{"id":"https://openalex.org/W4413917265","doi":"https://doi.org/10.1109/icra55743.2025.11128804","title":"VideoSAM: Open-World Video Segmentation","display_name":"VideoSAM: Open-World Video Segmentation","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413917265","doi":"https://doi.org/10.1109/icra55743.2025.11128804"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128804","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 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/A5085021663","display_name":"Pinxue Guo","orcid":"https://orcid.org/0000-0002-4388-9757"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pinxue Guo","raw_affiliation_strings":["Academy for Engineering and Technology, Fudan University"],"affiliations":[{"raw_affiliation_string":"Academy for Engineering and Technology, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101817999","display_name":"Zixu Zhao","orcid":"https://orcid.org/0000-0001-9399-3475"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Zixu Zhao","raw_affiliation_strings":["Amazon Web Services Shanghai AI Lab"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026628307","display_name":"Jianxiong Gao","orcid":"https://orcid.org/0000-0002-2975-0150"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210164150","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":"https://ror.org/0551a0y31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210164150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxiong Gao","raw_affiliation_strings":["Institute of Science and Technology for Brain-inspired Intelligence, Fudan University"],"affiliations":[{"raw_affiliation_string":"Institute of Science and Technology for Brain-inspired Intelligence, Fudan University","institution_ids":["https://openalex.org/I4210164150","https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089678310","display_name":"Chongruo Wu","orcid":"https://orcid.org/0000-0002-4569-5024"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Chongruo Wu","raw_affiliation_strings":["Amazon Web Services Shanghai AI Lab"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604494","display_name":"Tong He","orcid":"https://orcid.org/0000-0003-2772-9320"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Tong He","raw_affiliation_strings":["Amazon Web Services Shanghai AI Lab"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459097","display_name":"Zheng Zhang","orcid":"https://orcid.org/0000-0002-1398-7727"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng Zhang","raw_affiliation_strings":["Amazon Web Services Shanghai AI Lab"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020757657","display_name":"Tianjun Xiao","orcid":"https://orcid.org/0000-0003-4705-1545"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Tianjun Xiao","raw_affiliation_strings":["Amazon Web Services Shanghai AI Lab"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100669252","display_name":"Wenqiang Zhang","orcid":"https://orcid.org/0000-0002-0653-085X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqiang Zhang","raw_affiliation_strings":["Academy for Engineering and Technology, Fudan University"],"affiliations":[{"raw_affiliation_string":"Academy for Engineering and Technology, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5085021663"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":2.5024,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90818859,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11155","last_page":"11161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.8711000084877014,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.8711000084877014,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.8464000225067139,"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":0.8240000009536743,"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":0.669447124004364},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5107505321502686},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5107369422912598},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4432419538497925},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43584758043289185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.669447124004364},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5107505321502686},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5107369422912598},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4432419538497925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43584758043289185}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128804","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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":29,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2954929116","https://openalex.org/W2966669119","https://openalex.org/W2982723417","https://openalex.org/W3158120491","https://openalex.org/W3174415351","https://openalex.org/W3196204376","https://openalex.org/W3205596143","https://openalex.org/W3212555189","https://openalex.org/W4200045126","https://openalex.org/W4210986463","https://openalex.org/W4221166280","https://openalex.org/W4296467546","https://openalex.org/W4311166797","https://openalex.org/W4312396403","https://openalex.org/W4312473433","https://openalex.org/W4313117614","https://openalex.org/W4313156423","https://openalex.org/W4313176857","https://openalex.org/W4319300361","https://openalex.org/W4386066081","https://openalex.org/W4390872143","https://openalex.org/W4390874575","https://openalex.org/W4390874670","https://openalex.org/W4401416102","https://openalex.org/W4401416951","https://openalex.org/W4402727796","https://openalex.org/W4403906568","https://openalex.org/W4409261941"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Video":[0],"segmentation":[1,42,86],"is":[2,134],"essential":[3],"for":[4,111],"advancing":[5],"robotics":[6],"and":[7,17,60,85,103,140,143,151],"autonomous":[8],"driving,":[9],"particularly":[10],"in":[11,33,55,64,88,153],"open-world":[12],"settings":[13],"where":[14],"continuous":[15],"perception":[16],"object":[18,65,83,98,113],"association":[19,99],"across":[20,58,130],"video":[21,41],"frames":[22],"are":[23],"critical.":[24],"While":[25],"the":[26,123,138],"Segment":[27],"Anything":[28],"Model":[29],"(SAM)":[30],"has":[31],"excelled":[32],"static":[34],"image":[35],"segmentation,":[36],"extending":[37],"its":[38,149],"capabilities":[39],"to":[40,77,126],"poses":[43],"significant":[44],"challenges.":[45],"We":[46],"tackle":[47],"two":[48],"major":[49],"hurdles:":[50],"a)":[51],"SAM's":[52],"embedding":[53],"limitations":[54],"associating":[56],"objects":[57],"frames,":[59],"b)":[61],"granularity":[62,129],"inconsistencies":[63],"segmentation.":[66],"To":[67],"this":[68],"end,":[69],"we":[70,116],"introduce":[71],"VideoSAM,":[72],"an":[73,93,118],"end-to-end":[74],"framework":[75],"designed":[76],"address":[78],"these":[79],"challenges":[80],"by":[81],"improving":[82],"tracking":[84],"consistency":[87],"dynamic":[89],"environments.":[90],"VideoSAM":[91],"integrates":[92],"agglomerated":[94],"backbone,":[95],"RADIO,":[96],"enabling":[97],"through":[100],"similarity":[101],"metrics":[102],"introduces":[104],"Cycle-ack-Pairs":[105],"Propagation":[106],"with":[107],"a":[108],"memory":[109],"mechanism":[110,121],"stable":[112],"tracking.":[114],"Additionally,":[115],"incorporate":[117],"autoregressive":[119],"object-token":[120],"within":[122],"SAM":[124],"decoder":[125],"maintain":[127],"consistent":[128],"frames.":[131],"Our":[132],"method":[133],"extensively":[135],"evaluated":[136],"on":[137],"UVO":[139],"BURST":[141],"benchmarks,":[142],"robotic":[144],"videos":[145],"from":[146],"RoboTAP,":[147],"demonstrating":[148],"effectiveness":[150],"robustness":[152],"real-world":[154],"scenarios.":[155],"All":[156],"codes":[157],"will":[158],"be":[159],"available.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}