{"id":"https://openalex.org/W4386598434","doi":"https://doi.org/10.1109/icip49359.2023.10222318","title":"Leveraging Visual Prompts To Guide Language Modeling for Referring Video Object Segmentation","display_name":"Leveraging Visual Prompts To Guide Language Modeling for Referring Video Object Segmentation","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386598434","doi":"https://doi.org/10.1109/icip49359.2023.10222318"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222318","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10222318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","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/A5085680121","display_name":"Qiqi Gao","orcid":"https://orcid.org/0000-0002-4743-9657"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiqi Gao","raw_affiliation_strings":["Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019101763","display_name":"Wanjun Zhong","orcid":"https://orcid.org/0009-0007-2236-228X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wanjun Zhong","raw_affiliation_strings":["Sun Yat-Sen University"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066052627","display_name":"Jie Li","orcid":"https://orcid.org/0000-0001-9359-3586"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":["Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101661008","display_name":"Tiejun Zhao","orcid":"https://orcid.org/0000-0003-4659-4935"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiejun Zhao","raw_affiliation_strings":["Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5085680121"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.123,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.41339819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"34","issue":null,"first_page":"685","last_page":"689"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.995199978351593,"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":0.8765167593955994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6780070066452026},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.554929792881012},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5405716896057129},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5166435837745667},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.495776504278183},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4486992061138153},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4433695375919342},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4376753866672516},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4063870310783386},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09099790453910828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8765167593955994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6780070066452026},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.554929792881012},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5405716896057129},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5166435837745667},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.495776504278183},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4486992061138153},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4433695375919342},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4376753866672516},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4063870310783386},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09099790453910828},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10222318","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10222318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2489434015","https://openalex.org/W2963109634","https://openalex.org/W2965373594","https://openalex.org/W2970476646","https://openalex.org/W2980088508","https://openalex.org/W3035097537","https://openalex.org/W3094664776","https://openalex.org/W3104844437","https://openalex.org/W3171098737","https://openalex.org/W3173494067","https://openalex.org/W3174770825","https://openalex.org/W3185341429","https://openalex.org/W3215899623","https://openalex.org/W4226024706","https://openalex.org/W4287113019","https://openalex.org/W4312420092","https://openalex.org/W4386374572","https://openalex.org/W6766673545","https://openalex.org/W6791353385","https://openalex.org/W6796280812","https://openalex.org/W6797716411"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2057568687","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W3112772842"],"abstract_inverted_index":{"Referring":[0],"Video":[1],"Object":[2],"Segmentation":[3],"(R-VOS)":[4],"aims":[5],"to":[6,39,66,98,119],"segment":[7],"object":[8,130],"masks":[9],"in":[10,60,77,132],"a":[11,15,23,32,107,133],"target":[12,41,129],"video":[13],"given":[14],"language":[16,34,48,52,69,122],"query":[17,35],"describing":[18],"the":[19,29,40,78,139],"object.":[20],"It":[21],"is":[22,86,104],"challenging":[24],"task":[25],"that":[26],"requires":[27],"modeling":[28],"semantics":[30],"of":[31,92],"natural":[33],"and":[36,54],"its":[37],"correspondence":[38],"video.":[42],"Previous":[43],"works":[44],"directly":[45],"use":[46],"visual-agnostic":[47],"features":[49,59,70,91],"from":[50],"uni-modal":[51],"models,":[53],"only":[55],"interact":[56],"with":[57,95,106,116],"visual":[58,73,84,90,114],"late":[61],"decoding":[62],"stages.":[63],"We":[64,112],"propose":[65],"encode":[67,120],"visual-enriched":[68,121],"by":[71,88],"using":[72],"prompts":[74,115],"as":[75,126],"guidance":[76],"early":[79],"encoding":[80],"stage.":[81],"The":[82,101],"proposed":[83],"prompt":[85],"constructed":[87],"modulating":[89],"key":[93],"frames":[94],"alignment":[96,102],"scores":[97],"text":[99,117],"inputs.":[100],"score":[103],"computed":[105],"pre-trained":[108],"visual-language":[109],"contrastive":[110],"model.":[111],"concatenate":[113],"inputs":[118],"features,":[123],"which":[124],"serve":[125],"queries":[127],"for":[128],"segmentation":[131],"Transformer-based":[134],"decoder.":[135],"Our":[136],"method":[137,142],"outperforms":[138],"previous":[140],"state-of-the-art":[141],"(+2.3)":[143],"on":[144],"Refer-Youtube-VOS":[145],"benchmark.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}