{"id":"https://openalex.org/W4402680435","doi":"https://doi.org/10.1145/3653644.3653658","title":"A Spatiotemporal Mask Autoencoder for One-shot Video Object Segmentation","display_name":"A Spatiotemporal Mask Autoencoder for One-shot Video Object Segmentation","publication_year":2024,"publication_date":"2024-04-26","ids":{"openalex":"https://openalex.org/W4402680435","doi":"https://doi.org/10.1145/3653644.3653658"},"language":"en","primary_location":{"id":"doi:10.1145/3653644.3653658","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3653644.3653658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 3rd International Conference on Frontiers of Artificial Intelligence and Machine Learning","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/A5016318632","display_name":"Bai-Yu Chen","orcid":"https://orcid.org/0009-0009-6555-7743"},"institutions":[{"id":"https://openalex.org/I146620803","display_name":"Wenzhou University","ror":"https://ror.org/020hxh324","country_code":"CN","type":"education","lineage":["https://openalex.org/I146620803"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Baiyu Chen","raw_affiliation_strings":["Wenzhou University, China"],"raw_orcid":"https://orcid.org/0009-0009-6555-7743","affiliations":[{"raw_affiliation_string":"Wenzhou University, China","institution_ids":["https://openalex.org/I146620803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100730692","display_name":"Li Zhao","orcid":"https://orcid.org/0000-0001-5787-2705"},"institutions":[{"id":"https://openalex.org/I146620803","display_name":"Wenzhou University","ror":"https://ror.org/020hxh324","country_code":"CN","type":"education","lineage":["https://openalex.org/I146620803"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhao","raw_affiliation_strings":["Wenzhou University, China"],"raw_orcid":"https://orcid.org/0000-0001-5787-2705","affiliations":[{"raw_affiliation_string":"Wenzhou University, China","institution_ids":["https://openalex.org/I146620803"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003029072","display_name":"Sixian Chan","orcid":"https://orcid.org/0000-0001-8916-1174"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sixian Chan","raw_affiliation_strings":["Zhejiang University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0001-8916-1174","affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016318632"],"corresponding_institution_ids":["https://openalex.org/I146620803"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14807129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","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/T11605","display_name":"Visual Attention and Saliency Detection","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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9980000257492065,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9970999956130981,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7460000514984131},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7431631088256836},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.7413727641105652},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7319889068603516},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7180845737457275},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.610222339630127},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5322195291519165},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4791233539581299},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4756995141506195},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10197892785072327}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7460000514984131},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7431631088256836},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7413727641105652},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7319889068603516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7180845737457275},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.610222339630127},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5322195291519165},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4791233539581299},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4756995141506195},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10197892785072327},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3653644.3653658","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3653644.3653658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 3rd International Conference on Frontiers of Artificial Intelligence and Machine Learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2025768430","https://openalex.org/W2470139095","https://openalex.org/W2566588379","https://openalex.org/W2799157347","https://openalex.org/W2916797271","https://openalex.org/W2962825871","https://openalex.org/W2964157492","https://openalex.org/W2967890649","https://openalex.org/W3021957787","https://openalex.org/W3034538699","https://openalex.org/W3034915791","https://openalex.org/W3092944026","https://openalex.org/W3160550216","https://openalex.org/W3161300377","https://openalex.org/W3173284731","https://openalex.org/W3183673520","https://openalex.org/W4287864058","https://openalex.org/W4288378974","https://openalex.org/W4300991419","https://openalex.org/W4302065087","https://openalex.org/W4313156423","https://openalex.org/W4385945169"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2145836866","https://openalex.org/W2803255133","https://openalex.org/W1522196789"],"abstract_inverted_index":{"This":[0,105],"paper":[1],"introduces":[2],"a":[3,45,60,66,88,108],"novel":[4,46],"architecture":[5,48],"for":[6,97],"the":[7,40,54,101,113,117,122,130,144],"video":[8],"object":[9,95],"segmentation":[10],"(VOS)":[11],"challenge":[12],"to":[13,92,115],"achieve":[14],"greater":[15],"label":[16],"efficiency.":[17],"Previous":[18],"studies":[19],"have":[20],"primarily":[21],"tackled":[22],"this":[23],"problem":[24],"through":[25],"either":[26],"match-based":[27],"or":[28],"propagate-based":[29],"architectures,":[30],"relying":[31],"on":[32,73,129],"fully":[33],"annotated":[34],"datasets.":[35],"In":[36],"contrast,":[37],"we":[38],"propose":[39,87],"spatiotemporal":[41,123],"mask":[42,62,68,120],"autoencoder":[43],"(STMAE),":[44],"VOS":[47,98],"constructed":[49],"using":[50,99],"annotations":[51],"solely":[52],"from":[53,69,121],"first":[55,102,118],"frame.":[56],"Specifically,":[57],"STMAE":[58,137],"generates":[59],"precise":[61],"by":[63,77],"initially":[64],"aggregating":[65],"coarse":[67],"previous":[70],"frames":[71],"based":[72],"visual":[74],"correspondence":[75],"provided":[76],"an":[78],"image":[79],"encoder":[80],"and":[81,132],"then":[82],"reconstructing":[83],"it.":[84],"We":[85],"further":[86],"one-shot":[89],"training":[90],"strategy":[91,106],"learn":[93],"general":[94],"representations":[96],"only":[100],"frame":[103,119],"mask.":[104],"incorporates":[107],"reconstruction":[109],"loss":[110],"that":[111,136],"guides":[112],"network":[114],"reconstruct":[116],"aggregation.":[124],"Finally,":[125],"extensive":[126],"experiments":[127],"conducted":[128],"DAVIS":[131],"YouTube-VOS":[133],"datasets":[134],"demonstrate":[135],"achieves":[138],"remarkable":[139],"performance":[140],"while":[141],"effectively":[142],"addressing":[143],"labor-intensive":[145],"annotation":[146],"issue.":[147]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}