{"id":"https://openalex.org/W2922931507","doi":"https://doi.org/10.1109/cvpr.2019.00345","title":"Learning With Batch-Wise Optimal Transport Loss for 3D Shape Recognition","display_name":"Learning With Batch-Wise Optimal Transport Loss for 3D Shape Recognition","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2922931507","doi":"https://doi.org/10.1109/cvpr.2019.00345","mag":"2922931507"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2019.00345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2019.00345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.08923","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100440530","display_name":"Lin Xu","orcid":"https://orcid.org/0000-0003-4373-0591"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lin Xu","raw_affiliation_strings":["Institute of Advanced Artificial Intelligence (IAAI)"],"affiliations":[{"raw_affiliation_string":"Institute of Advanced Artificial Intelligence (IAAI)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004783670","display_name":"Han Sun","orcid":"https://orcid.org/0000-0002-2208-6672"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han Sun","raw_affiliation_strings":["Institute of Advanced Artificial Intelligence (IAAI)"],"affiliations":[{"raw_affiliation_string":"Institute of Advanced Artificial Intelligence (IAAI)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075188831","display_name":"Yuai Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuai Liu","raw_affiliation_strings":["Institute of Advanced Artificial Intelligence (IAAI)"],"affiliations":[{"raw_affiliation_string":"Institute of Advanced Artificial Intelligence (IAAI)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100440530"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1022,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.40944446,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3328","last_page":"3337"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9965000152587891,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9965000152587891,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9955000281333923,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9955000281333923,"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/mnist-database","display_name":"MNIST database","score":0.881961464881897},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7846566438674927},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7256813049316406},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6936032772064209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5893154740333557},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5619462132453918},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5300393104553223},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5208954811096191},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5204035043716431},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5021994113922119},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4532907009124756},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.4237244129180908},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07809627056121826}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.881961464881897},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7846566438674927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7256813049316406},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6936032772064209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5893154740333557},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5619462132453918},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5300393104553223},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5208954811096191},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5204035043716431},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5021994113922119},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4532907009124756},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4237244129180908},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07809627056121826},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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":4,"locations":[{"id":"doi:10.1109/cvpr.2019.00345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2019.00345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.08923","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.08923","pdf_url":"https://arxiv.org/pdf/1903.08923","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2922931507","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1903.08923","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1903.08923","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.08923","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.08923","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.08923","pdf_url":"https://arxiv.org/pdf/1903.08923","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2922931507.pdf"},"referenced_works_count":77,"referenced_works":["https://openalex.org/W191365292","https://openalex.org/W295048775","https://openalex.org/W1482825550","https://openalex.org/W1532499126","https://openalex.org/W1629010235","https://openalex.org/W1629559917","https://openalex.org/W1644641054","https://openalex.org/W1686810756","https://openalex.org/W1892078565","https://openalex.org/W1920022804","