{"id":"https://openalex.org/W4392798731","doi":"https://doi.org/10.1145/3638584.3638635","title":"Ontology-Semantic Alignment On Contrastive Video-Language Model for Multimodel Video Retrieval Task","display_name":"Ontology-Semantic Alignment On Contrastive Video-Language Model for Multimodel Video Retrieval Task","publication_year":2023,"publication_date":"2023-12-08","ids":{"openalex":"https://openalex.org/W4392798731","doi":"https://doi.org/10.1145/3638584.3638635"},"language":"en","primary_location":{"id":"doi:10.1145/3638584.3638635","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638584.3638635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-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/A5081358565","display_name":"Yifan Zhou","orcid":"https://orcid.org/0009-0001-2244-1945"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifan Zhou","raw_affiliation_strings":["Shanghai Jiao Tong University, State Key Lab of Advanced Optical Communication System and Network, China"],"raw_orcid":"https://orcid.org/0009-0001-2244-1945","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, State Key Lab of Advanced Optical Communication System and Network, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019166045","display_name":"Yizhou Ding","orcid":"https://orcid.org/0009-0001-5166-5753"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhou Ding","raw_affiliation_strings":["Shanghai Jiao Tong University, State Key Lab of Advanced Optical Communication System and Network, China"],"raw_orcid":"https://orcid.org/0009-0001-5166-5753","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, State Key Lab of Advanced Optical Communication System and Network, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040396843","display_name":"Yuwu Dong","orcid":"https://orcid.org/0009-0004-3392-4004"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwu Dong","raw_affiliation_strings":["Shanghai Jiao Tong University, State Key Lab of Advanced Optical Communication System and Network, China"],"raw_orcid":"https://orcid.org/0009-0004-3392-4004","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, State Key Lab of Advanced Optical Communication System and Network, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088175680","display_name":"Hao He","orcid":"https://orcid.org/0000-0002-4851-7012"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao He","raw_affiliation_strings":["Shanghai Jiao Tong University, State Key Lab of Advanced Optical Communication System and Network, China"],"raw_orcid":"https://orcid.org/0000-0002-4851-7012","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, State Key Lab of Advanced Optical Communication System and Network, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081358565"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20363603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"408","last_page":"413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9984999895095825,"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":0.9976999759674072,"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":0.8807034492492676},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6882822513580322},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6495175957679749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5643088221549988},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.46796637773513794},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41905394196510315}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8807034492492676},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6882822513580322},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6495175957679749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5643088221549988},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.46796637773513794},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41905394196510315},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3638584.3638635","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638584.3638635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2533598788","https://openalex.org/W2556388456","https://openalex.org/W2558834163","https://openalex.org/W2963351113","https://openalex.org/W2984008963","https://openalex.org/W3132005757","https://openalex.org/W3135367836","https://openalex.org/W3155721152","https://openalex.org/W3181951703","https://openalex.org/W3210586215","https://openalex.org/W4313181088","https://openalex.org/W4360600216","https://openalex.org/W4372265847","https://openalex.org/W4372349424"],"related_works":["https://openalex.org/W2003333417","https://openalex.org/W2378862226","https://openalex.org/W118236634","https://openalex.org/W2355326633","https://openalex.org/W2804669904","https://openalex.org/W2149777447","https://openalex.org/W2347456287","https://openalex.org/W2121651557","https://openalex.org/W2782969047","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Contrastive":[0],"Learning-based":[1],"models":[2],"have":[3,21,104,162],"shown":[4],"impressive":[5],"performance":[6,192],"in":[7,14,24,130,218],"text-image":[8],"retrieval":[9,98,142,220],"tasks.":[10,221],"However,":[11],"when":[12],"applied":[13],"video":[15,32,66,101,118,150,219],"retrieval,":[16],"traditional":[17],"contrastive":[18,156,209],"learning":[19,157,210],"strategies":[20],"faced":[22],"challenges":[23],"achieving":[25],"satisfactory":[26],"results":[27,198],"due":[28],"to":[29,148,189,212],"redundancy":[30],"of":[31,58,193,216],"contents.":[33],"We":[34],"discern":[35],"several":[36],"potential":[37],"reasons:":[38],"(1)Current":[39],"methodologies":[40,68],"sometimes":[41],"overlook":[42],"the":[43,54,59,62,91,127,131,155,177,186,191],"significant":[44],"information":[45],"imbalance":[46],"between":[47],"videos":[48],"and":[49,87,144,173,183],"query":[50],"text,":[51],"specifically":[52],"neglecting":[53],"in-depth":[55],"textual":[56,174],"representation":[57],"content":[60,102,119],"within":[61,176],"videos.":[63,178],"(2)":[64],"Current":[65],"matching":[67],"typically":[69],"focus":[70],"on":[71,100,111,185],"cross-model":[72],"alignment":[73],"at":[74,93],"general":[75],"entity":[76,84],"similarity":[77,88],"level,":[78],"without":[79,115],"specific":[80],"consideration":[81],"for":[82,122,208],"how":[83],"pair":[85],"preferences":[86],"properties":[89],"affect":[90],"task":[92],"hand.":[94],"(3)":[95],"Previous":[96],"vectorized":[97],"based":[99],"features":[103,114],"been":[105],"somewhat":[106],"flawed.":[107],"They":[108],"primarily":[109],"focused":[110],"aligning":[112],"overall":[113],"having":[116],"an":[117,137,213],"tags":[120],"feature":[121,124],"meaningful":[123],"discrimination.":[125],"Considering":[126],"shortcomings":[128],"identified":[129],"mentioned":[132],"three":[133],"aspects,":[134],"we":[135,161,180],"propose":[136],"ontology":[138,151,164,203],"semantic":[139,152,165],"labels":[140,153,204],"augments":[141],"model":[143],"introduce":[145],"a":[146],"method":[147],"integrate":[149],"into":[154],"framework.":[158],"In":[159],"particular,":[160],"developed":[163],"descriptions":[166],"about":[167],"entities":[168],"encompassing":[169],"both":[170],"human":[171],"figures":[172],"elements":[175],"Subsequently,":[179],"conducted":[181],"training":[182],"testing":[184],"CMIVQA":[187],"dataset":[188],"assess":[190],"our":[194],"approach.":[195],"The":[196],"experimental":[197],"show":[199],"that":[200],"employing":[201],"fine-grained":[202],"as":[205],"sample":[206],"pairs":[207],"leads":[211],"increased":[214],"level":[215],"precision":[217]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}