[7],"is":[8],"challenging":[10],"task":[11],"computer":[13],"vision.":[14],"Distinct":[15],"from":[16,63,90],"initializing":[17],"the":[18,23,27,50,64,91,95,99,126,130,135,139,160],"target":[19,100,137],"state":[20],"only":[21],"bounding":[24],"box":[25],"first":[28],"frame,":[29],"has":[32],"strong":[34],"potential":[35],"to":[36,41],"assist":[37],"visual":[38,92],"object":[39],"trackers":[40],"capture":[42],"appearance":[43],"variation":[44],"and":[45,78,94,110,121,149,162],"eliminate":[46],"semantic":[47],"ambiguity":[48],"of":[49,66,98,164],"tracked":[51],"object.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"carefully":[57],"design":[58],"unified":[60],"local-global-search":[61],"framework":[62],"perspective":[65],"cross-modal":[67],"retrieval,":[68],"including":[69],"local":[71,119],"tracker,":[72],"an":[73,115,143],"adaptive":[74,84],"retrieval":[75,81,85,132],"switch":[76,86,117],"module,":[77],"target-specific":[80,131],"module.":[82],"The":[83],"module":[87,133],"aligns":[88],"semantics":[89],"signal":[93],"lingual":[96],"description":[97],"using":[101],"three":[102,156],"sub-modules,":[103],"i.e.,":[104],"object-aware":[105],"attention":[106],"memory,":[107],"part-aware":[108],"cross-attention,":[109],"vision-language":[111,145],"contrast,":[112],"which":[113],"achieve":[114],"automatic":[116],"between":[118],"search":[120,128],"global":[122,127],"search.":[123],"When":[124],"booting":[125],"mechanism,":[129],"re-localizes":[134],"missing":[136],"image-wide":[140],"range":[141],"via":[142],"efficient":[144],"guided":[146],"proposal":[147],"selector":[148],"target-text":[150],"match.":[151],"Numerous":[152],"experimental":[153],"results":[154],"on":[155],"prevailing":[157],"benchmarks":[158],"show":[159],"effectiveness":[161],"generalization":[163],"our":[165],"framework.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":17},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":3}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2022-08-24T00:00:00"}