{"id":"https://openalex.org/W4200595213","doi":"https://doi.org/10.1109/iros51168.2021.9636725","title":"VoluMon: Weakly-Supervised Volumetric Monocular Estimation with Ellipsoid Representations","display_name":"VoluMon: Weakly-Supervised Volumetric Monocular Estimation with Ellipsoid Representations","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W4200595213","doi":"https://doi.org/10.1109/iros51168.2021.9636725"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9636725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636725","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1721.1/145528","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091371230","display_name":"Katherine Liu","orcid":"https://orcid.org/0000-0002-9616-9403"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine Liu","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology in Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology in Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063242159","display_name":"Kyel Ok","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyel Ok","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology in Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology in Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103263485","display_name":"Nicholas Roy","orcid":"https://orcid.org/0000-0001-9307-4196"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Roy","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology in Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology in Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.563,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63315177,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"5686","last_page":"5693"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10653","display_name":"Robot Manipulation and Learning","score":0.9977999925613403,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.9947999715805054,"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/minimum-bounding-box","display_name":"Minimum bounding box","score":0.8387794494628906},{"id":"https://openalex.org/keywords/ellipsoid","display_name":"Ellipsoid","score":0.7951784133911133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7134035229682922},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.7061773538589478},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6660959720611572},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.6449605226516724},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5858228206634521},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.49132075905799866},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48400017619132996},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.47506922483444214},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.44687020778656006},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38777613639831543},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2734120190143585},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2614929974079132},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09372520446777344}],"concepts":[{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.8387794494628906},{"id":"https://openalex.org/C57489055","wikidata":"https://www.wikidata.org/wiki/Q190046","display_name":"Ellipsoid","level":2,"score":0.7951784133911133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7134035229682922},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.7061773538589478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6660959720611572},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6449605226516724},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5858228206634521},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.49132075905799866},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48400017619132996},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.47506922483444214},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.44687020778656006},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38777613639831543},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2734120190143585},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2614929974079132},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09372520446777344},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros51168.2021.9636725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636725","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/145528","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/145528","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/145528","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/145528","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1517129425","https://openalex.org/W1526868886","https://openalex.org/W1861492603","https://openalex.org/W1991264156","https://openalex.org/W2033819227","https://openalex.org/W2109384047","https://openalex.org/W2123564600","https://openalex.org/W2150066425","https://openalex.org/W2184393491","https://openalex.org/W2468368736","https://openalex.org/W2610694266","https://openalex.org/W2798182271","https://openalex.org/W2799123546","https://openalex.org/W2884081170","https://openalex.org/W2891708887","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963188159","https://openalex.org/W2963675327","https://openalex.org/W2967044683","https://openalex.org/W2968147691","https://openalex.org/W2969050719","https://openalex.org/W2981857055","https://openalex.org/W3015446194","https://openalex.org/W3106250896","https://openalex.org/W3127066163","https://openalex.org/W4289489637","https://openalex.org/W6631711059","https://openalex.org/W6639102338","https://openalex.org/W6686211706","https://openalex.org/W6737681624","https://openalex.org/W6750544687","https://openalex.org/W6753334208","https://openalex.org/W6754677871","https://openalex.org/W6754872604","https://openalex.org/W6775913045","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W2167422950","https://openalex.org/W2128588724","https://openalex.org/W3036286480","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W4237171675","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"approaches":[2],"to":[3,14,29,95,99,110,114,124,133],"estimating":[4],"3D":[5,33,44,167],"object":[6,73,82,129],"pose":[7,160],"and":[8,77,103,141,171],"geometry":[9,83],"present":[10,52],"an":[11],"attractive":[12],"alternative":[13],"online":[15,136,143],"estimation":[16,23,61,130,139],"techniques,":[17],"which":[18,162],"can":[19,87],"suffer":[20],"from":[21,183],"significant":[22],"latency.":[24],"However,":[25],"a":[26,39,53,115,119,134,156,184,189],"practical":[27],"hurdle":[28],"training":[30],"state-of-the-art":[31],"deep":[32,158],"bounding":[34,45,74,100,168],"box":[35,46,75,101,169],"estimators":[36],"is":[37,163],"collecting":[38],"sufficiently":[40],"large":[41],"dataset":[42,121,186],"of":[43,92,107,155],"labels.":[47],"In":[48],"this":[49],"work,":[50],"we":[51,86,126,150,177],"novel":[54],"framework":[55],"for":[56],"weakly":[57],"supervised":[58,164],"volumetric":[59],"monocular":[60,128],"(VoluMon)":[62],"that":[63],"requires":[64],"annotations":[65,102],"in":[66],"the":[67,89,93,104,108,153],"image":[68],"space":[69],"only,":[70],"i.e.,":[71],"associated":[72],"detections":[76],"instance":[78],"segmentation.":[79],"By":[80],"approximating":[81],"as":[84],"ellipsoids,":[85],"exploit":[88],"dual":[90],"form":[91,106],"ellipsoid":[94,109],"optimize":[96,111],"with":[97,112,122,165],"respect":[98,113],"primal":[105],"segmented":[116],"pointcloud.":[117],"For":[118],"simulated":[120],"access":[123],"ground-truth,":[125],"show":[127,178],"performance":[131,154],"similar":[132],"naive":[135],"depth":[137,146],"based":[138],"approach":[140,152],"after":[142],"refinement":[144],"when":[145],"images":[147],"are":[148],"available,":[149],"also":[151],"learned":[157],"6D":[159],"estimator,":[161],"projected":[166],"keypoints":[170],"assumes":[172],"known":[173],"model":[174],"dimensions.":[175],"Finally,":[176],"promising":[179],"qualitative":[180],"results":[181],"generated":[182],"real-world":[185],"collected":[187],"using":[188],"stereo":[190],"pair.":[191]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}