{"id":"https://openalex.org/W7137938234","doi":"https://doi.org/10.1609/aaai.v40i10.37745","title":"Appearance-Motion Decomposed Alignment for Text-Video Retrieval","display_name":"Appearance-Motion Decomposed Alignment for Text-Video Retrieval","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137938234","doi":"https://doi.org/10.1609/aaai.v40i10.37745"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i10.37745","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37745","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37745/41707","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37745/41707","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129674100","display_name":"Meng Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122640","display_name":"Nigerian Institute For Oil Palm Reasearch","ror":"https://ror.org/02y05bg81","country_code":"NG","type":"government","lineage":["https://openalex.org/I4210122640"]}],"countries":["NG"],"is_corresponding":false,"raw_author_name":"Meng Meng","raw_affiliation_strings":["Sangfor Technologies Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sangfor Technologies Inc","institution_ids":["https://openalex.org/I4210122640"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040257967","display_name":"Zichang Tan","orcid":"https://orcid.org/0000-0002-8501-4123"},"institutions":[{"id":"https://openalex.org/I4210122640","display_name":"Nigerian Institute For Oil Palm Reasearch","ror":"https://ror.org/02y05bg81","country_code":"NG","type":"government","lineage":["https://openalex.org/I4210122640"]}],"countries":["NG"],"is_corresponding":false,"raw_author_name":"Zichang Tan","raw_affiliation_strings":["Sangfor Technologies Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sangfor Technologies Inc","institution_ids":["https://openalex.org/I4210122640"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129643011","display_name":"Yong E. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122640","display_name":"Nigerian Institute For Oil Palm Reasearch","ror":"https://ror.org/02y05bg81","country_code":"NG","type":"government","lineage":["https://openalex.org/I4210122640"]}],"countries":["NG"],"is_corresponding":false,"raw_author_name":"Yong Zhang","raw_affiliation_strings":["Sangfor Technologies Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sangfor Technologies Inc","institution_ids":["https://openalex.org/I4210122640"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129670451","display_name":"Xu Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122640","display_name":"Nigerian Institute For Oil Palm Reasearch","ror":"https://ror.org/02y05bg81","country_code":"NG","type":"government","lineage":["https://openalex.org/I4210122640"]}],"countries":["NG"],"is_corresponding":false,"raw_author_name":"Xu Zhou","raw_affiliation_strings":["Sangfor Technologies Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sangfor Technologies Inc","institution_ids":["https://openalex.org/I4210122640"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210122640"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"10","first_page":"7999","last_page":"8007"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8701000213623047,"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":0.8701000213623047,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.03779999911785126,"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/T11448","display_name":"Face recognition and analysis","score":0.020800000056624413,"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/discriminative-model","display_name":"Discriminative model","score":0.8472999930381775},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7113999724388123},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5866000056266785},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42809998989105225},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40689998865127563},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.3776000142097473},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.37070000171661377},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.35850000381469727},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.3441999852657318}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8472999930381775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.808899998664856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7215999960899353},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7113999724388123},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5866000056266785},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48330000042915344},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40689998865127563},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.32710000872612},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30219998955726624},{"id":"https://openalex.org/C2779020251","wikidata":"https://www.wikidata.org/wiki/Q3555171","display_name":"Motion vector","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.28139999508857727},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.257999986410141},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25279998779296875},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.25200000405311584},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i10.37745","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37745","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37745/41707","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37745","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i10.37745","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37745","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37745/41707","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7517037391662598}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137938234.pdf","grobid_xml":"https://content.openalex.org/works/W7137938234.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-video":[0],"retrieval":[1],"aims":[2],"to":[3,21,27,59,110,188],"bridge":[4],"vision":[5],"and":[6,24,65,89,114,123,156,164],"language":[7],"areas,":[8],"which":[9,185],"is":[10,20,38],"a":[11,51,69,81,142,157],"crucial":[12],"task":[13],"in":[14,35],"multi-modal":[15],"intelligence.":[16],"The":[17,128],"core":[18],"idea":[19],"learn":[22],"video":[23,42,100,167],"textual":[25],"features":[26,180,190],"quantify":[28],"their":[29,94],"semantic":[30],"relevance.":[31],"A":[32],"common":[33],"limitation":[34],"current":[36],"approaches":[37],"the":[39,119,135,170],"oversimplification":[40],"of":[41],"content,":[43],"where":[44],"complex":[45],"spatiotemporal":[46],"structures":[47],"are":[48,186],"compressed":[49],"into":[50],"single":[52],"global":[53],"representation.":[54],"Consequently,":[55],"these":[56,77],"methods":[57],"struggle":[58],"fully":[60],"capture":[61,178],"dynamic":[62],"visual":[63],"variations":[64],"discriminative":[66,120,137],"appearance":[67,88,113,121,138,154,189],"inside":[68],"video,":[70],"further":[71],"complicating":[72],"cross-modal":[73],"alignment.":[74],"To":[75],"alleviate":[76],"issues,":[78],"we":[79,103],"introduce":[80],"novel":[82],"decoupling":[83],"approach":[84],"that":[85,202],"independently":[86],"processes":[87],"motion":[90,116,125,173,179],"cues,":[91],"capitalizing":[92],"on":[93,197],"complementary":[95,187],"nature":[96],"for":[97,191],"more":[98],"expressive":[99],"modeling.":[101],"Specifically,":[102],"propose":[104],"an":[105],"appearance-motion":[106],"decomposed":[107],"network":[108],"(AMD-Net)":[109],"decouple":[111],"spatial-level":[112],"temporal-level":[115],"understanding":[117],"via":[118],"learning":[122,126,139,174],"multi-scale":[124,172],"modules.":[127],"proposed":[129,171],"model":[130],"enjoys":[131],"several":[132],"merits.":[133],"First,":[134],"designed":[136],"module":[140,176],"with":[141],"Singular":[143],"Value":[144],"Decomposition":[145],"(SVD)":[146],"based":[147],"prototype":[148,162],"initialization":[149],"can":[150,177],"effectively":[151],"reduce":[152],"redundant":[153],"information,":[155],"high-order":[158],"cross-aggregation":[159],"mechanism":[160],"enhances":[161],"resilience":[163],"facilitates":[165],"comprehensive":[166],"understanding.":[168],"Second,":[169],"(MML)":[175],"at":[181],"varying":[182],"temporal":[183],"scales,":[184],"accurate":[192],"text-video":[193],"retrieval.":[194],"Extensive":[195],"experiments":[196],"five":[198],"standard":[199],"benchmarks":[200],"demonstrate":[201],"our":[203],"method":[204],"performs":[205],"favorably":[206],"against":[207],"state-of-the-art":[208],"methods.":[209]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}