{"id":"https://openalex.org/W7125927348","doi":"https://doi.org/10.1109/smc58881.2025.11343627","title":"ConMH-Based Multi-Modal Video Retrieval with Contrastive Hashing and Fusion","display_name":"ConMH-Based Multi-Modal Video Retrieval with Contrastive Hashing and Fusion","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125927348","doi":"https://doi.org/10.1109/smc58881.2025.11343627"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5124057603","display_name":"Rongye Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rongye Ling","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China,510006"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China,510006","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100421076","display_name":"Juan Li","orcid":"https://orcid.org/0000-0003-3520-6191"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingrou Li","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China,510006"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China,510006","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124107690","display_name":"Wing W. Y. Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wing W. Y. Ng","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China,510006"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China,510006","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106724391","display_name":"Qihua Li","orcid":"https://orcid.org/0009-0006-0937-9012"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihua Li","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China,510006"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China,510006","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030825059","display_name":"Xing Tian","orcid":"https://orcid.org/0000-0002-7546-1018"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Tian","raw_affiliation_strings":["South China Normal University,School of Artificial Intelligence,Guangzhou,China,510631"],"affiliations":[{"raw_affiliation_string":"South China Normal University,School of Artificial Intelligence,Guangzhou,China,510631","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124084866","display_name":"Xingfu Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingfu Yan","raw_affiliation_strings":["South China Normal University,School of Computer Science,Guangzhou,China,510631"],"affiliations":[{"raw_affiliation_string":"South China Normal University,School of Computer Science,Guangzhou,China,510631","institution_ids":["https://openalex.org/I187400657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5124057603"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68609906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"728","last_page":"733"},"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":0.5579000115394592,"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":0.5579000115394592,"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":0.08659999817609787,"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":0.07620000094175339,"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/hash-function","display_name":"Hash function","score":0.6959999799728394},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5303000211715698},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.4959999918937683},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.48660001158714294},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4494999945163727},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.39969998598098755},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.39309999346733093},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.38830000162124634},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.38519999384880066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8597000241279602},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6959999799728394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5426999926567078},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5303000211715698},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.4959999918937683},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.48660001158714294},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4494999945163727},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42980000376701355},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.38519999384880066},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.3666999936103821},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3492000102996826},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3343999981880188},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C133667856","wikidata":"https://www.wikidata.org/wiki/Q5439682","display_name":"Feature hashing","level":5,"score":0.328000009059906},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32760000228881836},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.29249998927116394},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8464381098747253,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"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":11,"referenced_works":["https://openalex.org/W1566135517","https://openalex.org/W1974647172","https://openalex.org/W2074668987","https://openalex.org/W2124386111","https://openalex.org/W2151103935","https://openalex.org/W2162006472","https://openalex.org/W2527195341","https://openalex.org/W2786585376","https://openalex.org/W2979656080","https://openalex.org/W3173956867","https://openalex.org/W4382240197"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,28,87],"rapid":[2],"progress":[3],"of":[4,30],"urbanization,":[5],"city":[6],"governance":[7],"faces":[8],"growing":[9],"challenges":[10],"such":[11],"as":[12],"traffic":[13],"violations":[14],"and":[15,24,32,65,105,119,126,138,152,156],"environmental":[16],"pollution.":[17],"Traditional":[18],"manual":[19],"monitoring":[20,31],"methods":[21],"are":[22],"inefficient":[23],"costly.":[25],"To":[26,96],"enhance":[27],"efficiency":[29],"managing":[33],"uncivil":[34,48],"behaviors":[35],"in":[36,86,136],"urban":[37],"environments,":[38],"we":[39,100],"propose":[40],"a":[41,69,109],"self-supervised":[42],"video":[43,64],"hashing":[44,89],"retrieval":[45,98,150],"framework":[46,142],"for":[47,62],"behavior":[49],"recognition.":[50],"Leveraging":[51],"deep":[52],"learning":[53],"techniques,":[54],"our":[55,131],"method":[56,114],"generates":[57],"compact":[58],"binary":[59,160],"hash":[60],"codes":[61],"both":[63],"text":[66,88],"modalities":[67],"via":[68],"contrastive":[70],"masked":[71],"autoencoder":[72],"(ConMH),":[73],"enabling":[74],"efficient":[75],"large-scale":[76],"retrieval.":[77],"We":[78],"further":[79],"improve":[80],"ConMH":[81],"by":[82],"introducing":[83],"cross-attention":[84],"mechanisms":[85],"branch":[90],"to":[91],"better":[92],"handle":[93],"context":[94],"dependencies.":[95],"optimize":[97],"results,":[99],"integrate":[101],"five":[102],"multimodal":[103],"fusion":[104],"ranking":[106],"strategies,":[107],"including":[108],"novel":[110],"Hybrid":[111],"Distance-Rank":[112],"Fusion":[113],"that":[115,130],"balances":[116],"similarity":[117],"scores":[118],"rank":[120],"information.":[121],"Experiments":[122],"conducted":[123],"on":[124],"MSRVTT":[125],"MSVD":[127],"datasets":[128],"demonstrate":[129],"approach":[132],"achieves":[133],"superior":[134],"performance":[135],"mAP@K":[137],"NDCG":[139],"metrics.":[140],"The":[141],"significantly":[143],"enhances":[144],"cross-modal":[145],"semantic":[146],"coverage,":[147],"ensures":[148],"high":[149],"precision,":[151],"maintains":[153],"low":[154],"computational":[155],"storage":[157],"overhead":[158],"through":[159],"encoding.":[161]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-29T00:00:00"}