{"id":"https://openalex.org/W2504949052","doi":"https://doi.org/10.1109/dicta.2016.7797039","title":"Exploiting Temporal Information for DCNN-Based Fine-Grained Object Classification","display_name":"Exploiting Temporal Information for DCNN-Based Fine-Grained Object Classification","publication_year":2016,"publication_date":"2016-11-01","ids":{"openalex":"https://openalex.org/W2504949052","doi":"https://doi.org/10.1109/dicta.2016.7797039","mag":"2504949052"},"language":"en","primary_location":{"id":"doi:10.1109/dicta.2016.7797039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta.2016.7797039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1608.00486","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"ZongYuan Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"ZongYuan Ge","raw_affiliation_strings":["Australian Centre for Robotic Vision, University of Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Centre for Robotic Vision, University of Adelaide, Australia","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chris McCool","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chris McCool","raw_affiliation_strings":["Australian Centre for Robotic Vision, University of Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Centre for Robotic Vision, University of Adelaide, Australia","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Conrad Sanderson","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Conrad Sanderson","raw_affiliation_strings":["Australian Centre for Robotic Vision, University of Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Centre for Robotic Vision, University of Adelaide, Australia","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Peng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["Australian Centre for Robotic Vision, University of Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Centre for Robotic Vision, University of Adelaide, Australia","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lingqiao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lingqiao Liu","raw_affiliation_strings":["Australian Centre for Robotic Vision, University of Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Centre for Robotic Vision, University of Adelaide, Australia","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ian Reid","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ian Reid","raw_affiliation_strings":["Australian Centre for Robotic Vision, University of Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Centre for Robotic Vision, University of Adelaide, Australia","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":null,"display_name":"Peter Corke","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peter Corke","raw_affiliation_strings":["Australian Centre for Robotic Vision, University of Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Centre for Robotic Vision, University of Adelaide, Australia","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2012,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.52228596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9973999857902527,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9973999857902527,"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":0.9958000183105469,"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":0.9919000267982483,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6796000003814697},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.6639999747276306},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.6589000225067139},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6011000275611877},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.5486000180244446},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5235999822616577},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4683000147342682},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.4578999876976013}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7296000123023987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7010999917984009},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6796000003814697},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6639999747276306},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6589000225067139},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6011000275611877},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.5486000180244446},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5235999822616577},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4578999876976013},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.32350000739097595},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2712000012397766},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/dicta.2016.7797039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta.2016.7797039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1608.00486","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1608.00486","pdf_url":"https://arxiv.org/pdf/1608.00486","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},{"id":"pmh:oai:digital.library.adelaide.edu.au:2440/105001","is_oa":false,"landing_page_url":"http://hdl.handle.net/2440/105001","pdf_url":null,"source":{"id":"https://openalex.org/S4306401835","display_name":"Adelaide Research & Scholarship (AR&S) (University of Adelaide)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5681781","host_organization_name":"The University of Adelaide","host_organization_lineage":["https://openalex.org/I5681781"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dx.doi.org/10.1109/dicta.2016.7797039","raw_type":"Conference paper"},{"id":"pmh:oai:research-repository.griffith.edu.au:10072/395907","is_oa":false,"landing_page_url":"http://hdl.handle.net/10072/395907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference output"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1608.00486","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1608.00486","pdf_url":"https://arxiv.org/pdf/1608.00486","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331724","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1556540526","https://openalex.org/W1923404803","https://openalex.org/W1995543189","https://openalex.org/W1996904744","https://openalex.org/W2016053056","https://openalex.org/W2031489346","https://openalex.org/W2079789819","https://openalex.org/W2094116030","https://openalex.org/W2104657103","https://openalex.org/W2110765924","https://openalex.org/W2118696714","https://openalex.org/W2126579184","https://openalex.org/W2130827850","https://openalex.org/W2135706578","https://openalex.org/W2155893237","https://openalex.org/W2256837533","https://openalex.org/W6600983433","https://openalex.org/W6602324145","https://openalex.org/W6618372016","https://openalex.org/W6620707391","https://openalex.org/W6631760426","https://openalex.org/W6639126518","https://openalex.org/W6682132143","https://openalex.org/W6682778277","https://openalex.org/W6682864246","https://openalex.org/W6684191040"],"related_works":[],"abstract_inverted_index":{"Fine-grained":[0],"classification":[1,174,200],"is":[2,132,176],"a":[3,14,43,50],"relatively":[4],"new":[5,45,167],"field":[6],"that":[7],"has":[8],"concentrated":[9],"on":[10],"using":[11,23,186],"information":[12,121,156],"from":[13,92,122,178],"single":[15,181],"image,":[16],"while":[17],"ignoring":[18],"the":[19,34,68,82,104,112,116,123,127,140,147,152,158,166,187,199],"enormous":[20],"potential":[21],"of":[22,37,53,81,103,111,115,126,146,172],"video":[24,46,170],"data":[25,91],"to":[26,67,150,183,202],"improve":[27],"classification.":[28],"In":[29],"this":[30],"work":[31],"we":[32,64],"present":[33],"novel":[35],"task":[36],"video-based":[38],"fine-grained":[39],"object":[40],"classification,":[41],"propose":[42],"corresponding":[44],"dataset,":[47],"and":[48,76,89,107,129,143,154,160,168],"perform":[49],"systematic":[51],"study":[52],"several":[54],"recent":[55],"deep":[56],"convolutional":[57,124],"neural":[58],"network":[59],"(DCNN)":[60],"based":[61],"approaches,":[62],"which":[63],"specifically":[65],"adapt":[66],"task.":[69],"We":[70,137],"evaluate":[71],"three-dimensional":[72],"DCNNs,":[73,75,120],"two-stream":[74,83,148],"bilinear":[77,119,141],"DCNNs.":[78],"Two":[79],"forms":[80],"approach":[84,149],"are":[85,96],"used,":[86],"where":[87],"spatial":[88,128,153],"temporal":[90,130,155],"two":[93],"independent":[94],"DCNNs":[95,131],"fused":[97],"either":[98],"via":[99,134],"early":[100,144],"fusion":[101,109,145],"(combination":[102],"fully-connected":[105],"layers)":[106],"late":[108],"(concatenation":[110],"softmax":[113],"outputs":[114],"DCNNs).":[117],"For":[118],"layers":[125],"combined":[133],"local":[135,159],"co-occurrences.":[136],"then":[138],"fuse":[139],"DCNN":[142],"combine":[151],"at":[157],"global":[161],"level":[162],"(Spatio-Temporal":[163],"Co-occurrence).":[164],"Using":[165],"challenging":[169],"dataset":[171],"birds,":[173],"performance":[175],"improved":[177],"23.1%":[179],"(using":[180],"images)":[182],"41.1%":[184],"when":[185],"Spatio-Temporal":[188],"Co-occurrence":[189],"system.":[190],"Incorporating":[191],"automatically":[192],"detected":[193],"bounding":[194],"box":[195],"location":[196],"further":[197],"improves":[198],"accuracy":[201],"53.6%.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2016-08-23T00:00:00"}