{"id":"https://openalex.org/W4362657847","doi":"https://doi.org/10.1109/tpami.2022.3172932","title":"SiamMask: A Framework for Fast Online Object Tracking and Segmentation.","display_name":"SiamMask: A Framework for Fast Online Object Tracking and Segmentation.","publication_year":2023,"publication_date":"2023-03-01","ids":{"openalex":"https://openalex.org/W4362657847","doi":"https://doi.org/10.1109/tpami.2022.3172932","pmid":"https://pubmed.ncbi.nlm.nih.gov/37022470"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37022470","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["pubmed"],"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/A5114549594","display_name":"Weiming Hu","orcid":"https://orcid.org/0000-0001-9237-8825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiming Hu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367009","display_name":"Qiang Wang","orcid":"https://orcid.org/0000-0002-7078-7545"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiang Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425669","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0002-9321-3421"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009876111","display_name":"Luca Bertinetto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luca Bertinetto","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001534492","display_name":"Philip H. S. Torr","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philip H S Torr","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.47,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.99996,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"45","issue":"3","first_page":"3072","last_page":"3089"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9997,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9997,"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":0.9988,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.996,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/initialization","display_name":"Initialization","score":0.7149568},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.56822395},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.5091316},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.47647592},{"id":"https://openalex.org/keywords/active-appearance-model","display_name":"Active appearance model","score":0.4276808}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.88843286},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7719454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7356711},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7149568},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.69974136},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.69497687},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.60939956},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.56822395},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5467899},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.5091316},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5039455},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.47848767},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4784365},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.47647592},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.4276808},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2349157},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37022470","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4300263603","https://openalex.org/W4284681239","https://openalex.org/W2949302831","https://openalex.org/W2384987031","https://openalex.org/W2154333700","https://openalex.org/W2026019026","https://openalex.org/W2007953656","https://openalex.org/W1967061043","https://openalex.org/W1963494852","https://openalex.org/W1631910785"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3,74],"introduce":[4],"SiamMask,":[5],"a":[6,41,54,98,136],"framework":[7,83],"to":[8,80,84],"perform":[9],"both":[10],"visual":[11,65],"object":[12,16,66,87,141],"tracking":[13,67,88,125],"and":[14,60,68,89],"video":[15,140],"segmentation,":[17],"in":[18,97],"real-time,":[19],"with":[20,40],"the":[21,27,46,82,94,129],"same":[22,130],"simple":[23],"method.":[24],"We":[25],"improve":[26],"offline":[28,47],"training":[29,48],"procedure":[30],"of":[31],"popular":[32],"fully-convolutional":[33],"Siamese":[34],"approaches":[35],"by":[36,91],"augmenting":[37],"their":[38],"losses":[39],"binary":[42],"segmentation":[43,69,90,142],"task.":[44],"Once":[45],"is":[49,78],"completed,":[50],"SiamMask":[51],"only":[52],"requires":[53],"single":[55],"bounding":[56],"box":[57],"for":[58,139],"initialization":[59],"can":[61],"simultaneously":[62],"carry":[63],"out":[64],"at":[70,111,128,135],"high":[71,108,137],"frame-rates.":[72],"Moreover,":[73],"show":[75,103],"that":[76,104],"it":[77],"possible":[79],"extend":[81],"handle":[85],"multiple":[86],"simply":[92],"re-using":[93],"multi-task":[95],"model":[96],"cascaded":[99],"fashion.":[100],"Experimental":[101],"results":[102,122],"our":[105],"approach":[106],"has":[107],"processing":[109],"efficiency,":[110],"around":[112],"55":[113],"frames":[114],"per":[115],"second.":[116],"It":[117],"yields":[118],"real-time":[119],"state-of-the":[120],"art":[121],"on":[123],"visual-object":[124],"benchmarks,":[126],"while":[127],"time":[131],"demonstrating":[132],"competitive":[133],"performance":[134],"speed":[138],"benchmarks.":[143]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4362657847","counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-04-22T21:48:00.449367","created_date":"2023-04-07"}