{"id":"https://openalex.org/W4310269116","doi":"https://doi.org/10.1109/avss56176.2022.9959354","title":"Learning Occlusion-Aware Dense Correspondences for Multi-Modal Images","display_name":"Learning Occlusion-Aware Dense Correspondences for Multi-Modal Images","publication_year":2022,"publication_date":"2022-11-24","ids":{"openalex":"https://openalex.org/W4310269116","doi":"https://doi.org/10.1109/avss56176.2022.9959354"},"language":"en","primary_location":{"id":"doi:10.1109/avss56176.2022.9959354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss56176.2022.9959354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 18th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)","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/A5040087060","display_name":"Ryosuke Shimoya","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ryosuke Shimoya","raw_affiliation_strings":["Mitsubishi Electric Corporation Yokohama,Kanagawa,Japan","Mitsubishi Electric Corporation Yokohama, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Corporation Yokohama,Kanagawa,Japan","institution_ids":["https://openalex.org/I4210133125"]},{"raw_affiliation_string":"Mitsubishi Electric Corporation Yokohama, Kanagawa, Japan","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055151557","display_name":"Takashi Morimoto","orcid":"https://orcid.org/0000-0002-6428-5274"},"institutions":[{"id":"https://openalex.org/I4210103869","display_name":"The Core Institute","ror":"https://ror.org/01bxb2y87","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210103869"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takashi Morimoto","raw_affiliation_strings":["Woven Core, Inc.,Tokyo,Japan","Woven Core, Inc., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Woven Core, Inc.,Tokyo,Japan","institution_ids":["https://openalex.org/I4210103869"]},{"raw_affiliation_string":"Woven Core, Inc., Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103507544","display_name":"Jeroen van Baar","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeroen Van Baar","raw_affiliation_strings":["Amazon Robotics,North Reading,MA","Amazon Robotics, North Reading, MA"],"affiliations":[{"raw_affiliation_string":"Amazon Robotics,North Reading,MA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Robotics, North Reading, MA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034522188","display_name":"Petros T. Boufounos","orcid":"https://orcid.org/0000-0003-1369-0947"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Petros Boufounos","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories,Cambridge,MA","Mitsubishi Electric Research Laboratories, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories,Cambridge,MA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101185697","display_name":"Yanting Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanting Ma","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories,Cambridge,MA","Mitsubishi Electric Research Laboratories, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories,Cambridge,MA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101648073","display_name":"Hassan Mansour","orcid":"https://orcid.org/0000-0002-1667-9885"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hassan Mansour","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories,Cambridge,MA","Mitsubishi Electric Research Laboratories, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories,Cambridge,MA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5040087060"],"corresponding_institution_ids":["https://openalex.org/I4210133125"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11084813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs 1612 1925","issue":null,"first_page":"1","last_page":"8"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991000294685364,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9975000023841858,"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":0.754965603351593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.744659423828125},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6507642269134521},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6032107472419739},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5597460269927979},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5405548810958862},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5376400351524353},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5195203423500061},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.5125010013580322},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4599892199039459},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4576690196990967},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4251860976219177},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4100247621536255},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2902911305427551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.754965603351593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.744659423828125},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6507642269134521},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6032107472419739},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5597460269927979},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5405548810958862},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5376400351524353},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5195203423500061},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.5125010013580322},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4599892199039459},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4576690196990967},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4251860976219177},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4100247621536255},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2902911305427551},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/avss56176.2022.9959354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss56176.2022.9959354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 18th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W602397586","https://openalex.org/W764651262","https://openalex.org/W1901129140","https://openalex.org/W1939319527","https://openalex.org/W2171184283","https://openalex.org/W2309561466","https://openalex.org/W2560474170","https://openalex.org/W2785694322","https://openalex.org/W2962865163","https://openalex.org/W2963677766","https://openalex.org/W2963876278","https://openalex.org/W2963956866","https://openalex.org/W3035501466","https://openalex.org/W4233450617","https://openalex.org/W6639824700","https://openalex.org/W6730303213","https://openalex.org/W6738279954"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W4295532600","https://openalex.org/W2063823869","https://openalex.org/W2047973478","https://openalex.org/W2012410061","https://openalex.org/W627697492","https://openalex.org/W2970427506","https://openalex.org/W2053610073"],"abstract_inverted_index":{"We":[0,53,95],"introduce":[1],"a":[2,18,41,48,86,90,100,110],"scalable":[3],"multi-modal":[4,74],"approach":[5],"to":[6,44,67,79,114,124,140],"learn":[7],"dense,":[8],"i.e.,":[9],"pixel-level,":[10],"correspondences":[11,26],"and":[12,27,56,64,85,108],"occlusion":[13,28,65,81],"maps,":[14,82],"between":[15],"images":[16,58,103],"in":[17,32],"video":[19],"sequence.":[20],"The":[21,130],"problems":[22],"of":[23,102,120,132],"finding":[24],"dense":[25],"maps":[29,66],"are":[30],"fundamental":[31],"computer":[33],"vision.":[34],"In":[35],"this":[36],"work":[37],"we":[38],"jointly":[39],"train":[40,68],"deep":[42],"network":[43,70,77],"tackle":[45],"both,":[46],"with":[47,59],"shared":[49],"feature":[50,93],"extraction":[51],"stage.":[52],"use":[54],"depth":[55],"color":[57],"ground":[60],"truth":[61],"optical":[62,83],"flow":[63],"the":[69,73,76,97,117,126,138],"end-to-end.":[71],"From":[72],"input,":[75],"learns":[78],"estimate":[80],"flows,":[84],"correspondence":[87,128],"embedding":[88],"providing":[89],"meaningful":[91],"latent":[92],"space.":[94],"evaluate":[96],"performance":[98],"on":[99],"dataset":[101],"derived":[104],"from":[105,137],"synthetic":[106],"characters,":[107],"perform":[109],"thorough":[111],"ablation":[112],"study":[113],"demonstrate":[115],"that":[116],"proposed":[118,134],"components":[119],"our":[121,133],"architecture":[122],"combine":[123],"achieve":[125],"lowest":[127],"error.":[129],"scalability":[131],"method":[135],"comes":[136],"ability":[139],"incorporate":[141],"additional":[142],"modalities,":[143],"e.g.,":[144],"infrared":[145],"images.":[146]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}