{"id":"https://openalex.org/W4387969771","doi":"https://doi.org/10.1145/3581783.3612117","title":"CARIS: Context-Aware Referring Image Segmentation","display_name":"CARIS: Context-Aware Referring Image Segmentation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969771","doi":"https://doi.org/10.1145/3581783.3612117"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612117","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5046158385","display_name":"Sun-Ao Liu","orcid":"https://orcid.org/0009-0002-7913-0483"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sun-Ao Liu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101624432","display_name":"Yiheng Zhang","orcid":"https://orcid.org/0000-0002-1940-6137"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiheng Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024833177","display_name":"Zhaofan Qiu","orcid":"https://orcid.org/0000-0002-7485-9198"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaofan Qiu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078162380","display_name":"Hongtao Xie","orcid":"https://orcid.org/0000-0002-6249-5315"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtao Xie","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088760097","display_name":"Ting Yao","orcid":"https://orcid.org/0000-0001-7587-101X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ting Yao","raw_affiliation_strings":["HiDream.ai Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"HiDream.ai Inc., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5046158385"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.3838,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90822252,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"779","last_page":"788"},"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":0.9987999796867371,"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":0.9987000226974487,"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":0.7981363534927368},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6497663855552673},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6390814781188965},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6058500409126282},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5616018176078796},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.513787567615509},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.487911194562912},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.48105573654174805},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4711802303791046},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4531649649143219},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4255877435207367},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4206653833389282},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3541538119316101}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7981363534927368},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6497663855552673},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6390814781188965},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6058500409126282},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5616018176078796},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.513787567615509},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.487911194562912},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.48105573654174805},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4711802303791046},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4531649649143219},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4255877435207367},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4206653833389282},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3541538119316101},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612117","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2182495747","display_name":null,"funder_award_id":"2121002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2802911279","display_name":null,"funder_award_id":"Young","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3828173677","display_name":null,"funder_award_id":"62121002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4457724168","display_name":null,"funder_award_id":"YSBR-067","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G4897510482","display_name":null,"funder_award_id":"62232006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6005869675","display_name":null,"funder_award_id":"62121002,62232006,62102384","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G891989852","display_name":null,"funder_award_id":"62102384","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1903029394","https://openalex.org/W2876852810","https://openalex.org/W2964284374","https://openalex.org/W3004019157","https://openalex.org/W3034325957","https://openalex.org/W3035097537","https://openalex.org/W3093025045","https://openalex.org/W3096739052","https://openalex.org/W3138516171","https://openalex.org/W3169998662","https://openalex.org/W3172522282","https://openalex.org/W3187664142","https://openalex.org/W3201770677","https://openalex.org/W4312235312","https://openalex.org/W4312815172","https://openalex.org/W4312935996","https://openalex.org/W4312956471","https://openalex.org/W4386076341","https://openalex.org/W4390874575","https://openalex.org/W6600062020","https://openalex.org/W6600339457","https://openalex.org/W6714454088"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3177678247","https://openalex.org/W3103844505","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2145850538"],"abstract_inverted_index":{"Referring":[0,106],"image":[1,173],"segmentation":[2],"aims":[3],"to":[4,49,57,71,86,140,164],"segment":[5],"the":[6,29,43,59,115,142,171,176],"target":[7,44],"object":[8,45],"described":[9],"by":[10,19,90],"a":[11,34,50,110,131],"natural-language":[12],"utterance.":[13],"Recent":[14],"approaches":[15],"typically":[16],"distinguish":[17],"pixels":[18],"aligning":[20],"pixel-wise":[21,153],"visual":[22,61,75,93,146,154],"features":[23,26,67,97,120,144],"with":[24,73,135,145,152,178],"linguistic":[25,66,96,119,143],"extracted":[27],"from":[28,170],"referring":[30],"description.":[31],"Nevertheless,":[32],"such":[33],"free-form":[35],"description":[36],"only":[37],"specifies":[38],"certain":[39],"discriminative":[40],"attributes":[41],"of":[42,53,118,159],"or":[46],"its":[47],"relations":[48],"limited":[51],"number":[52],"objects,":[54],"which":[55,148],"fails":[56],"represent":[58],"rich":[60,92],"context":[62,94],"adequately.":[63],"The":[64],"stand-alone":[65],"are":[68,149,162],"therefore":[69],"unable":[70],"align":[72],"all":[74],"concepts,":[76],"resulting":[77],"in":[78],"inaccurate":[79],"segmentation.":[80],"In":[81],"this":[82,88],"paper,":[83],"we":[84,103],"propose":[85],"address":[87],"issue":[89],"incorporating":[91],"into":[95,166],"for":[98],"sufficient":[99],"vision-language":[100,123],"alignment.":[101],"Specifically,":[102],"present":[104],"Context-Aware":[105],"Image":[107],"Segmentation":[108],"(CARIS),":[109],"novel":[111],"architecture":[112],"that":[113,185],"enhances":[114],"contextual":[116,168],"awareness":[117],"via":[121],"sequential":[122,136],"attention":[124,139],"and":[125,174],"learnable":[126,160],"prompts.":[127],"Technically,":[128],"CARIS":[129,186],"develops":[130],"context-aware":[132],"mask":[133],"decoder":[134],"bidirectional":[137],"cross-modal":[138],"integrate":[141],"context,":[147],"then":[150],"aligned":[151],"features.":[155],"Furthermore,":[156],"two":[157],"groups":[158],"prompts":[161],"employed":[163],"delve":[165],"additional":[167],"information":[169],"input":[172],"facilitate":[175],"alignment":[177],"non-target":[179],"pixels,":[180],"respectively.":[181],"Extensive":[182],"experiments":[183],"demonstrate":[184],"achieves":[187],"new":[188],"state-of-the-art":[189],"performances":[190],"on":[191],"three":[192],"public":[193],"benchmarks.":[194],"Code":[195],"is":[196],"available":[197],"at":[198],"https://github.com/lsa1997/CARIS.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}