{"id":"https://openalex.org/W7168340221","doi":"https://doi.org/10.1145/3805712.3809704","title":"StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video Retrieval","display_name":"StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video Retrieval","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W7168340221","doi":"https://doi.org/10.1145/3805712.3809704"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809704","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809704","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809704","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140851223","display_name":"Shaokun Wang","orcid":"https://orcid.org/0000-0001-8945-1200"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaokun Wang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8945-1200","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140926407","display_name":"Weili Guan","orcid":"https://orcid.org/0000-0002-5658-5509"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weili Guan","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China and Shenzhen Loop Area Institute, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5658-5509","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China and Shenzhen Loop Area Institute, Shenzhen, China","institution_ids":["https://openalex.org/I158809036"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140800855","display_name":"Jizhou Han","orcid":"https://orcid.org/0009-0007-7804-3739"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jizhou Han","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0007-7804-3739","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140931105","display_name":"Jianlong Wu","orcid":"https://orcid.org/0000-0003-0247-5221"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlong Wu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0247-5221","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140814152","display_name":"Yupeng Hu","orcid":"https://orcid.org/0000-0002-5653-8286"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yupeng Hu","raw_affiliation_strings":["Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-5653-8286","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140760227","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":"1800","last_page":"1811"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27709999680519104},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2583000063896179},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.23739999532699585},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.23579999804496765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6118000149726868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46889999508857727},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2615000009536743},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24809999763965607},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.23739999532699585},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.23579999804496765},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2353000044822693},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.23190000653266907}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809704","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809704","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809704","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809704","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2425121537","https://openalex.org/W2473930607","https://openalex.org/W2798354744","https://openalex.org/W2885775891","https://openalex.org/W2948734064","https://openalex.org/W2954929116","https://openalex.org/W2963072899","https://openalex.org/W2996760632","https://openalex.org/W3006499007","https://openalex.org/W3035356601","https://openalex.org/W3065974826","https://openalex.org/W3113584014","https://openalex.org/W3144281354","https://openalex.org/W3173223111","https://openalex.org/W3174873881","https://openalex.org/W3175294706","https://openalex.org/W3180392831","https://openalex.org/W3204532479","https://openalex.org/W3204588463","https://openalex.org/W3204670646","https://openalex.org/W4225414521","https://openalex.org/W4281261996","https://openalex.org/W4285606530","https://openalex.org/W4289656127","https://openalex.org/W4298357738","https://openalex.org/W4304014690","https://openalex.org/W4304099166","https://openalex.org/W4312238419","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4312533113","https://openalex.org/W4312655527","https://openalex.org/W4312813479","https://openalex.org/W4361741631","https://openalex.org/W4386065833","https://openalex.org/W4386075840","https://openalex.org/W4386076680","https://openalex.org/W4387968011","https://openalex.org/W4387968500","https://openalex.org/W4390871664","https://openalex.org/W4390872020","https://openalex.org/W4390872434","https://openalex.org/W4390874668","https://openalex.org/W4392904145","https://openalex.org/W4402702936","https://openalex.org/W4402727988","https://openalex.org/W4402754307","https://openalex.org/W4402777374","https://openalex.org/W4403791593","https://openalex.org/W4403791665","https://openalex.org/W4403792076","https://openalex.org/W4403792095","https://openalex.org/W4409363793","https://openalex.org/W4412377078","https://openalex.org/W4412394892","https://openalex.org/W4413000605","https://openalex.org/W4413144429","https://openalex.org/W4413146312","https://openalex.org/W4413156207","https://openalex.org/W4415537122","https://openalex.org/W4416748498","https://openalex.org/W7133189282","https://openalex.org/W7160123608","https://openalex.org/W7160188269"],"related_works":[],"abstract_inverted_index":{"Continual":[0],"Text-to-Video":[1],"Retrieval":[2],"(CTVR)":[3],"is":[4,41],"a":[5,77,87,95,110,145],"challenging":[6],"multimodal":[7],"continual":[8,54,199],"learning":[9,55],"setting,":[10],"where":[11],"models":[12],"must":[13],"incrementally":[14],"learn":[15],"new":[16],"semantic":[17],"categories":[18],"while":[19],"maintaining":[20],"accurate":[21],"text-video":[22],"alignment":[23,80,113],"for":[24,82,163],"previously":[25],"learned":[26,127],"ones,":[27],"thus":[28],"making":[29],"it":[30],"particularly":[31],"prone":[32],"to":[33,67,99,129,138,154],"catastrophic":[34,181],"forgetting.":[35],"A":[36],"key":[37],"challenge":[38],"in":[39,46,183],"CTVR":[40],"feature":[42,50,61,141,164,170,176],"drift,":[43,142,177],"which":[44,150],"manifests":[45],"two":[47],"forms:":[48],"intra-modal":[49,140,175],"drift":[51,62,171],"caused":[52],"by":[53],"within":[56],"each":[57],"modality,":[58],"and":[59,118,174],"non-cooperative":[60,169],"across":[63,172],"modalities":[64,153,173],"that":[65,115,191],"leads":[66],"modality":[68,101],"misalignment.":[69,102],"To":[70],"mitigate":[71,100],"these":[72],"issues,":[73],"we":[74,108,143],"propose":[75],"StructAlign,":[76],"structured":[78],"cross-modal":[79,111,156],"method":[81,193],"CTVR.":[83,184],"First,":[84],"StructAlign":[85,178],"introduces":[86],"simplex":[88,133],"Equiangular":[89],"Tight":[90],"Frame":[91],"(ETF)":[92],"geometry":[93],"as":[94],"unified":[96],"geometric":[97,106],"prior":[98],"Building":[103],"upon":[104],"this":[105],"prior,":[107],"design":[109,144],"ETF":[112,123,134],"loss":[114],"aligns":[116],"text":[117],"video":[119],"features":[120],"with":[121],"category-level":[122],"prototypes,":[124],"encouraging":[125],"the":[126],"representations":[128],"form":[130],"an":[131],"approximate":[132],"geometry.":[135],"In":[136],"addition,":[137],"suppress":[139],"Cross-modal":[146],"Relation":[147],"Preserving":[148],"loss,":[149],"leverages":[151],"complementary":[152],"preserve":[155],"similarity":[157],"relations,":[158],"providing":[159],"stable":[160],"relational":[161],"supervision":[162],"updates.":[165],"By":[166],"jointly":[167],"addressing":[168],"effectively":[179],"alleviates":[180],"forgetting":[182],"Extensive":[185],"experiments":[186],"on":[187],"benchmark":[188],"datasets":[189],"demonstrate":[190],"our":[192],"shows":[194],"competitive":[195],"advantages":[196],"over":[197],"state-of-the-art":[198],"retrieval":[200],"approaches.":[201]},"counts_by_year":[],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2026-07-16T00:00:00"}