{"id":"https://openalex.org/W4385656471","doi":"https://doi.org/10.1109/tcsii.2023.3302801","title":"Enhanced Cross-Modal Transformer Model for Video Semantic Similarity Measurement","display_name":"Enhanced Cross-Modal Transformer Model for Video Semantic Similarity Measurement","publication_year":2023,"publication_date":"2023-08-08","ids":{"openalex":"https://openalex.org/W4385656471","doi":"https://doi.org/10.1109/tcsii.2023.3302801"},"language":"en","primary_location":{"id":"doi:10.1109/tcsii.2023.3302801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsii.2023.3302801","pdf_url":null,"source":{"id":"https://openalex.org/S93916849","display_name":"IEEE Transactions on Circuits & Systems II Express Briefs","issn_l":"1549-7747","issn":["1549-7747","1558-3791"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems II: Express Briefs","raw_type":"journal-article"},"type":"article","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/A5102835025","display_name":"Da Li","orcid":"https://orcid.org/0009-0006-6925-5476"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da Li","raw_affiliation_strings":["Tencent, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018669598","display_name":"Boqing Zhu","orcid":"https://orcid.org/0000-0001-7867-2112"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boqing Zhu","raw_affiliation_strings":["School of Computer Science, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-7867-2112","affiliations":[{"raw_affiliation_string":"School of Computer Science, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013340793","display_name":"Kele Xu","orcid":"https://orcid.org/0000-0001-5997-5169"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kele Xu","raw_affiliation_strings":["School of Computer Science, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-5997-5169","affiliations":[{"raw_affiliation_string":"School of Computer Science, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002854172","display_name":"Sen Yang","orcid":"https://orcid.org/0000-0003-3222-2268"},"institutions":[{"id":"https://openalex.org/I4210134982","display_name":"Institute of Microbiology","ror":"https://ror.org/047yhep71","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210134982"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sen Yang","raw_affiliation_strings":["Beijing Institute of Microbiology and Epidemiology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3222-2268","affiliations":[{"raw_affiliation_string":"Beijing Institute of Microbiology and Epidemiology, Beijing, China","institution_ids":["https://openalex.org/I4210134982"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039795290","display_name":"Dawei Feng","orcid":"https://orcid.org/0000-0002-7587-8905"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Feng","raw_affiliation_strings":["School of Computer Science, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050900731","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-9953-8438"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["School of Computer Science, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101522100","display_name":"Huaimin Wang","orcid":"https://orcid.org/0000-0002-3245-1901"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaimin Wang","raw_affiliation_strings":["School of Computer Science, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3191,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56372397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"71","issue":"1","first_page":"475","last_page":"479"},"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":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8410372734069824},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.6480575203895569},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6144412159919739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5206795930862427},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.49247536063194275},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4864771068096161},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4347835183143616},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4303245544433594},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4100653827190399},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3803540766239166},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13021788001060486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410372734069824},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.6480575203895569},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6144412159919739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5206795930862427},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.49247536063194275},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4864771068096161},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4347835183143616},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4303245544433594},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4100653827190399},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3803540766239166},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13021788001060486},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsii.2023.3302801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsii.2023.3302801","pdf_url":null,"source":{"id":"https://openalex.org/S93916849","display_name":"IEEE Transactions on Circuits & Systems II Express Briefs","issn_l":"1549-7747","issn":["1549-7747","1558-3791"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems II: Express Briefs","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2546190447","https://openalex.org/W2608787653","https://openalex.org/W2900560726","https://openalex.org/W2968124245","https://openalex.org/W2970231061","https://openalex.org/W2981851019","https://openalex.org/W2998356391","https://openalex.org/W2999004587","https://openalex.org/W3001555892","https://openalex.org/W3012568767","https://openalex.org/W3099023595","https://openalex.org/W3130909864","https://openalex.org/W3155001903","https://openalex.org/W4221167396","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6767279747","https://openalex.org/W6772527114","https://openalex.org/W6773248631","https://openalex.org/W6810265253"],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W2011264131","https://openalex.org/W4306353150","https://openalex.org/W2026860389","https://openalex.org/W4301143707","https://openalex.org/W2952745240","https://openalex.org/W2114797768","https://openalex.org/W2380654781","https://openalex.org/W2176214140","https://openalex.org/W2516873349"],"abstract_inverted_index":{"Video":[0],"processing":[1],"is":[2],"critical":[3],"to":[4,14,55,64,88,97,123,141],"many":[5,40],"industrial":[6],"systems.":[7],"Semantic":[8],"similarity":[9,92,164],"measures":[10],"for":[11,47],"videos":[12],"aim":[13],"evaluate":[15],"the":[16,48,66,74,90,94,99,126,143,146,155,158,162],"semantic":[17,91,163],"distance":[18],"of":[19,93,145,157],"videos,":[20],"and":[21,33,131],"its":[22,149],"downstream":[23],"applications":[24],"seem":[25],"obvious,":[26],"such":[27],"as":[28],"deduplication,":[29],"related":[30],"matching,":[31],"ranking":[32],"content":[34],"diversity":[35],"control.":[36],"Despite":[37,148],"sustainable":[38],"efforts,":[39],"previous":[41,61],"approaches":[42],"require":[43],"large-scale":[44],"human":[45],"annotation":[46],"training":[49],"purpose,":[50],"which":[51,71],"can":[52],"be":[53],"difficult":[54],"obtain":[56],"in":[57,80],"practical":[58],"settings.":[59],"Moreover,":[60,113],"methods":[62],"struggle":[63],"characterize":[65],"interactions":[67],"between":[68,129],"multiple":[69],"modalities,":[70],"severely":[72],"constraints":[73],"performance.":[75],"To":[76],"address":[77,98],"aforementioned":[78],"challenges,":[79],"this":[81],"paper,":[82],"we":[83,103],"introduce":[84],"a":[85,106],"novel":[86],"framework":[87],"measure":[89],"video.":[95],"Specifically,":[96],"limited":[100],"annotated":[101],"datasets,":[102],"firstly":[104],"propose":[105],"pre-training":[107],"paradigm":[108],"leveraging":[109],"weakly-supervised":[110],"label":[111],"classification.":[112],"our":[114],"approach":[115,160],"proposes":[116],"an":[117],"Enhanced":[118],"Cross-modal":[119],"Transformer":[120],"(ECT)":[121],"block,":[122],"fully":[124],"utilize":[125],"interaction":[127],"information":[128],"video":[130],"textural":[132],"features.":[133],"Various":[134],"optimization":[135],"strategies":[136],"have":[137],"also":[138],"been":[139],"proposed":[140,159],"improve":[142],"performance":[144],"model.":[147],"conceptually":[150],"simpleness,":[151],"extensive":[152],"experiments":[153],"demonstrate":[154],"effectiveness":[156],"on":[161],"measurement":[165],"tasks.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}