{"id":"https://openalex.org/W2527197300","doi":"https://doi.org/10.1145/2964284.2964324","title":"Cross-batch Reference Learning for Deep Classification and Retrieval","display_name":"Cross-batch Reference Learning for Deep Classification and Retrieval","publication_year":2016,"publication_date":"2016-09-29","ids":{"openalex":"https://openalex.org/W2527197300","doi":"https://doi.org/10.1145/2964284.2964324","mag":"2527197300"},"language":"en","primary_location":{"id":"doi:10.1145/2964284.2964324","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2964324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th 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/A5019328343","display_name":"Huei\u2010Fang Yang","orcid":"https://orcid.org/0000-0001-8261-6965"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Huei-Fang Yang","raw_affiliation_strings":["Academia Sinica, Taipei, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108030232","display_name":"Kevin Lin","orcid":"https://orcid.org/0000-0001-8944-1336"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kevin Lin","raw_affiliation_strings":["Academia Sinica, Taipei, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072890368","display_name":"Chu\u2010Song Chen","orcid":"https://orcid.org/0000-0002-2959-2471"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chu-Song Chen","raw_affiliation_strings":["Academia Sinica, Taipei, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I84653119"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1237","last_page":"1246"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9980000257492065,"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":0.7801501750946045},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.761745035648346},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.690853476524353},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6316790580749512},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6242897510528564},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6048256754875183},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5936186909675598},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5833649039268494},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5402931571006775},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5327271223068237},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46817153692245483},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46538272500038147},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41615766286849976},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34728091955184937},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2762569189071655}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7801501750946045},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.761745035648346},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.690853476524353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6316790580749512},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6242897510528564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6048256754875183},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5936186909675598},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5833649039268494},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5402931571006775},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5327271223068237},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46817153692245483},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46538272500038147},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41615766286849976},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34728091955184937},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2762569189071655},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2964284.2964324","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2964284.2964324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6700000166893005,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W204268067","https://openalex.org/W1524680991","https://openalex.org/W1606858007","https://openalex.org/W1922773808","https://openalex.org/W1974647172","https://openalex.org/W1984309565","https://openalex.org/W1999956270","https://openalex.org/W2017814585","https://openalex.org/W2038752770","https://openalex.org/W2045143396","https://openalex.org/W2049744691","https://openalex.org/W2055667362","https://openalex.org/W2059001985","https://openalex.org/W2062118960","https://openalex.org/W2064797228","https://openalex.org/W2094050922","https://openalex.org/W2095569536","https://openalex.org/W2097117768","https://openalex.org/W2102605133","https://openalex.org/W2103924867","https://openalex.org/W2106053110","https://openalex.org/W2117539524","https://openalex.org/W2123229215","https://openalex.org/W2127176025","https://openalex.org/W2128877075","https://openalex.org/W2141362318","https://openalex.org/W2142537246","https://openalex.org/W2147238549","https://openalex.org/W2148809531","https://openalex.org/W2150856297","https://openalex.org/W2151103935","https://openalex.org/W2153273131","https://openalex.org/W2155541015","https://openalex.org/W2155893237","https://openalex.org/W2156303437","https://openalex.org/W2161381512","https://openalex.org/W2164022341","https://openalex.org/W2183182206","https://openalex.org/W2194775991","https://openalex.org/W2204975001","https://openalex.org/W2212363941","https://openalex.org/W2293824885","https://openalex.org/W2618530766","https://openalex.org/W2949447708","https://openalex.org/W2953106684","https://openalex.org/W2962835968","https://openalex.org/W2963542991","https://openalex.org/W2963911037","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W2761785940","https://openalex.org/W156213964","https://openalex.org/W2050960118","https://openalex.org/W2129933262","https://openalex.org/W2123991572","https://openalex.org/W4390143830"],"abstract_inverted_index":{"Learning":[0],"feature":[1,36,61,102,196,246],"representations":[2,37,62],"for":[3,84,256,272],"image":[4,32,71,92],"retrieval":[5,97,164,191,276],"is":[6,75,159,198,236,252],"essential":[7],"to":[8,24,49,70,90,113,182,202,211,222],"multimedia":[9],"search":[10],"and":[11,31,34,177,187,254,263,275],"mining":[12],"applications.":[13],"Recently,":[14],"deep":[15,66],"convolutional":[16],"networks":[17],"(CNNs)":[18],"have":[19],"gained":[20],"much":[21],"attention":[22],"due":[23],"their":[25,88],"impressive":[26],"performance":[27,74],"on":[28,52,134,144,167,185,244,280],"object":[29],"detection":[30],"classification,":[33,85],"the":[35,53,60,73,96,100,115,128,135,145,149,152,168,175,190,206,216,227,242,245,249,260,267,284],"learned":[38,63,101,195,268],"from":[39],"a":[40,65,106,139,162,232],"large-scale":[41],"generic":[42],"dataset":[43],"(e.g.,":[44],"ImageNet)":[45],"can":[46],"be":[47,183,223],"transferred":[48],"or":[50,214],"fine-tuned":[51],"datasets":[54],"of":[55,99,119,124,189,215,241,248,286],"other":[56,153,213],"domains.":[57],"However,":[58],"when":[59],"with":[64],"CNN":[67],"are":[68,82,180,209,219,270],"applied":[69],"retrieval,":[72],"still":[76],"not":[77,132,199],"as":[78,80,161],"good":[79],"they":[81],"used":[83],"which":[86,251],"restricts":[87],"applicability":[89],"relevant":[91,176,210],"search.":[93],"To":[94,225],"ensure":[95],"capability":[98],"space,":[103],"we":[104,230],"introduce":[105],"new":[107],"idea":[108],"called":[109],"cross-batch":[110,163,228],"reference":[111],"(CBR)":[112],"enhance":[114],"stochastic-gradient-descent":[116],"(SGD)":[117],"training":[118,126,136],"CNNs.":[120],"In":[121],"each":[122,212],"iteration":[123],"our":[125,287],"process,":[127],"network":[129],"adjustment":[130],"relies":[131],"only":[133,200],"samples":[137,150,179,207],"in":[138,151],"single":[140],"batch,":[141],"but":[142,205],"also":[143,220],"information":[146],"passed":[147],"by":[148],"batches.":[154],"This":[155],"inter-batches":[156],"communication":[157],"mechanism":[158],"formulated":[160],"process":[165],"based":[166],"mean":[169],"average":[170],"precision":[171],"(MAP)":[172],"criterion,":[173],"where":[174],"irrelevant":[178],"encouraged":[181],"placed":[184],"top":[186],"rear":[188],"list,":[192],"respectively.":[193],"The":[194],"space":[197],"discriminative":[201],"different":[203],"classes,":[204],"that":[208,235],"same":[217],"class":[218],"enforced":[221],"centralized.":[224],"maximize":[226],"MAP,":[229],"design":[231],"loss":[233],"function":[234],"an":[237],"approximated":[238],"lower":[239],"bound":[240],"MAP":[243],"layer":[247],"network,":[250],"differentiable":[253],"easier":[255],"optimization.":[257],"By":[258],"combining":[259],"intra-batch":[261],"classification":[262,274],"inter-batch":[264],"cross-reference":[265],"losses,":[266],"features":[269],"effective":[271],"both":[273],"tasks.":[277],"Experimental":[278],"results":[279],"various":[281],"benchmarks":[282],"demonstrate":[283],"effectiveness":[285],"approach.":[288]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}