{"id":"https://openalex.org/W4403851900","doi":"https://doi.org/10.1109/wacv61042.2026.00095","title":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","display_name":"Saliency-Guided DETR for Moment Retrieval and Highlight Detection","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4403851900","doi":"https://doi.org/10.1109/wacv61042.2026.00095"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.01615","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Aleksandr Gordeev","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099368","display_name":"Puglia Salute","ror":"https://ror.org/00jrmky87","country_code":"IT","type":"healthcare","lineage":["https://openalex.org/I4210099368","https://openalex.org/I4210117053"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Aleksandr Gordeev","raw_affiliation_strings":["SALUTEDEV LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SALUTEDEV LLC","institution_ids":["https://openalex.org/I4210099368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043851029","display_name":"Vladimir Dokholyan","orcid":"https://orcid.org/0000-0001-7143-8657"},"institutions":[{"id":"https://openalex.org/I4210099368","display_name":"Puglia Salute","ror":"https://ror.org/00jrmky87","country_code":"IT","type":"healthcare","lineage":["https://openalex.org/I4210099368","https://openalex.org/I4210117053"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Vladimir Dokholyan","raw_affiliation_strings":["SALUTEDEV LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SALUTEDEV LLC","institution_ids":["https://openalex.org/I4210099368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051942642","display_name":"Irina Tolstykh","orcid":"https://orcid.org/0000-0001-9619-5399"},"institutions":[{"id":"https://openalex.org/I4210099368","display_name":"Puglia Salute","ror":"https://ror.org/00jrmky87","country_code":"IT","type":"healthcare","lineage":["https://openalex.org/I4210099368","https://openalex.org/I4210117053"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Irina Tolstykh","raw_affiliation_strings":["SALUTEDEV LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SALUTEDEV LLC","institution_ids":["https://openalex.org/I4210099368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092449823","display_name":"Maksim Kuprashevich","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099368","display_name":"Puglia Salute","ror":"https://ror.org/00jrmky87","country_code":"IT","type":"healthcare","lineage":["https://openalex.org/I4210099368","https://openalex.org/I4210117053"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Maksim Kuprashevich","raw_affiliation_strings":["SALUTEDEV LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SALUTEDEV LLC","institution_ids":["https://openalex.org/I4210099368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210099368"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.00326496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"907","last_page":"916"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9524999856948853,"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":0.9524999856948853,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9217000007629395,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/moment","display_name":"Moment (physics)","score":0.6197079420089722},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43313995003700256},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4094989001750946},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33300864696502686},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10819604992866516}],"concepts":[{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.6197079420089722},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43313995003700256},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4094989001750946},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33300864696502686},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10819604992866516},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/wacv61042.2026.00095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.01615","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.01615","pdf_url":"https://arxiv.org/pdf/2410.01615","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2410.01615","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:share.osf.io:4e6b33bd-6312-4274-9964-c7ade761d4af","is_oa":true,"landing_page_url":"https://osf.io/9e6un","pdf_url":null,"source":{"id":"https://openalex.org/S4306401127","display_name":"OSF Preprints (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.48550/arxiv.2410.01615","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.01615","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.01615","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.01615","pdf_url":"https://arxiv.org/pdf/2410.01615","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":"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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403851900.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"With":[0],"the":[1,8,150,153,174,179],"rapid":[2],"growth":[3],"of":[4,152,178],"video":[5,44,56,69,80],"content":[6],"available,":[7],"ability":[9],"to":[10,38,46,64,99],"search":[11],"for":[12,48,55,83,137,181],"specific":[13,40],"moments":[14],"within":[15],"videos":[16],"using":[17],"textual":[18],"queries":[19],"has":[20],"become":[21],"increasingly":[22],"relevant.":[23],"This":[24],"is":[25],"crucial":[26],"in":[27,42,184],"many":[28],"scenarios,":[29],"from":[30],"surveillance":[31],"cameras":[32],"where":[33],"it":[34],"may":[35],"be":[36,195],"necessary":[37],"find":[39],"events":[41],"extensive":[43],"streams":[45],"searching":[47],"exciting":[49],"movie":[50],"scenes.":[51],"However,":[52],"existing":[53],"approaches":[54],"Moment":[57],"Retrieval":[58],"and":[59,68,111,143,165,176,187,192],"Highlight":[60],"Detection":[61],"often":[62],"struggle":[63],"effectively":[65],"align":[66],"text":[67],"features,":[70],"limiting":[71],"their":[72],"performance.":[73],"We":[74,90],"argue":[75],"that":[76,95],"utilizing":[77],"recent":[78],"foundational":[79],"models":[81,98],"designed":[82,136],"video-text":[84],"alignment":[85],"can":[86],"overcome":[87],"these":[88],"limitations.":[89],"propose":[91],"a":[92,112,131,138],"novel":[93,106],"architecture":[94],"utilizes":[96],"such":[97],"test":[100],"this":[101],"hypothesis.":[102],"Combined":[103],"with":[104,145],"our":[105,116,125],"Saliency-Guided":[107],"Cross":[108],"Attention":[109],"mechanism":[110],"hybrid":[113],"DETR":[114],"architecture,":[115],"approach":[117],"provides":[118],"significantly":[119],"improved":[120],"results.":[121],"To":[122],"further":[123],"enhance":[124],"approach,":[126,154],"we":[127],"developed":[128],"InterVid-MR":[129],"\u2014":[130],"large-scale,":[132],"high-quality":[133],"dataset":[134,191],"specifically":[135],"pretraining":[139],"stage.":[140],"Extensive":[141],"experiments":[142],"comparisons":[144],"current":[146],"state-of-the-art":[147],"methods":[148],"confirm":[149],"effectiveness":[151],"achieving":[155],"58.8":[156],"mAP":[157],"on":[158,163,169],"QVHighlights,":[159],"60.7":[160],"R@1":[161,167],"mIoU":[162,168],"Charades-STA,":[164],"42.4":[166],"TACoS.":[170],"These":[171],"results":[172],"highlight":[173],"efficiency":[175],"scalability":[177],"method":[180],"video-language":[182],"tasks":[183],"both":[185],"zero-shot":[186],"fine-tuning":[188],"scenarios.":[189],"The":[190],"code":[193],"will":[194],"publicly":[196],"available.":[197],"<sup":[198],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[199],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}