{"id":"https://openalex.org/W4285102456","doi":"https://doi.org/10.1109/icra46639.2022.9811747","title":"SAFIT: Segmentation-Aware Scene Flow with Improved Transformer","display_name":"SAFIT: Segmentation-Aware Scene Flow with Improved Transformer","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4285102456","doi":"https://doi.org/10.1109/icra46639.2022.9811747"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9811747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811747","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","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/A5025258583","display_name":"Yukang Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yukang Shi","raw_affiliation_strings":["School of Computer Science and Technology, Xi'an Jiaotong University,Xi'an,China,710049"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi'an Jiaotong University,Xi'an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006570986","display_name":"Kaisheng Ma","orcid":"https://orcid.org/0000-0001-9226-3366"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaisheng Ma","raw_affiliation_strings":["Institute for Interdisciplinary In-formation Sciences, Tsinghua University,Beijing,China,100080"],"affiliations":[{"raw_affiliation_string":"Institute for Interdisciplinary In-formation Sciences, Tsinghua University,Beijing,China,100080","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025258583"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.7191,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.79160131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10648","last_page":"10655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","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/T10531","display_name":"Advanced Vision and Imaging","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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.8408238291740417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7288144826889038},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7048811912536621},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.6993229985237122},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6340765357017517},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.5685615539550781},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5645474791526794},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.5475528836250305},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4384564459323883},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42431530356407166},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.41845273971557617},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3761546015739441},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.23158028721809387},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1371619701385498}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8408238291740417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7288144826889038},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7048811912536621},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6993229985237122},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6340765357017517},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.5685615539550781},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5645474791526794},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5475528836250305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4384564459323883},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42431530356407166},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41845273971557617},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3761546015739441},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.23158028721809387},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1371619701385498},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9811747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811747","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W764651262","https://openalex.org/W1522301498","https://openalex.org/W1921093919","https://openalex.org/W2049981393","https://openalex.org/W2098500213","https://openalex.org/W2129671742","https://openalex.org/W2168538937","https://openalex.org/W2286655030","https://openalex.org/W2548527721","https://openalex.org/W2560474170","https://openalex.org/W2560609797","https://openalex.org/W2560722161","https://openalex.org/W2594727217","https://openalex.org/W2612112834","https://openalex.org/W2770804203","https://openalex.org/W2788158258","https://openalex.org/W2795374598","https://openalex.org/W2896457183","https://openalex.org/W2899771611","https://openalex.org/W2918473435","https://openalex.org/W2919233342","https://openalex.org/W2962771259","https://openalex.org/W2963121255","https://openalex.org/W2963231572","https://openalex.org/W2963333168","https://openalex.org/W2963727135","https://openalex.org/W2963782415","https://openalex.org/W2964062501","https://openalex.org/W2964080601","https://openalex.org/W2971252756","https://openalex.org/W2971686478","https://openalex.org/W2979750740","https://openalex.org/W2991215750","https://openalex.org/W3008105217","https://openalex.org/W3010090948","https://openalex.org/W3024841368","https://openalex.org/W3034321406","https://openalex.org/W3096609285","https://openalex.org/W3097055324","https://openalex.org/W3100388886","https://openalex.org/W3106932526","https://openalex.org/W3107971425","https://openalex.org/W3109908659","https://openalex.org/W3153465022","https://openalex.org/W4385245566","https://openalex.org/W4394671432","https://openalex.org/W6631190155","https://openalex.org/W6687484953","https://openalex.org/W6739778489","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6763422710","https://openalex.org/W6768009244","https://openalex.org/W6770404345","https://openalex.org/W6778485988","https://openalex.org/W6784923365","https://openalex.org/W6785226069","https://openalex.org/W6788305448","https://openalex.org/W6793697131"],"related_works":["https://openalex.org/W2047973478","https://openalex.org/W4295532600","https://openalex.org/W2063823869","https://openalex.org/W3016928466","https://openalex.org/W2012410061","https://openalex.org/W2562256921","https://openalex.org/W2970427506","https://openalex.org/W4386076228","https://openalex.org/W4310825149","https://openalex.org/W2798269247"],"abstract_inverted_index":{"Scene":[0],"flow":[1,58,112],"prediction":[2],"is":[3,63],"a":[4,51,96],"challenging":[5],"task":[6],"that":[7],"aims":[8],"at":[9],"jointly":[10],"estimating":[11],"the":[12,32,40,66,81,84,147],"3D":[13,16],"structure":[14],"and":[15,86,115,135,143,158,173,180,192],"motion":[17],"of":[18,30,42,68,83,149],"dynamic":[19],"scenes.":[20],"The":[21,60],"previous":[22],"methods":[23],"concentrate":[24],"more":[25,113],"on":[26,139,169,190],"point-wise":[27],"estimation":[28],"instead":[29],"considering":[31],"correspondence":[33],"between":[34],"objects":[35],"as":[36,38],"well":[37],"lacking":[39],"sensation":[41],"high-level":[43],"semantic":[44],"knowledge.":[45],"In":[46,92],"this":[47,118],"paper,":[48],"we":[49,94],"propose":[50],"concise":[52],"yet":[53],"effective":[54],"method":[55],"for":[56,71],"scene":[57,111],"prediction.":[59],"key":[61],"idea":[62],"to":[64,108],"extend":[65],"view":[67],"all":[69],"points":[70],"computing":[72],"point":[73],"cloud":[74],"features":[75],"into":[76],"object-level,":[77],"thus":[78],"simultaneously":[79],"modeling":[80],"relationships":[82],"object-level":[85],"point-level":[87],"via":[88],"an":[89],"improved":[90],"transformer.":[91],"addition,":[93],"introduce":[95],"novel":[97],"unsupervised":[98],"loss":[99,119],"called":[100],"segmentation-aware":[101],"loss,":[102],"which":[103],"can":[104,120,128,166,187],"model":[105],"semanticaware":[106],"details":[107],"help":[109],"predict":[110],"accurately":[114],"robustly.":[116],"Since":[117],"be":[121,129,167,188],"trained":[122],"without":[123],"any":[124],"ground":[125],"truth,":[126],"it":[127],"used":[130],"in":[131],"both":[132,140],"supervised":[133,141,153],"training":[134,142,145],"self-supervised":[136,144,177],"training.":[137],"Experiments":[138],"demonstrate":[146],"effectiveness":[148],"our":[150],"method.":[151],"On":[152,176],"training,":[154],"3.8%,":[155],"22.58%,":[156],"10.90%":[157],"21.82":[159],"%":[160],"accuracy":[161,182],"boosts":[162],"than":[163,184],"FLOT":[164],"[23]":[165],"observed":[168,189],"FT3Ds,":[170],"KITTIs,":[171],"FT3Do":[172],"KITTIo":[174,191],"datasets.":[175,194],"scheme,":[178],"48.23%":[179],"48.96%":[181],"boost":[183],"PointPWC-Net":[185],"[40]":[186],"KITTIs":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}