https://openalex.org/W1964566761","https://openalex.org/W1975517671","https://openalex.org/W2017765444","https://openalex.org/W2021354639","https://openalex.org/W2027554194","https://openalex.org/W2036163530","https://openalex.org/W2049716301","https://openalex.org/W2059917035","https://openalex.org/W2086234878","https://openalex.org/W2096733369","https://openalex.org/W2097117768","https://openalex.org/W2102605133","https://openalex.org/W2106053110","https://openalex.org/W2112796928","https://openalex.org/W2113307832","https://openalex.org/W2115667499","https://openalex.org/W2122111042","https://openalex.org/W2124561101","https://openalex.org/W2125483582","https://openalex.org/W2127589108","https://openalex.org/W2138621090","https://openalex.org/W2141362318","https://openalex.org/W2143668817","https://openalex.org/W2153635508","https://openalex.org/W2153649445","https://openalex.org/W2155541015","https://openalex.org/W2155806937","https://openalex.org/W2158131535","https://openalex.org/W2176040302","https://openalex.org/W2194775991","https://openalex.org/W2211722331","https://openalex.org/W2295332248","https://openalex.org/W2312355711","https://openalex.org/W2342223463","https://openalex.org/W2518780089","https://openalex.org/W2539033431","https://openalex.org/W2552476815","https://openalex.org/W2555897561","https://openalex.org/W2604164738","https://openalex.org/W2749056374","https://openalex.org/W2951798229","https://openalex.org/W2952320381","https://openalex.org/W2962798895","https://openalex.org/W2963026686","https://openalex.org/W2963775347","https://openalex.org/W2964176323","https://openalex.org/W3099206234","https://openalex.org/W3135946615","https://openalex.org/W4229855683","https://openalex.org/W6615672858","https://openalex.org/W6631637103","https://openalex.org/W6636708570","https://openalex.org/W6637373629","https://openalex.org/W6640300118","https://openalex.org/W6675751002","https://openalex.org/W6676931166","https://openalex.org/W6678960063","https://openalex.org/W6682778277","https://openalex.org/W6682962330","https://openalex.org/W6683390034","https://openalex.org/W6684191040","https://openalex.org/W6726726311","https://openalex.org/W6729358208","https://openalex.org/W6730323794","https://openalex.org/W6735945695","https://openalex.org/W6736612982","https://openalex.org/W6898611122"],"related_works":["https://openalex.org/W2964268240","https://openalex.org/W2935456071","https://openalex.org/W2404287519","https://openalex.org/W2270409809","https://openalex.org/W2966777502","https://openalex.org/W3180805579","https://openalex.org/W2482453869","https://openalex.org/W2974265398","https://openalex.org/W2689134854","https://openalex.org/W2921310091","https://openalex.org/W2775085707","https://openalex.org/W2963113119","https://openalex.org/W3103740959","https://openalex.org/W2981213835","https://openalex.org/W2527197300","https://openalex.org/W3035119337","https://openalex.org/W3135824164","https://openalex.org/W2904631550","https://openalex.org/W3035604016","https://openalex.org/W2794492892"],"abstract_inverted_index":{"Deep":[0],"metric":[1,60,97,107],"learning":[2,98],"is":[3],"essential":[4],"for":[5,113],"visual":[6,118],"recognition.":[7,114],"The":[8],"widely":[9],"used":[10],"pair-wise":[11],"(or":[12],"triplet)":[13],"based":[14],"loss":[15,89],"objectives":[16],"cannot":[17],"make":[18],"full":[19],"use":[20,101],"of":[21,67,138],"semantical":[22],"information":[23],"in":[24,80,93,157],"training":[25],"samples":[26,34],"or":[27],"give":[28],"enough":[29],"attention":[30],"to":[31,55,77,103],"those":[32],"hard":[33,73],"during":[35],"optimization.":[36],"Thus,":[37],"they":[38],"often":[39],"suffer":[40],"from":[41,65],"a":[42,84,151],"slow":[43],"convergence":[44,146],"rate":[45,147],"and":[46,75,90,108,120,133],"inferior":[47],"performance.":[48,154],"In":[49],"this":[50],"paper,":[51],"we":[52,162],"show":[53,163],"how":[54],"learn":[56,104],"an":[57,94],"importance-driven":[58],"distance":[59,106],"via":[61],"optimal":[62,87],"transport":[63,88],"programming":[64],"batches":[66],"samples.":[68],"It":[69,142],"can":[70,143,167,178],"automatically":[71],"emphasize":[72],"examples":[74],"lead":[76],"significant":[78],"improvements":[79],"convergence.":[81],"We":[82,100],"propose":[83],"new":[85],"batch-wise":[86],"combine":[91],"it":[92,102],"end-to-end":[95],"deep":[96,109],"manner.":[99],"the":[105,136,139,145],"feature":[110],"representation":[111],"jointly":[112],"Empirical":[115],"results":[116],"on":[117],"retrieval":[119],"classification":[121],"tasks":[122],"with":[123],"six":[124],"benchmark":[125],"datasets,":[126],"i.e.,":[127],"MNIST,":[128],"CIFAR10,":[129],"SHREC13,":[130],"SHREC14,":[131],"ModelNet10,":[132],"ModelNet40,":[134],"demonstrate":[135],"superiority":[137],"proposed":[140],"method.":[141],"accelerate":[144],"significantly":[148],"while":[149],"achieving":[150],"state-of-the-art":[152],"recognition":[153,160,170,185],"For":[155],"example,":[156],"3D":[158,183],"shape":[159,184],"experiments,":[161],"that":[164],"our":[165],"method":[166],"achieve":[168],"better":[169],"performance":[171],"within":[172],"only":[173],"5":[174],"epochs":[175],"than":[176],"what":[177],"be":[179],"obtained":[180],"by":[181],"mainstream":[182],"approaches":[186],"after":[187],"200":[188],"epochs.":[189]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}