{"id":"https://openalex.org/W4402982246","doi":"https://doi.org/10.1109/icme57554.2024.10687816","title":"Video Object Segmentation with Dynamic Query Modulation","display_name":"Video Object Segmentation with Dynamic Query Modulation","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402982246","doi":"https://doi.org/10.1109/icme57554.2024.10687816"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5083942931","display_name":"Hantao Zhou","orcid":"https://orcid.org/0000-0002-0514-0905"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hantao Zhou","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,ShenZhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,ShenZhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011299161","display_name":"Runze Hu","orcid":"https://orcid.org/0000-0002-6366-3763"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runze Hu","raw_affiliation_strings":["Beijing Institute of Technology,School of Information and Electronics,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Information and Electronics,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004942213","display_name":"Xiu Li","orcid":"https://orcid.org/0000-0002-7860-1784"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiu Li","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,ShenZhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,ShenZhen,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083942931"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.5499,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66517754,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9878000020980835,"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":0.9878000020980835,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9732000231742859,"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":0.760556697845459},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6228171586990356},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6223866939544678},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5655145645141602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5275014638900757},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.4389949440956116},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33859485387802124}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760556697845459},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6228171586990356},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6223866939544678},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5655145645141602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5275014638900757},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.4389949440956116},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33859485387802124},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2470139095","https://openalex.org/W2794847483","https://openalex.org/W2889986507","https://openalex.org/W2963253279","https://openalex.org/W2964218467","https://openalex.org/W2990205821","https://openalex.org/W3094664776","https://openalex.org/W3096609285","https://openalex.org/W3106773277","https://openalex.org/W3160550216","https://openalex.org/W3170630188","https://openalex.org/W3183673520","https://openalex.org/W3192871594","https://openalex.org/W4312396403","https://openalex.org/W4312815172","https://openalex.org/W4313044016","https://openalex.org/W4372266156","https://openalex.org/W4385245566","https://openalex.org/W4386071535","https://openalex.org/W4386108434","https://openalex.org/W4390190854","https://openalex.org/W4390872682","https://openalex.org/W4390873252","https://openalex.org/W4390874025","https://openalex.org/W4390874670","https://openalex.org/W4393148505","https://openalex.org/W4399881572","https://openalex.org/W4402753830"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2737719445","https://openalex.org/W4239098401","https://openalex.org/W2501551404","https://openalex.org/W4385583601","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W2898210368","https://openalex.org/W4395685956"],"abstract_inverted_index":{"Storing":[0],"intermediate":[1],"frame":[2],"segmentations":[3],"as":[4,91],"memory":[5],"for":[6,45,94,104],"long-range":[7],"context":[8],"modeling,":[9],"spatial-temporal":[10],"memory-based":[11,58,129],"methods":[12,26,59],"have":[13],"recently":[14],"showcased":[15],"impressive":[16],"results":[17],"in":[18,41,61],"semi-supervised":[19],"video":[20],"object":[21,50,63,82],"segmentation":[22],"(SVOS).":[23],"However,":[24],"these":[25,69],"face":[27],"two":[28],"key":[29],"limitations:":[30],"1)":[31],"relying":[32],"on":[33,136],"non-local":[34],"pixel-level":[35],"matching":[36],"to":[37,127],"read":[38],"memory,":[39],"resulting":[40],"noisy":[42],"retrieved":[43],"features":[44,83],"segmentation;":[46],"2)":[47],"segmenting":[48],"each":[49],"independently":[51],"without":[52],"interaction.":[53],"These":[54],"shortcomings":[55],"make":[56],"the":[57,105,128],"struggle":[60],"similar":[62],"and":[64,87,101,108,132],"multi-object":[65,110],"segmentation.":[66],"To":[67],"address":[68],"issues,":[70],"we":[71],"propose":[72],"a":[73],"query":[74],"modulation":[75],"method,":[76],"termed":[77],"QMVOS.":[78],"This":[79],"method":[80,122,131],"summarizes":[81],"into":[84],"dynamic":[85,92],"queries":[86],"then":[88],"treats":[89],"them":[90],"filters":[93],"mask":[95],"prediction,":[96],"thereby":[97],"providing":[98],"high-level":[99],"descriptions":[100],"object-level":[102],"perception":[103],"model.":[106],"Efficient":[107],"effective":[109],"interactions":[111],"are":[112],"realized":[113],"through":[114],"inter-query":[115],"attention.":[116],"Extensive":[117],"experiments":[118],"demonstrate":[119],"that":[120],"our":[121],"can":[123],"bring":[124],"significant":[125],"improvements":[126],"SVOS":[130,138],"achieve":[133],"competitive":[134],"performance":[135],"standard":[137],"benchmarks.":[139],"The":[140],"code":[141],"is":[142],"available":[143],"at":[144],"https://github.com/zht8506/QMVOS.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}