{"id":"https://openalex.org/W4372266213","doi":"https://doi.org/10.1109/icassp49357.2023.10096283","title":"Robust Video Object Segmentation with Restricted Attention","display_name":"Robust Video Object Segmentation with Restricted Attention","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266213","doi":"https://doi.org/10.1109/icassp49357.2023.10096283"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096283","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5019572221","display_name":"Huaizheng Zhang","orcid":"https://orcid.org/0000-0002-0153-6400"},"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":"Huaizheng Zhang","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing","School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","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":false,"raw_author_name":"Pinxue Guo","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing","Academy for Engineering and Technology, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing","institution_ids":[]},{"raw_affiliation_string":"Academy for Engineering and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073543641","display_name":"Zhongwen Le","orcid":null},"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":"Zhongwen Le","raw_affiliation_strings":["Shanghai Key Laboratory of Intelligent Information Processing","School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100669255","display_name":"Wenqiang Zhang","orcid":"https://orcid.org/0000-0002-3339-8751"},"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":["Shanghai Key Laboratory of Intelligent Information Processing","School of Computer Science, Fudan University, Shanghai, China","Academy for Engineering and Technology, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Academy for Engineering and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1123,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36569858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":1.0,"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":1.0,"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":0.9990000128746033,"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":0.9984999895095825,"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/segmentation","display_name":"Segmentation","score":0.8161752820014954},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.736653208732605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7096526622772217},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6768589615821838},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5979194641113281},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.5529108047485352},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5119155645370483},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5006628036499023},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4786975681781769},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.47228771448135376},{"id":"https://openalex.org/keywords/distraction","display_name":"Distraction","score":0.46893858909606934},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.45544955134391785},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.44564592838287354},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41007184982299805},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.40443578362464905}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8161752820014954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.736653208732605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7096526622772217},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6768589615821838},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5979194641113281},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.5529108047485352},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5119155645370483},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5006628036499023},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4786975681781769},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.47228771448135376},{"id":"https://openalex.org/C2776378700","wikidata":"https://www.wikidata.org/wiki/Q3030775","display_name":"Distraction","level":2,"score":0.46893858909606934},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.45544955134391785},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.44564592838287354},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41007184982299805},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.40443578362464905},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096283","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2470139095","https://openalex.org/W2564998703","https://openalex.org/W2605229288","https://openalex.org/W2889658408","https://openalex.org/W2890447039","https://openalex.org/W2916743882","https://openalex.org/W2916797271","https://openalex.org/W2963253279","https://openalex.org/W2964218467","https://openalex.org/W2990205821","https://openalex.org/W3030520226","https://openalex.org/W3093016409","https://openalex.org/W3094664776","https://openalex.org/W3108819577","https://openalex.org/W3117097536","https://openalex.org/W3170630188","https://openalex.org/W3172099915","https://openalex.org/W3172917640","https://openalex.org/W3183673520","https://openalex.org/W3192871594","https://openalex.org/W3200949949","https://openalex.org/W3211993051","https://openalex.org/W4200318028","https://openalex.org/W4221141660","https://openalex.org/W4221166007","https://openalex.org/W4283827327","https://openalex.org/W4294871818","https://openalex.org/W4308689110","https://openalex.org/W4309802081","https://openalex.org/W4312396403","https://openalex.org/W4312610155","https://openalex.org/W4382568144","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6753214761","https://openalex.org/W6754033419","https://openalex.org/W6759693999","https://openalex.org/W6778485988","https://openalex.org/W6784713722","https://openalex.org/W6791776128","https://openalex.org/W6796505553","https://openalex.org/W6796524941","https://openalex.org/W6847673887"],"related_works":["https://openalex.org/W3144569342","https://openalex.org/W2945274617","https://openalex.org/W2185902295","https://openalex.org/W2103507220","https://openalex.org/W2055202857","https://openalex.org/W2371519352","https://openalex.org/W4205800335","https://openalex.org/W2386644571","https://openalex.org/W2372421320","https://openalex.org/W2551987074"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3,33,107],"the":[4,8,13,34,49,61,78,85,97,104,108],"two":[5,39],"problems":[6,40],"of":[7,15,81,99],"similar":[9,65],"objects":[10,66],"distraction":[11],"and":[12,67,102,121],"lack":[14],"robustness":[16],"for":[17,89],"unseen":[18],"object":[19,24,91],"categories":[20],"in":[21],"semi-supervised":[22],"video":[23,90],"segmentation":[25,92],"task.":[26,93],"Existing":[27],"methods":[28],"have":[29,42],"achieved":[30],"great":[31],"results":[32],"benchmark":[35],"dataset,":[36],"but":[37],"these":[38],"still":[41],"not":[43],"been":[44],"completely":[45],"solved.":[46],"We":[47],"propose":[48],"Robust":[50],"Video":[51],"Object":[52],"Segmentation":[53],"With":[54],"Restricted":[55],"Attention":[56],"(RVOSR),":[57],"which":[58,83],"can":[59],"suppress":[60],"effects":[62],"caused":[63],"by":[64],"filter":[68],"out":[69],"noise":[70],"confusion":[71],"from":[72],"other":[73],"irrelevant":[74],"regions.":[75],"Meanwhile":[76],"augmenting":[77],"semantic":[79],"information":[80],"features,":[82],"makes":[84],"features":[86],"more":[87],"suitable":[88],"Extensive":[94],"experiments":[95],"demonstrate":[96],"effectiveness":[98],"our":[100],"approach":[101],"achieve":[103],"state-of-the-art":[105],"performance":[106],"widely-used":[109],"VOS":[110],"benchmarks":[111],"including":[112],"DAVIS-2016":[113],"(92.1%":[114],"$\\mathcal{J}{{\\&":[115,119],"}}\\mathcal{F}$),":[116],"DAVIS-2017":[117],"(86.8%":[118],"}}\\mathcal{F}$)":[120],"YouTubeVOS-2019":[122],"(84.8%).":[123]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}