{"id":"https://openalex.org/W7128543721","doi":"https://doi.org/10.1145/3796721","title":"Resilient Semantic Pseudo-Text Embedding for Zero-Shot Video Moment Retrieval","display_name":"Resilient Semantic Pseudo-Text Embedding for Zero-Shot Video Moment Retrieval","publication_year":2026,"publication_date":"2026-02-10","ids":{"openalex":"https://openalex.org/W7128543721","doi":"https://doi.org/10.1145/3796721"},"language":"en","primary_location":{"id":"doi:10.1145/3796721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3796721","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5101658131","display_name":"Donglin Zhang","orcid":"https://orcid.org/0000-0002-0716-0918"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Donglin Zhang","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China and Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, United Kingdom of Great Britain and Northern Ireland"],"raw_orcid":"https://orcid.org/0000-0002-0716-0918","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China and Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Weixiang Shi","orcid":"https://orcid.org/0009-0008-6242-7970"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixiang Shi","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0009-0008-6242-7970","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125580157","display_name":"Xiao-jun Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Jun Wu","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0009-0000-0199-5001","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016045863","display_name":"J. Kittler","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Josef Kittler","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, United Kingdom of Great Britain and Northern Ireland"],"raw_orcid":"https://orcid.org/0000-0002-8110-9205","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.6924,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97778974,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"22","issue":"4","first_page":"1","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8314999938011169,"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":0.8314999938011169,"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/T11439","display_name":"Video Analysis and Summarization","score":0.07289999723434448,"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":0.04800000041723251,"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/embedding","display_name":"Embedding","score":0.6758000254631042},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6427000164985657},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.5760999917984009},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.49709999561309814},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4406999945640564},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3366999924182892},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3285999894142151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9146999716758728},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6758000254631042},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6427000164985657},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.5760999917984009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5547999739646912},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.49709999561309814},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4406999945640564},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3366999924182892},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30630001425743103},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3052999973297119},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.289000004529953},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C108801101","wikidata":"https://www.wikidata.org/wiki/Q15032","display_name":"Steganography","level":3,"score":0.2750000059604645},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26820001006126404},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3796721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3796721","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4692016002","display_name":null,"funder_award_id":"62202204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G75458426","display_name":null,"funder_award_id":"JUSRP123032","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1977556410","https://openalex.org/W2897091983","https://openalex.org/W2963017553","https://openalex.org/W2963524571","https://openalex.org/W2963916161","https://openalex.org/W2963919999","https://openalex.org/W2964089981","https://openalex.org/W2997429269","https://openalex.org/W3035339529","https://openalex.org/W3160105412","https://openalex.org/W3162694035","https://openalex.org/W3183800903","https://openalex.org/W3186995366","https://openalex.org/W3198985204","https://openalex.org/W3211076469","https://openalex.org/W4212848270","https://openalex.org/W4224314500","https://openalex.org/W4304091802","https://openalex.org/W4309756585","https://openalex.org/W4312402470","https://openalex.org/W4387968586","https://openalex.org/W4390873056","https://openalex.org/W4391941517","https://openalex.org/W4400810332","https://openalex.org/W4400892527","https://openalex.org/W4403792095"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,54,64,69,76,130,140,169],"explosive":[2],"growth":[3],"of":[4,41,78,96,142,172],"video":[5,7],"data,":[6,66],"moment":[8],"retrieval":[9],"(VMR)":[10],"has":[11],"attracted":[12],"increasing":[13],"attention":[14],"due":[15],"to":[16,19,50,99],"its":[17,188],"ability":[18],"localize":[20],"semantically":[21,101,145],"relevant":[22],"moments":[23],"in":[24,57],"untrimmed":[25],"videos.":[26],"However,":[27],"existing":[28,184],"VMR":[29],"approaches":[30],"usually":[31],"rely":[32],"on":[33,176],"annotated":[34],"video-text":[35],"correspondences":[36],"or":[37],"temporal":[38],"annotations,":[39],"both":[40],"which":[42],"require":[43],"significant":[44],"human":[45],"effort":[46],"and":[47,84,122,135,144,157,178],"are":[48],"costly":[49],"scale.":[51],"Even":[52],"worse,":[53],"inherent":[55],"subjectivity":[56],"manual":[58],"labeling":[59],"often":[60],"introduces":[61,162],"inconsistencies":[62],"into":[63,119],"training":[65],"further":[67],"complicating":[68],"issue.":[70],"In":[71],"this":[72],"article,":[73],"we":[74],"investigate":[75],"problem":[77],"Zero-Shot":[79],"Video":[80],"Moment":[81],"Retrieval":[82],"(ZS-VMR)":[83],"develop":[85],"a":[86,163],"novel":[87],"method,":[88],"Resilient":[89],"Semantic":[90],"Pseudo-Text":[91],"Modeling":[92],"(RSPT).":[93],"The":[94],"core":[95],"RSPT":[97,110,161,182],"is":[98,191],"construct":[100],"rich":[102],"pseudo-text":[103],"embeddings":[104],"through":[105],"visually":[106],"guided":[107],"perturbations.":[108],"Specifically,":[109],"first":[111],"generates":[112],"initial":[113],"pseudo-texts":[114,134],"by":[115,128],"injecting":[116],"random":[117],"noise":[118,126],"visual":[120,136,155],"features":[121],"then":[123],"learns":[124],"adaptive":[125],"weights":[127],"modeling":[129],"correlations":[131],"between":[132],"these":[133],"features.":[137],"This":[138],"enables":[139],"generation":[141],"diverse":[143],"aligned":[146],"representations":[147],"from":[148],"multiple":[149],"perspectives.":[150],"To":[151],"ensure":[152],"alignment":[153],"with":[154],"semantics":[156],"suppress":[158],"irrelevant":[159],"noise,":[160],"quality-aware":[164],"contrastive":[165],"loss":[166],"that":[167,181],"regularizes":[168],"semantic":[170],"boundaries":[171],"pseudo-texts.":[173],"Extensive":[174],"experiments":[175],"Charades-STA":[177],"ActivityNet-Captions":[179],"show":[180],"outperforms":[183],"competitive":[185],"baselines,":[186],"validating":[187],"efficacy.":[189],"Code":[190],"available":[192],"at":[193],"https://github.com/dmcsy/RSPT":[194],".":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-11T00:00:00"}