{"id":"https://openalex.org/W4414760297","doi":"https://doi.org/10.1109/iccv51701.2025.02271","title":"Hybrid-Tower: Fine-Grained Pseudo-Query Interaction and Generation for Text-to-Video Retrieval","display_name":"Hybrid-Tower: Fine-Grained Pseudo-Query Interaction and Generation for Text-to-Video Retrieval","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414760297","doi":"https://doi.org/10.1109/iccv51701.2025.02271"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.04773","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111338575","display_name":"Bangxiang Lan","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bangxiang Lan","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101577090","display_name":"Ruobing Xie","orcid":"https://orcid.org/0000-0003-3170-5647"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruobing Xie","raw_affiliation_strings":["Tencent,Large Language Model Department"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Large Language Model Department","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112894121","display_name":"Ruixiang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruixiang Zhao","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xingwu Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingwu Sun","raw_affiliation_strings":["Tencent,Large Language Model Department"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Large Language Model Department","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020128898","display_name":"Zhanhui Kang","orcid":"https://orcid.org/0009-0006-5151-4222"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanhui Kang","raw_affiliation_strings":["Tencent,Large Language Model Department"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Large Language Model Department","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100300144","display_name":"Yang Gang","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Yang","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060270456","display_name":"Xirong Li","orcid":"https://orcid.org/0000-0002-0220-8310"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xirong Li","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"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":0.22786285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24497","last_page":"24506"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9958999752998352,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9909999966621399,"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/overhead","display_name":"Overhead (engineering)","score":0.5852000117301941},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5782999992370605},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5098000168800354},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4878000020980835},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.482699990272522},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.33320000767707825},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3292999863624573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8300999999046326},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5852000117301941},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5782999992370605},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5098000168800354},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4878000020980835},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.482699990272522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47589999437332153},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3767000138759613},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3440999984741211},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33320000767707825},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30230000615119934},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.04773","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.04773","pdf_url":"https://arxiv.org/pdf/2509.04773","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.04773","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.04773","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.04773","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.04773","pdf_url":"https://arxiv.org/pdf/2509.04773","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"Text-to-Video":[1],"Retrieval":[2],"(T2VR)":[3],"task":[4],"aims":[5],"to":[6,91,109,116,120,143],"retrieve":[7],"unlabeled":[8],"videos":[9],"by":[10],"textual":[11,105,128],"queries":[12],"with":[13,175],"the":[14,30,37,55,58,100,104,117,126,144,148,173,188,199,202],"same":[15],"semantic":[16],"meanings.":[17],"Recent":[18],"CLIP-based":[19],"approaches":[20,119],"have":[21],"explored":[22],"two":[23],"frameworks:":[24],"Two-Tower":[25,59,145,191],"versus":[26],"Single-Tower":[27,61,118],"framework,":[28,62],"yet":[29],"former":[31],"suffers":[32,39],"from":[33,40],"low":[34,41],"effectiveness,":[35,123],"while":[36,193],"latter":[38],"efficiency.":[42,154],"In":[43],"this":[44],"study,":[45],"we":[46],"explore":[47],"a":[48,71,86,93,112,169],"new":[49,87],"Hybrid-Tower":[50,203],"framework":[51,146],"that":[52,165],"can":[53],"hybridize":[54],"advantages":[56,200],"of":[57,107,178,190,201],"and":[60,66,78,103],"achieving":[63,194],"high":[64,122,153],"effectiveness":[65],"efficiency":[67,189],"simultaneously.":[68],"We":[69],"propose":[70],"novel":[72],"hybrid":[73],"method,":[74],"Fine-grained":[75],"Pseudo-query":[76],"Interaction":[77],"Generation":[79],"for":[80,95],"T2VR,":[81],"ie,":[82],"PIG,":[83],"which":[84],"includes":[85],"pseudo-query":[88,94,108],"generator":[89],"designed":[90],"generate":[92],"each":[96],"video.":[97],"This":[98],"enables":[99],"video":[101],"feature":[102],"features":[106],"interact":[110],"in":[111,182],"fine-grained":[113],"manner,":[114],"similar":[115],"hold":[121],"even":[124],"before":[125],"real":[127],"query":[129],"is":[130],"received.":[131],"Simultaneously,":[132],"our":[133,166,185],"method":[134,167,186],"introduces":[135],"no":[136],"additional":[137],"storage":[138],"or":[139],"computational":[140],"overhead":[141],"compared":[142],"during":[147],"inference":[149],"stage,":[150],"thus":[151],"maintaining":[152],"Extensive":[155],"experiments":[156],"on":[157],"five":[158],"commonly":[159],"used":[160],"text-video":[161],"retrieval":[162],"benchmarks":[163],"demonstrate":[164],"achieves":[168],"significant":[170],"improvement":[171],"over":[172],"baseline,":[174],"an":[176],"increase":[177],"$1.6\\%":[179],"\\sim":[180],"3.9\\%$":[181],"R@1.":[183],"Furthermore,":[184],"matches":[187],"models":[192],"near":[195],"state-of-the-art":[196],"performance,":[197],"highlighting":[198],"framework.":[204]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}