{"id":"https://openalex.org/W7160358100","doi":"https://doi.org/10.1109/wacv61042.2026.00433","title":"Similarity-aware Probabilistic Embeddings Modeling for Video-Text Retrieval","display_name":"Similarity-aware Probabilistic Embeddings Modeling for Video-Text Retrieval","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160358100","doi":"https://doi.org/10.1109/wacv61042.2026.00433"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00433","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":"conference-paper","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/A5135339172","display_name":"Yuliang Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuliang Huang","raw_affiliation_strings":["Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135378524","display_name":"Pengxu Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengxu Wei","raw_affiliation_strings":["Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135390123","display_name":"Zhicheng Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I140786321","display_name":"Tibet University","ror":"https://ror.org/05petvd47","country_code":"CN","type":"education","lineage":["https://openalex.org/I140786321"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicheng Dong","raw_affiliation_strings":["Tibet University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tibet University","institution_ids":["https://openalex.org/I140786321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135316819","display_name":"Lin Liang","orcid":"https://orcid.org/0009-0006-8604-6000"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Lin","raw_affiliation_strings":["Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4451","last_page":"4460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.5457000136375427,"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":0.5457000136375427,"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":0.3140999972820282,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.016200000420212746,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.5667999982833862},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.33570000529289246},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2842000126838684},{"id":"https://openalex.org/keywords/divergence-from-randomness-model","display_name":"Divergence-from-randomness model","score":0.28200000524520874},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2754000127315521}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5976999998092651},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5667999982833862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4844000041484833},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3098999857902527},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C149189445","wikidata":"https://www.wikidata.org/wiki/Q5283894","display_name":"Divergence-from-randomness model","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26649999618530273},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2630999982357025}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00433","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2078238240","https://openalex.org/W2425121537","https://openalex.org/W2885775891","https://openalex.org/W2963017553","https://openalex.org/W2989322838","https://openalex.org/W3035356601","https://openalex.org/W3035376925","https://openalex.org/W3043840704","https://openalex.org/W3081375228","https://openalex.org/W3155721152","https://openalex.org/W3168433561","https://openalex.org/W3168640669","https://openalex.org/W3205021045","https://openalex.org/W4214931087","https://openalex.org/W4225414521","https://openalex.org/W4285606530","https://openalex.org/W4292794825","https://openalex.org/W4304014690","https://openalex.org/W4312372711","https://openalex.org/W4313007634","https://openalex.org/W4319299894","https://openalex.org/W4385767942","https://openalex.org/W4386072365","https://openalex.org/W4387967944","https://openalex.org/W4389520066","https://openalex.org/W4389520792","https://openalex.org/W4390871725","https://openalex.org/W4390872434","https://openalex.org/W4390889802","https://openalex.org/W4392384263","https://openalex.org/W4392667077","https://openalex.org/W4402704596","https://openalex.org/W4402754023","https://openalex.org/W4402980118","https://openalex.org/W4403791665","https://openalex.org/W4403889113","https://openalex.org/W4409366588","https://openalex.org/W4415795415","https://openalex.org/W7126382208","https://openalex.org/W7133200928"],"related_works":[],"abstract_inverted_index":{"Video-text":[0],"retrieval":[1,83,176],"is":[2],"a":[3,33,95,150],"fundamental":[4],"task":[5],"in":[6,159],"multi-modal":[7],"learning,":[8],"aiming":[9],"to":[10,49,54,117,131,154],"accurately":[11],"retrieve":[12],"videos":[13,29,46],"that":[14,98,182],"match":[15],"given":[16],"textual":[17],"descriptions.":[18],"While":[19],"recent":[20],"contrastive":[21],"methods":[22],"have":[23],"made":[24],"significant":[25],"progress":[26],"by":[27,102],"embedding":[28,135],"and":[30,81,122,126,180],"texts":[31],"into":[32],"joint":[34],"space,":[35,162],"they":[36],"often":[37],"suffer":[38],"from":[39],"semantic":[40,142],"over-clustering\u2014a":[41],"phenomenon":[42],"where":[43,76],"semantically":[44],"distinct":[45],"are":[47],"mapped":[48],"overly":[50],"similar":[51],"embeddings":[52],"due":[53],"dominant":[55],"but":[56,140],"uninformative":[57],"visual":[58,120],"patterns":[59],"(e.g.,":[60],"recurring":[61],"backgrounds":[62],"or":[63,73],"common":[64],"objects).":[65],"This":[66],"effect":[67],"becomes":[68],"particularly":[69],"problematic":[70],"under":[71],"short":[72],"ambiguous":[74],"queries,":[75],"it":[77],"suppresses":[78],"fine-grained":[79],"semantics":[80],"degrades":[82],"precision.":[84],"To":[85,144],"address":[86],"this,":[87],"we":[88,148],"propose":[89],"Similarity-aware":[90],"Probabilistic":[91],"Embeddings":[92],"Modeling":[93],"(SPEM),":[94],"novel":[96],"framework":[97],"refines":[99],"video":[100],"representations":[101],"modeling":[103],"them":[104],"as":[105],"adaptive":[106],"probability":[107],"distributions":[108],"rather":[109],"than":[110],"static":[111],"vectors.":[112],"SPEM":[113,183],"incorporates":[114],"cross-modal":[115],"attention":[116],"high-light":[118],"text-relevant":[119],"content":[121],"suppress":[123],"irrelevant":[124],"patterns,":[125],"leverages":[127],"multi-level":[128],"similarity":[129],"features":[130],"dynamically":[132],"adjust":[133],"the":[134,156,160],"variance,":[136],"thereby":[137],"preserving":[138],"subtle":[139],"critical":[141],"cues.":[143],"further":[145],"improve":[146],"alignment,":[147],"employ":[149],"Semantic-Distribution":[151],"Contrastive":[152],"Loss":[153],"optimize":[155],"alignment":[157],"structure":[158],"probabilistic":[161],"encouraging":[163],"more":[164],"discriminative":[165],"separation":[166],"across":[167],"hard":[168],"negatives.":[169],"Extensive":[170],"experiments":[171],"on":[172],"four":[173],"widely-used":[174],"video-text":[175],"benchmarks\u2014MSRVTT,":[177],"DiDeMo,":[178],"VATEX,":[179],"MSVD\u2014demonstrate":[181],"consistently":[184],"outperforms":[185],"strong":[186],"CLIP-based":[187],"baselines.":[188]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}