{"id":"https://openalex.org/W4308237319","doi":"https://doi.org/10.1109/icip46576.2022.9897206","title":"Context-Aware Hierarchical Transformer for Fine-Grained Video-Text Retrieval","display_name":"Context-Aware Hierarchical Transformer for Fine-Grained Video-Text Retrieval","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308237319","doi":"https://doi.org/10.1109/icip46576.2022.9897206"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897206","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","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/A5100438163","display_name":"Mingliang Chen","orcid":"https://orcid.org/0000-0003-2005-4295"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingliang Chen","raw_affiliation_strings":["Peking University Shenzhen Graduate School,School of Electronic and Computer Engineering","School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University Shenzhen Graduate School,School of Electronic and Computer Engineering","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340717","display_name":"Weimin Zhang","orcid":"https://orcid.org/0000-0001-6632-0144"},"institutions":[{"id":"https://openalex.org/I11838497","display_name":"Aviation Industry Corporation of China (China)","ror":"https://ror.org/02wq41p38","country_code":"CN","type":"company","lineage":["https://openalex.org/I11838497"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weimin Zhang","raw_affiliation_strings":["AVS Industry Alliance,China","AVS Industry Alliance, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AVS Industry Alliance,China","institution_ids":["https://openalex.org/I11838497"]},{"raw_affiliation_string":"AVS Industry Alliance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101891152","display_name":"Yurui Ren","orcid":"https://orcid.org/0000-0003-0178-4460"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yurui Ren","raw_affiliation_strings":["Peking University Shenzhen Graduate School,School of Electronic and Computer Engineering","School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University Shenzhen Graduate School,School of Electronic and Computer Engineering","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100447691","display_name":"Ge Li","orcid":"https://orcid.org/0000-0003-0140-0949"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Li","raw_affiliation_strings":["Peking University Shenzhen Graduate School,School of Electronic and Computer Engineering","School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University Shenzhen Graduate School,School of Electronic and Computer Engineering","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1283197,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"386","last_page":"390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9993000030517578,"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":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.8623889088630676},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.694648027420044},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5528315901756287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5241737365722656},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.523242175579071},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46392735838890076},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4578617215156555},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.42473703622817993},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4238562285900116},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4147719740867615},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.0921991765499115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8623889088630676},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.694648027420044},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5528315901756287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5241737365722656},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.523242175579071},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46392735838890076},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4578617215156555},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.42473703622817993},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4238562285900116},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4147719740867615},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0921991765499115},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897206","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2596164567","https://openalex.org/W2619947201","https://openalex.org/W2956018683","https://openalex.org/W2963293463","https://openalex.org/W2975813532","https://openalex.org/W2990503944","https://openalex.org/W3034467781","https://openalex.org/W3034882096","https://openalex.org/W3035356601","https://openalex.org/W3091588028","https://openalex.org/W3167886702","https://openalex.org/W3195280391","https://openalex.org/W3207042189","https://openalex.org/W4385245566","https://openalex.org/W6631516269","https://openalex.org/W6739901393","https://openalex.org/W6747225742","https://openalex.org/W6789753369","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2378211422","https://openalex.org/W2988126442","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W1974414866","https://openalex.org/W2130974462"],"abstract_inverted_index":{"Video-Text":[0],"Retrieval":[1],"aims":[2],"to":[3,11,47,59,77,107],"perform":[4],"accurate":[5],"retrieval":[6,122],"process":[7],"that":[8],"adopts":[9],"texts":[10],"retrieve":[12],"the":[13,35,45,61,79,109,125,135],"corresponding":[14],"videos,":[15],"and":[16,32,39,68,100],"vice":[17],"versa.":[18],"Typically,":[19],"mainstream":[20],"methods":[21,43],"solve":[22],"this":[23],"problem":[24],"by":[25],"learning":[26],"a":[27,71],"common":[28],"joint":[29],"embedding":[30],"space,":[31],"then":[33,69],"measure":[34],"similarities":[36],"between":[37,82,112],"videos":[38],"texts.":[40],"However,":[41],"these":[42,83],"lack":[44],"ability":[46],"represent":[48],"detailed":[49],"semantic":[50,66,96,114],"information.":[51],"Therefore,":[52],"we":[53],"first":[54],"utilize":[55],"three":[56,95],"pre-trained":[57],"models":[58],"construct":[60],"video":[62,92],"embeddings":[63,93],"of":[64,94,127,137],"different":[65,113],"levels,":[67],"propose":[70],"Context-aware":[72],"Hierarchical":[73],"Transformer":[74],"(CHT)":[75],"model":[76,88],"encode":[78],"context":[80,110],"information":[81],"levels.":[84,115],"More":[85],"specifically,":[86],"our":[87,128,138],"builds":[89],"fine-grained":[90],"hierarchical":[91],"levels:":[97],"global,":[98],"objects,":[99],"actions.":[101],"Attention-based":[102],"contextual":[103],"transformers":[104],"are":[105],"utilized":[106],"establish":[108],"interactions":[111],"Experimental":[116],"results":[117],"on":[118],"two":[119],"benchmark":[120],"video-text":[121],"datasets":[123],"demonstrate":[124],"superiority":[126],"CHT":[129],"model.":[130,140],"Ablation":[131],"studies":[132],"also":[133],"prove":[134],"effectiveness":[136],"proposed":[139]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}