{"id":"https://openalex.org/W2603608964","doi":"https://doi.org/10.5220/0006129200750085","title":"Joint Semantic and Motion Segmentation for Dynamic Scenes using Deep Convolutional Networks","display_name":"Joint Semantic and Motion Segmentation for Dynamic Scenes using Deep Convolutional Networks","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2603608964","doi":"https://doi.org/10.5220/0006129200750085","mag":"2603608964"},"language":"en","primary_location":{"id":"doi:10.5220/0006129200750085","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0006129200750085","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0006129200750085","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065671186","display_name":"Nazrul Haque","orcid":"https://orcid.org/0000-0003-0411-8367"},"institutions":[{"id":"https://openalex.org/I188963388","display_name":"International Institute of Information Technology","ror":"https://ror.org/02dernx73","country_code":"IN","type":"education","lineage":["https://openalex.org/I188963388"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nazrul Haque","raw_affiliation_strings":["International Institute of Information Technology, India","International Institute of Information Technology, Pune, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, India","institution_ids":["https://openalex.org/I188963388"]},{"raw_affiliation_string":"International Institute of Information Technology, Pune, India","institution_ids":["https://openalex.org/I188963388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113804417","display_name":"N. Dinesh Reddy","orcid":null},"institutions":[{"id":"https://openalex.org/I188963388","display_name":"International Institute of Information Technology","ror":"https://ror.org/02dernx73","country_code":"IN","type":"education","lineage":["https://openalex.org/I188963388"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Dinesh Reddy","raw_affiliation_strings":["International Institute of Information Technology, India","Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, India","institution_ids":["https://openalex.org/I188963388"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075816776","display_name":"K. Madhava Krishna","orcid":"https://orcid.org/0000-0001-7846-7901"},"institutions":[{"id":"https://openalex.org/I188963388","display_name":"International Institute of Information Technology","ror":"https://ror.org/02dernx73","country_code":"IN","type":"education","lineage":["https://openalex.org/I188963388"]},{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K. Madhava Krishna","raw_affiliation_strings":["International Institute of Information Technology, India","International Institute of Information Technology, Hyderabad, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, India","institution_ids":["https://openalex.org/I188963388"]},{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0924,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.43691163,"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":"75","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.7907153367996216},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7664501667022705},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6858113408088684},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6420332193374634},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.5532153844833374},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5269092917442322},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5148786306381226},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5005936622619629},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4996984004974365},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4791702330112457},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.47096043825149536},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43440061807632446},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4296777844429016},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.41706210374832153},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.41311895847320557},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32583072781562805},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12889516353607178},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.11218813061714172}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907153367996216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7664501667022705},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6858113408088684},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6420332193374634},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.5532153844833374},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5269092917442322},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5148786306381226},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5005936622619629},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4996984004974365},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4791702330112457},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.47096043825149536},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43440061807632446},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4296777844429016},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.41706210374832153},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.41311895847320557},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32583072781562805},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12889516353607178},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.11218813061714172},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.5220/0006129200750085","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0006129200750085","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1704.08331","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.08331","pdf_url":"https://arxiv.org/pdf/1704.08331","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":null,"raw_type":"text"},{"id":"mag:2603608964","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1704.08331.pdf","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.1704.08331","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1704.08331","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":"doi:10.5220/0006129200750085","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0006129200750085","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W198996565","https://openalex.org/W360623563","https://openalex.org/W1907877624","https://openalex.org/W2003217181","https://openalex.org/W2147800946","https://openalex.org/W2150066425","https://openalex.org/W2161236525","https://openalex.org/W2308045930","https://openalex.org/W2949086864","https://openalex.org/W2950094539","https://openalex.org/W2951309005","https://openalex.org/W2964288706"],"related_works":["https://openalex.org/W2963279353","https://openalex.org/W1993662509","https://openalex.org/W2964104806","https://openalex.org/W2146042450","https://openalex.org/W20295167","https://openalex.org/W2789332689","https://openalex.org/W3130639450","https://openalex.org/W2851217339","https://openalex.org/W3199407192","https://openalex.org/W2798569237","https://openalex.org/W2899380617","https://openalex.org/W1913356549","https://openalex.org/W2736685366","https://openalex.org/W2925310131","https://openalex.org/W2908978583","https://openalex.org/W3134572896","https://openalex.org/W2897855555","https://openalex.org/W2964343881","https://openalex.org/W3049318984","https://openalex.org/W2948647700"],"abstract_inverted_index":{"Dynamic":[0],"scene":[1],"understanding":[2],"is":[3],"a":[4,11,99],"challenging":[5,59,150],"problem":[6,82],"and":[7,19,74,91,120,129],"motion":[8,20,75,86,92,140],"segmentation":[9,141],"plays":[10],"crucial":[12],"role":[13],"in":[14,138],"solving":[15],"it.":[16],"Incorporating":[17],"semantics":[18,128],"enhances":[21],"the":[22,26,52,81,127,143,146],"overall":[23],"perception":[24],"of":[25,31,83,111,145],"dynamic":[27],"scene.":[28],"For":[29],"applications":[30],"outdoor":[32],"robotic":[33],"navigation,":[34],"joint":[35,133],"learning":[36],"methods":[37,148],"have":[38],"not":[39],"been":[40],"extensively":[41],"used":[42],"for":[43],"extracting":[44],"spatio-temporal":[45],"features":[46,73,103],"or":[47],"adding":[48],"different":[49],"priors":[50],"into":[51,104],"formulation.":[53],"The":[54,108],"task":[55],"becomes":[56],"even":[57],"more":[58],"without":[60],"stereo":[61],"information":[62],"being":[63],"incorporated.":[64],"This":[65],"paper":[66],"proposes":[67],"an":[68],"approach":[69],"to":[70,79,125],"fuse":[71,126],"semantic":[72,85,90,102],"clues":[76],"using":[77],"CNNs,":[78],"address":[80],"monocular":[84,139],"segmentation.":[87],"We":[88],"deduce":[89],"labels":[93],"by":[94],"integrating":[95],"optical":[96],"flow":[97,130],"as":[98],"constraint":[100],"with":[101],"dilated":[105],"convolution":[106],"network.":[107],"pipeline":[109],"consists":[110],"three":[112],"main":[113],"stages":[114],"i.e":[115],"Feature":[116,118],"extraction,":[117],"amplification":[119],"Multi":[121],"Scale":[122],"Context":[123],"Aggregation":[124],"features.":[131],"Our":[132],"formulation":[134],"shows":[135],"significant":[136],"improvements":[137],"over":[142],"state":[144],"art":[147],"on":[149],"KITTI":[151],"tracking":[152],"dataset.":[153]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}