{"id":"https://openalex.org/W4415539940","doi":"https://doi.org/10.1145/3746027.3755684","title":"Dynamic Optimization Noisy Cross-Modal Hashing","display_name":"Dynamic Optimization Noisy Cross-Modal Hashing","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539940","doi":"https://doi.org/10.1145/3746027.3755684"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755684","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5120132200","display_name":"Zebing Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zebing Yao","raw_affiliation_strings":["Yanshan University, Qinhuangdao, China"],"affiliations":[{"raw_affiliation_string":"Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120132201","display_name":"Hao Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Fu","raw_affiliation_strings":["Yanshan University, Qinhuangdao, China"],"affiliations":[{"raw_affiliation_string":"Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068017886","display_name":"Y.H. Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanhang Yang","raw_affiliation_strings":["Yanshan University, Qinhuangdao, China"],"affiliations":[{"raw_affiliation_string":"Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080706260","display_name":"Guanghua Gu","orcid":"https://orcid.org/0000-0002-9532-8273"},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanghua Gu","raw_affiliation_strings":["Yanshan University, Qinhuangdao, China"],"affiliations":[{"raw_affiliation_string":"Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5120132200"],"corresponding_institution_ids":["https://openalex.org/I39333907"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32547741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2113","last_page":"2121"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9945999979972839,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9944999814033508,"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/overfitting","display_name":"Overfitting","score":0.6682999730110168},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6323000192642212},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6309999823570251},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5820000171661377},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.48919999599456787},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4408999979496002},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.439300000667572},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43209999799728394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796500027179718},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6682999730110168},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6323000192642212},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6309999823570251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6118000149726868},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5820000171661377},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.48919999599456787},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4846000075340271},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4408999979496002},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4205000102519989},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39480000734329224},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C133667856","wikidata":"https://www.wikidata.org/wiki/Q5439682","display_name":"Feature hashing","level":5,"score":0.33739998936653137},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.3176000118255615},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.3084999918937683},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.27160000801086426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755684","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2106277773","https://openalex.org/W2155803963","https://openalex.org/W2566079294","https://openalex.org/W3155471926","https://openalex.org/W4233762729"],"related_works":[],"abstract_inverted_index":{"Cross-Modal":[0,62,120],"Hashing":[1,63,121],"(CMH)":[2],"has":[3],"gained":[4],"significant":[5],"attention":[6],"for":[7,118],"its":[8],"ability":[9],"to":[10,66,72,91,101,158,170],"learn":[11],"semantic":[12],"category":[13],"discrimination":[14],"and":[15,42,128,176,203],"enable":[16],"efficient":[17],"retrieval.":[18],"However,":[19],"in":[20,148],"practical":[21],"applications,":[22],"the":[23,31,68,86,137,155,172,193,198],"massive":[24],"amounts":[25],"of":[26,70,140,174,200],"multi-modal":[27],"data":[28],"collected":[29],"from":[30,179],"internet":[32],"often":[33],"contain":[34],"coarse":[35],"annotations,":[36],"which":[37,123],"inevitably":[38],"introduce":[39,109],"noisy":[40,73,98,159,201],"labels":[41,74,202],"degrade":[43],"retrieval":[44,207],"performance.":[45,208],"To":[46],"address":[47],"this":[48,50],"challenge,":[49],"paper":[51],"proposes":[52],"a":[53,79,111,132,163],"dynamic":[54],"optimization-based":[55],"training":[56,106],"framework,":[57],"namely":[58],"Dynamic":[59],"Optimization":[60],"Noisy":[61,119],"(DONCMH).":[64],"Firstly,":[65],"alleviate":[67],"issue":[69],"overfitting":[71],"during":[75],"training,":[76],"we":[77,108],"propose":[78],"novel":[80,112],"regularization-based":[81],"noise-robust":[82],"strategy":[83],"that":[84,192],"updates":[85],"target":[87],"distribution":[88,139,145],"with":[89],"momentum":[90],"optimize":[92],"clustering":[93],"learning,":[94,151],"thus":[95],"avoiding":[96],"over-emphasizing":[97],"samples.":[99],"Secondly,":[100],"more":[102],"accurately":[103],"select":[104],"high-quality":[105],"samples,":[107,141],"ClusterOT,":[110],"Optimal":[113],"Transport":[114],"formulation":[115],"explicitly":[116],"tailored":[117],"(NCMH),":[122],"integrates":[124],"center":[125,149],"representation":[126,150],"learning":[127,166],"cross-modal":[129,206],"alignment":[130],"into":[131],"unified":[133],"structure.":[134],"By":[135],"leveraging":[136],"spatial":[138],"ClusterOT":[142],"effectively":[143,196],"mitigates":[144,197],"imbalances":[146],"inherent":[147],"thereby":[152],"significantly":[153,204],"improving":[154],"model's":[156],"robustness":[157],"label":[160],"predictions.":[161],"Finally,":[162],"robust":[164],"feature":[165],"module":[167],"is":[168],"employed":[169],"enhance":[171],"extraction":[173],"informative":[175],"discriminative":[177],"representations":[178],"both":[180],"modalities.":[181],"Extensive":[182],"experiments":[183],"conducted":[184],"on":[185],"four":[186],"widely":[187],"used":[188],"benchmark":[189],"datasets":[190],"demonstrate":[191],"proposed":[194],"method":[195],"impact":[199],"improves":[205]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-25T00:00:00"}