{"id":"https://openalex.org/W4403792435","doi":"https://doi.org/10.1145/3664647.3681606","title":"Similarity Preserving Transformer Cross-Modal Hashing for Video-Text Retrieval","display_name":"Similarity Preserving Transformer Cross-Modal Hashing for Video-Text Retrieval","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792435","doi":"https://doi.org/10.1145/3664647.3681606"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5112230887","display_name":"Qianxin Huang","orcid":"https://orcid.org/0009-0004-2458-8459"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianxin Huang","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0004-2458-8459","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083963873","display_name":"Siyao Peng","orcid":"https://orcid.org/0000-0003-4758-4763"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyao Peng","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4758-4763","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061132796","display_name":"Xiaobo Shen","orcid":"https://orcid.org/0000-0001-8494-4532"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobo Shen","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8494-4532","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111382617","display_name":"Y. Yuan","orcid":"https://orcid.org/0000-0002-5922-7934"},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun-Hao Yuan","raw_affiliation_strings":["Yangzhou University, Yangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5922-7934","affiliations":[{"raw_affiliation_string":"Yangzhou University, Yangzhou, China","institution_ids":["https://openalex.org/I78978612"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008056593","display_name":"Shirui Pan","orcid":"https://orcid.org/0000-0003-0794-527X"},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shirui Pan","raw_affiliation_strings":["Griffith University, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0794-527X","affiliations":[{"raw_affiliation_string":"Griffith University, Brisbane, Australia","institution_ids":["https://openalex.org/I11701301"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":"5883","last_page":"5891"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9994000196456909,"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":0.7165328860282898},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5821092128753662},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5729008316993713},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5066757798194885},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4917488396167755},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45007848739624023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3952369689941406},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09105849266052246},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06800439953804016},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06625106930732727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7165328860282898},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5821092128753662},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5729008316993713},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5066757798194885},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4917488396167755},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45007848739624023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3952369689941406},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09105849266052246},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06800439953804016},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06625106930732727},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":31,"referenced_works":["https://openalex.org/W1922199343","https://openalex.org/W1976258951","https://openalex.org/W2067766814","https://openalex.org/W2108523493","https://openalex.org/W2117539524","https://openalex.org/W2187089797","https://openalex.org/W2203543769","https://openalex.org/W2266728343","https://openalex.org/W2337252826","https://openalex.org/W2425121537","https://openalex.org/W2527195341","https://openalex.org/W2563615176","https://openalex.org/W2602753196","https://openalex.org/W2749145308","https://openalex.org/W2767687205","https://openalex.org/W2786585376","https://openalex.org/W2808243243","https://openalex.org/W2900790473","https://openalex.org/W2963524571","https://openalex.org/W2963916161","https://openalex.org/W2982905682","https://openalex.org/W3004085219","https://openalex.org/W3025665229","https://openalex.org/W3035747010","https://openalex.org/W3099677434","https://openalex.org/W3122091215","https://openalex.org/W3128401049","https://openalex.org/W3173956867","https://openalex.org/W3177244733","https://openalex.org/W4200528395","https://openalex.org/W4312477797"],"related_works":["https://openalex.org/W2159024673","https://openalex.org/W3001987467","https://openalex.org/W2968165261","https://openalex.org/W1603161560","https://openalex.org/W1587382781","https://openalex.org/W2375480909","https://openalex.org/W2154676777","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W2950663250"],"abstract_inverted_index":{"As":[0],"social":[1],"networks":[2],"grow":[3],"exponentially,":[4],"there":[5],"is":[6,70],"an":[7],"increasing":[8],"demand":[9],"for":[10,103],"video":[11,80,108,172],"retrieval":[12],"using":[13,22],"natural":[14],"language.":[15],"Cross-modal":[16],"hashing":[17,50,101],"that":[18,115,176],"encodes":[19,107],"multi-modal":[20,68,123,130,148],"data":[21],"compact":[23],"hash":[24],"code":[25],"has":[26],"been":[27],"widely":[28],"used":[29],"in":[30,183],"large-scale":[31],"image-text":[32],"retrieval,":[33,46],"primarily":[34],"due":[35],"to":[36,44,75,126,155],"its":[37],"computation":[38],"and":[39,58,81,109,132,151,159,165],"storage":[40],"efficiency.":[41],"When":[42],"applied":[43],"video-text":[45,104,184],"existing":[47],"unsupervised":[48,98,147],"cross-modal":[49,100],"extracts":[51],"the":[52,67,76,85,177],"frame-":[53],"or":[54],"word-level":[55],"features":[56],"individually,":[57],"thus":[59],"ignores":[60],"long-term":[61,118],"dependencies.":[62,119],"In":[63],"addition,":[64],"effectively":[65,156],"exploiting":[66],"structure":[69,162],"a":[71,96,122],"remarkable":[72],"challenge":[73],"owing":[74],"complex":[77],"nature":[78],"of":[79],"text.":[82],"To":[83],"address":[84],"above":[86],"issues,":[87],"we":[88],"propose":[89],"Similarity":[90],"Preserving":[91],"Transformer":[92],"Cross-Modal":[93],"Hashing":[94],"(SPTCH),":[95],"new":[97],"deep":[99],"method":[102],"retrieval.":[105,185],"SPTCH":[106,120,145,179],"text":[110],"by":[111,136],"bidirectional":[112],"transformer":[113],"encoder":[114],"exploits":[116],"their":[117],"constructs":[121],"collaborative":[124],"graph":[125],"model":[127],"correlations":[128],"among":[129,163],"data,":[131],"applies":[133],"semantic":[134],"aggregation":[135],"employing":[137],"Graph":[138],"Convolutional":[139],"Network":[140],"(GCN)":[141],"on":[142,170],"such":[143],"graph.":[144],"designs":[146],"contrastive":[149],"loss":[150,154],"neighborhood":[152],"reconstruction":[153],"leverage":[157],"inter-":[158],"intra-modal":[160],"similarity":[161],"videos":[164],"texts.":[166],"The":[167],"empirical":[168],"results":[169],"three":[171],"benchmark":[173],"datasets":[174],"illustrate":[175],"proposed":[178],"generally":[180],"outperforms":[181],"state-of-the-arts":[182]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}