{"id":"https://openalex.org/W6943923507","doi":"https://doi.org/10.17615/tz1x-se79","title":"Recognizing Fine-Grained Object Instances for Robotics Applications","display_name":"Recognizing Fine-Grained Object Instances for Robotics Applications","publication_year":2020,"publication_date":"2020-02-11","ids":{"openalex":"https://openalex.org/W6943923507","doi":"https://doi.org/10.17615/tz1x-se79"},"language":"en","primary_location":{"id":"doi:10.17615/tz1x-se79","is_oa":true,"landing_page_url":"https://doi.org/10.17615/tz1x-se79","pdf_url":null,"source":{"id":"https://openalex.org/S7407051488","display_name":"UNC Libraries","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"thesis"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.17615/tz1x-se79","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ammirato, Philip Gary","orcid":null},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ammirato, Philip Gary","raw_affiliation_strings":["University of North Carolina at Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114027177"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.4726000130176544,"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":0.4726000130176544,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.08020000159740448,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.07240000367164612,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6832000017166138},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6690000295639038},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.5985999703407288},{"id":"https://openalex.org/keywords/3d-single-object-recognition","display_name":"3D single-object recognition","score":0.5954999923706055},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5845999717712402},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5827999711036682},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.44440001249313354},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.42260000109672546},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.412200003862381}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8259000182151794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763000130653381},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6832000017166138},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6690000295639038},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.5985999703407288},{"id":"https://openalex.org/C14551309","wikidata":"https://www.wikidata.org/wiki/Q4636325","display_name":"3D single-object recognition","level":4,"score":0.5954999923706055},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5866000056266785},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5845999717712402},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5827999711036682},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.44440001249313354},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.33230000734329224},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.304500013589859},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.2969000041484833},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.28220000863075256},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.25619998574256897},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.17615/tz1x-se79","is_oa":true,"landing_page_url":"https://doi.org/10.17615/tz1x-se79","pdf_url":null,"source":{"id":"https://openalex.org/S7407051488","display_name":"UNC Libraries","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"thesis"}],"best_oa_location":{"id":"doi:10.17615/tz1x-se79","is_oa":true,"landing_page_url":"https://doi.org/10.17615/tz1x-se79","pdf_url":null,"source":{"id":"https://openalex.org/S7407051488","display_name":"UNC Libraries","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"thesis"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"State-of-the-art":[0],"object":[1,27,53,88,127,154,161],"recognition":[2,50,89],"systems,":[3],"and":[4,13,33,62,80,104,129],"computer":[5,83],"vision":[6,84],"methods":[7],"in":[8],"general,":[9],"are":[10],"getting":[11],"better":[12,14],"at":[15,75],"a":[16,57,117,152],"variety":[17],"of":[18,21,39,51,60],"tasks.":[19,90],"Many":[20],"these":[22],"techniques":[23,85],"focus":[24,123],"on":[25,124],"general":[26],"categories,":[28],"like":[29],"person":[30],"or":[31,37],"bottle,":[32],"use":[34],"many":[35],"hundreds":[36],"thousands":[38],"training":[40,68,139],"examples":[41],"per":[42],"category.":[43],"Some":[44],"domains,":[45],"such":[46,55],"as":[47,56],"robotics,":[48],"require":[49],"fine-grained":[52,87,126],"instances,":[54,128],"16oz.":[58],"bottle":[59],"Coke,":[61],"only":[63],"have":[64],"access":[65],"to":[66,77,122,133,135,150,160],"limited":[67],"data.":[69],"In":[70],"this":[71],"work":[72],"we":[73],"look":[74],"how":[76],"build":[78],"data":[79],"adapt":[81],"successful":[82],"for":[86,101],"Our":[91,110,141],"Active":[92],"Vision":[93],"Dataset":[94],"is":[95,158],"the":[96,131,145],"first":[97],"deep-learning":[98],"scale":[99],"dataset":[100],"instance":[102],"detection":[103],"motion":[105],"simulation":[106],"using":[107],"real":[108],"images.":[109],"Target":[111],"Driven":[112],"Instance":[113],"Detection":[114],"method":[115,143],"uses":[116],"siamese":[118],"convolutional":[119],"neural":[120],"network":[121],"specific":[125],"has":[130],"capacity":[132],"generalize":[134],"instances":[136],"outside":[137],"its":[138],"set.":[140],"SymGan":[142],"used":[144],"Generative":[146],"Adversarial":[147],"Network":[148],"paradigm":[149],"train":[151],"3D":[153],"orientation":[155],"predictor":[156],"that":[157],"robust":[159],"symmetries.":[162]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}