{"id":"https://openalex.org/W4402979971","doi":"https://doi.org/10.1109/icme57554.2024.10687402","title":"Contrastive masked auto-encoders based self-supervised hashing for 2D image and 3D point cloud cross-modal retrieval","display_name":"Contrastive masked auto-encoders based self-supervised hashing for 2D image and 3D point cloud cross-modal retrieval","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979971","doi":"https://doi.org/10.1109/icme57554.2024.10687402"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687402","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5047375075","display_name":"Rukai Wei","orcid":"https://orcid.org/0000-0003-1164-6360"},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rukai Wei","raw_affiliation_strings":["HUST,Wuhan National Laboratory for Optoelectronics,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"HUST,Wuhan National Laboratory for Optoelectronics,Wuhan,China","institution_ids":["https://openalex.org/I4210138186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103282923","display_name":"Heng Cui","orcid":"https://orcid.org/0009-0005-3464-1556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng Cui","raw_affiliation_strings":["HUST,School of Software Engineering,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"HUST,School of Software Engineering,Wuhan,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004895426","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0002-2067-9175"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["HUST,School of Computer Science and Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"HUST,School of Computer Science and Technology,Wuhan,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050542870","display_name":"Yanzhao Xie","orcid":"https://orcid.org/0000-0002-9274-2807"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanzhao Xie","raw_affiliation_strings":["GZU,School of Computer Science and Cyber Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"GZU,School of Computer Science and Cyber Engineering,Guangzhou,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105229823","display_name":"Yufeng Hou","orcid":"https://orcid.org/0009-0007-2866-3956"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yufeng Hou","raw_affiliation_strings":["HUST,School of Computer Science and Technology,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"HUST,School of Computer Science and Technology,Wuhan,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111632355","display_name":"Ke Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Zhou","raw_affiliation_strings":["HUST,Wuhan National Laboratory for Optoelectronics,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"HUST,Wuhan National Laboratory for Optoelectronics,Wuhan,China","institution_ids":["https://openalex.org/I4210138186"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5047375075"],"corresponding_institution_ids":["https://openalex.org/I4210138186"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16804514,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9987000226974487,"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":0.9987000226974487,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9936000108718872,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9894999861717224,"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":0.7295114994049072},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6912311315536499},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6206853985786438},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.6000311374664307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.585755467414856},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5736263990402222},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5365318059921265},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4882502853870392},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.44693949818611145},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44384005665779114},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36816897988319397},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36419105529785156},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.15425467491149902},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10010087490081787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7295114994049072},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6912311315536499},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6206853985786438},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.6000311374664307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.585755467414856},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5736263990402222},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5365318059921265},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4882502853870392},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.44693949818611145},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44384005665779114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36816897988319397},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36419105529785156},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.15425467491149902},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10010087490081787},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687402","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2145836866","https://openalex.org/W2803255133","https://openalex.org/W2909431601"],"abstract_inverted_index":{"Implementing":[0],"cross-modal":[1,21],"hashing":[2,60],"between":[3,40,64],"2D":[4,41],"images":[5,65],"and":[6,34,42,66,75,96],"3D":[7],"point-cloud":[8,67],"data":[9,120],"is":[10,125],"a":[11,80],"growing":[12],"concern":[13],"in":[14],"real-world":[15],"retrieval":[16,63],"systems.":[17],"Simply":[18],"applying":[19],"existing":[20],"approaches":[22],"to":[23,28,107,127],"this":[24],"new":[25],"task":[26],"fails":[27],"adequately":[29],"capture":[30,128],"latent":[31],"multi-modal":[32,105,113,136],"semantics":[33],"effectively":[35,97],"bridge":[36],"the":[37,92,99,109,117,123,134,153],"modality":[38,100],"gap":[39],"3D.":[43],"To":[44],"address":[45],"these":[46],"issues":[47],"without":[48],"relying":[49],"on":[50,147],"hand-crafted":[51],"labels,":[52],"we":[53,103],"propose":[54],"contrastive":[55,85],"masked":[56,118],"autoencoders":[57],"based":[58],"self-supervised":[59],"(CMAH)":[61],"for":[62,91],"data.":[68],"We":[69],"start":[70],"by":[71],"contrasting":[72],"2D-3D":[73],"pairs":[74],"explicitly":[76],"constraining":[77],"them":[78],"into":[79],"joint":[81],"Hamming":[82],"space.":[83],"This":[84],"learning":[86],"process":[87],"ensures":[88],"robust":[89],"discriminability":[90],"generated":[93],"hash":[94],"codes":[95],"reduces":[98],"gap.":[101],"Moreover,":[102],"utilize":[104],"auto-encoders":[106],"enhance":[108],"model\u2019s":[110],"understanding":[111],"of":[112],"semantics.":[114],"By":[115],"completing":[116],"image/point-cloud":[119],"modeling":[121],"task,":[122],"model":[124],"encouraged":[126],"more":[129],"localized":[130],"clues.":[131],"In":[132],"addition,":[133],"proposed":[135,154],"fusion":[137],"block":[138],"facilitates":[139],"fine-grained":[140],"interactions":[141],"among":[142],"different":[143],"modalities.":[144],"Extensive":[145],"experiments":[146],"three":[148],"public":[149],"datasets":[150],"demonstrate":[151],"that":[152],"CMAH":[155],"significantly":[156],"outperforms":[157],"all":[158],"baseline":[159],"methods.":[160]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}