{"id":"https://openalex.org/W7166831621","doi":"https://doi.org/10.18653/v1/2026.acl-long.244","title":"DPDV: Dual-Pathway and Dual-View Representation Learning for Bridging Information Asymmetry in Text-Video Retrieval","display_name":"DPDV: Dual-Pathway and Dual-View Representation Learning for Bridging Information Asymmetry in Text-Video Retrieval","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166831621","doi":"https://doi.org/10.18653/v1/2026.acl-long.244"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.244","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.244","pdf_url":"https://aclanthology.org/2026.acl-long.244.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.244.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139745323","display_name":"Zequn Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zequn Xie","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139741234","display_name":"Xin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139734219","display_name":"Fangming Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fangming Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123515154","display_name":"Boyun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boyun Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139816329","display_name":"Tao Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Jin","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8419716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5385","last_page":"5394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7261999845504761,"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":0.7261999845504761,"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":0.10029999911785126,"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":0.05389999970793724,"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/bridging","display_name":"Bridging (networking)","score":0.5895000100135803},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3968000113964081},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3513999879360199},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.26750001311302185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6122000217437744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6007999777793884},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5895000100135803},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3968000113964081},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3467999994754791},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2712000012397766},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25600001215934753},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.244","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.244","pdf_url":"https://aclanthology.org/2026.acl-long.244.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.244","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.244","pdf_url":"https://aclanthology.org/2026.acl-long.244.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1101031052","display_name":null,"funder_award_id":"U24A20326","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166831621.pdf","grobid_xml":"https://content.openalex.org/works/W7166831621.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-based":[0],"person":[1],"anomaly":[2],"search":[3],"retrieves":[4],"specific":[5],"behavioral":[6],"events":[7],"from":[8],"surveillance":[9],"archives":[10],"using":[11,44],"natural-language":[12],"queries.Although":[13],"recent":[14],"pose-aware":[15],"methods":[16],"align":[17],"geometric":[18],"structures":[19],"well,":[20],"they":[21],"face":[22],"a":[23,69,83,91,103],"fundamental":[24],"Pose-Semantic":[25],"Gap:":[26],"semantically":[27],"different":[28],"actions":[29],"can":[30,40],"share":[31],"similar":[32],"skeletal":[33,76],"geometries.While":[34],"Multimodal":[35],"Large":[36],"Language":[37],"Models":[38],"(MLLMs)":[39],"reduce":[41],"this":[42],"ambiguity,":[43],"them":[45],"for":[46,93,99,105],"large-scale":[47],"retrieval":[48,61],"is":[49,136],"computationally":[50],"prohibitive.We":[51],"propose":[52],"the":[53,113,120],"Structure-Semantic":[54],"Decoupled":[55],"Cascade":[56],"(SSDC)":[57],"framework,":[58],"which":[59],"decouples":[60],"into":[62],"two":[63],"stages:(1)":[64],"Structure-Aware":[65],"Coarse":[66],"Retrieval,":[67],"where":[68],"lightweight":[70],"model":[71],"quickly":[72],"filters":[73],"candidates":[74,110],"by":[75,111,129],"similarity;":[77],"and":[78,102,132],"(2)":[79],"Detective":[80,92],"Squad":[81],"Interaction,":[82],"multi-agent":[84],"semantic":[85,106,133],"verification":[86],"module.The":[87],"squad":[88],"consists":[89],"of":[90],"fast":[94],"binary":[95],"filtering,":[96],"an":[97],"Analyst":[98],"evidence":[100],"extraction,":[101],"Writer":[104],"synthesis.Finally,":[107],"we":[108],"re-rank":[109],"fusing":[112],"synthesized":[114],"captions":[115],"with":[116],"structural":[117],"priors.Experiments":[118],"on":[119],"PAB":[121],"benchmark":[122],"show":[123],"that":[124],"SSDC":[125],"achieves":[126],"state-of-theart":[127],"performance":[128],"balancing":[130],"efficiency":[131],"reasoning.Our":[134],"code":[135],"available":[137]},"counts_by_year":[],"updated_date":"2026-08-22T07:34:49.880490","created_date":"2026-07-02T00:00:00"}