{"id":"https://openalex.org/W4402979682","doi":"https://doi.org/10.1109/icme57554.2024.10687937","title":"Visual-guided Query with Temporal Interaction for Video Object Segementation","display_name":"Visual-guided Query with Temporal Interaction for Video Object Segementation","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979682","doi":"https://doi.org/10.1109/icme57554.2024.10687937"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687937","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687937","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/A5027033058","display_name":"J. Qiu","orcid":"https://orcid.org/0009-0000-6286-2608"},"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":true,"raw_author_name":"Jiaxin Qiu","raw_affiliation_strings":["Zhejiang University of Technology,College of Computer Science,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,College of Computer Science,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052567771","display_name":"Guo\u2010Yu Yang","orcid":"https://orcid.org/0000-0002-0911-2805"},"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":"Guoyu Yang","raw_affiliation_strings":["Zhejiang University of Technology,College of Computer Science,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,College of Computer Science,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101781050","display_name":"Jie Lei","orcid":"https://orcid.org/0009-0002-5642-4745"},"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":"Jie Lei","raw_affiliation_strings":["Zhejiang University of Technology,College of Computer Science,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,College of Computer Science,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043914348","display_name":"Zunlei Feng","orcid":"https://orcid.org/0000-0001-8640-8434"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zunlei Feng","raw_affiliation_strings":["Zhejiang University,College of Computer Science,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Computer Science,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056760589","display_name":"Ronghua Liang","orcid":null},"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":"Ronghua Liang","raw_affiliation_strings":["Zhejiang University of Technology,College of Computer Science,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,College of Computer Science,Hangzhou,China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027033058"],"corresponding_institution_ids":["https://openalex.org/I55712492"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16784584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.9944000244140625,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9919000267982483,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8350844383239746},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5646501779556274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48755162954330444},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3704882562160492},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3526628017425537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8350844383239746},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5646501779556274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48755162954330444},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3704882562160492},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3526628017425537}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687937","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687937","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":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","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":{"The":[0],"task":[1],"of":[2,93],"referring":[3,67],"video":[4,12,68],"object":[5,69],"segmentation":[6,70,103,115],"(RVOS)":[7],"involves":[8],"segmenting":[9],"objects":[10],"in":[11,89],"frames":[13],"based":[14],"on":[15,76],"a":[16,29,60,101],"given":[17],"text":[18,26],"description.":[19],"However,":[20],"most":[21],"existing":[22],"approaches":[23],"treat":[24],"the":[25,32,39,45,51,84,94,108],"directly":[27],"as":[28],"query,":[30],"neglecting":[31],"valuable":[33],"visual":[34],"and":[35,79],"temporal":[36,64],"information":[37],"from":[38],"video.":[40],"This":[41],"limitation":[42],"may":[43],"cause":[44],"query":[46,62,85],"unable":[47],"to":[48,82,106,112],"accurately":[49],"perceive":[50],"target":[52,95],"object.":[53,96],"To":[54],"address":[55],"this":[56],"issue,":[57],"we":[58,99],"introduce":[59,100],"visual-guided":[61],"with":[63],"interaction":[65],"for":[66],"(VQTI)":[71],"approach.":[72],"Our":[73],"method":[74],"capitalizes":[75],"frame-level":[77],"features":[78,81],"video-level":[80],"guide":[83],"generation":[86],"process,":[87],"resulting":[88],"an":[90],"enhanced":[91],"perception":[92],"In":[97],"addition,":[98],"spectral-guided":[102],"optimizer":[104],"module":[105],"enhance":[107],"fine-grained":[109],"information,":[110],"leading":[111],"more":[113],"precise":[114],"masks.":[116],"Extensive":[117],"experiments":[118],"shows":[119],"competitive":[120],"performance":[121],"against":[122],"state-of-the-art":[123],"approaches.":[124]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
