{"id":"https://openalex.org/W3206197237","doi":"https://doi.org/10.1109/icra48506.2021.9561797","title":"Referring Image Segmentation via Language-Driven Attention","display_name":"Referring Image Segmentation via Language-Driven Attention","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3206197237","doi":"https://doi.org/10.1109/icra48506.2021.9561797","mag":"3206197237"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","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/A5003705508","display_name":"Ding-Jie Chen","orcid":"https://orcid.org/0000-0001-7649-7824"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Ding-Jie Chen","raw_affiliation_strings":["Academia Sinica,Institute of Information Science,Taiwan","Institute of Information Science, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Institute of Information Science,Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103130251","display_name":"He\u2010Yen Hsieh","orcid":"https://orcid.org/0000-0001-7657-6549"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"He-Yen Hsieh","raw_affiliation_strings":["Academia Sinica,Institute of Information Science,Taiwan","Institute of Information Science, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Institute of Information Science,Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043386280","display_name":"Tyng-Luh Liu","orcid":"https://orcid.org/0000-0002-8366-5213"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tyng-Luh Liu","raw_affiliation_strings":["Academia Sinica,Institute of Information Science,Taiwan","Institute of Information Science, Academia Sinica, Taiwan","Taiwan AI Labs"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Institute of Information Science,Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Taiwan AI Labs","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003705508"],"corresponding_institution_ids":["https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":0.1921,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.49828431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"13997","last_page":"14003"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987999796867371,"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":0.9961000084877014,"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":0.7151297330856323},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.6334020495414734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.578372597694397},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4832668900489807},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4777216613292694},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46692439913749695},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44073134660720825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7151297330856323},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6334020495414734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.578372597694397},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4832668900489807},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4777216613292694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46692439913749695},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44073134660720825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48506.2021.9561797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"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":74,"referenced_works":["https://openalex.org/W1485009520","https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1903029394","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2097117768","https://openalex.org/W2115595010","https://openalex.org/W2133564696","https://openalex.org/W2141311545","https://openalex.org/W2154071538","https://openalex.org/W2161236525","https://openalex.org/W2250539671","https://openalex.org/W2251512949","https://openalex.org/W2302548814","https://openalex.org/W2412782625","https://openalex.org/W2463565445","https://openalex.org/W2470673105","https://openalex.org/W2489434015","https://openalex.org/W2515963802","https://openalex.org/W2519091744","https://openalex.org/W2565639579","https://openalex.org/W2605127024","https://openalex.org/W2747053578","https://openalex.org/W2751185861","https://openalex.org/W2752782242","https://openalex.org/W2798556392","https://openalex.org/W2798895485","https://openalex.org/W2799263800","https://openalex.org/W2876852810","https://openalex.org/W2894964039","https://openalex.org/W2952793010","https://openalex.org/W2962749469","https://openalex.org/W2963091558","https://openalex.org/W2963109634","https://openalex.org/W2963403868","https://openalex.org/W2963420686","https://openalex.org/W2963668159","https://openalex.org/W2963735856","https://openalex.org/W2963800628","https://openalex.org/W2963954913","https://openalex.org/W2964052394","https://openalex.org/W2964195914","https://openalex.org/W2964308564","https://openalex.org/W2964309882","https://openalex.org/W2964345792","https://openalex.org/W2973233205","https://openalex.org/W2980088508","https://openalex.org/W2982763192","https://openalex.org/W2984121207","https://openalex.org/W2991471181","https://openalex.org/W3004019157","https://openalex.org/W3020827971","https://openalex.org/W3034325957","https://openalex.org/W3034692043","https://openalex.org/W3034764937","https://openalex.org/W3035097537","https://openalex.org/W3091422568","https://openalex.org/W4238155858","https://openalex.org/W4385245566","https://openalex.org/W6628877408","https://openalex.org/W6630875275","https://openalex.org/W6677032036","https://openalex.org/W6679434410","https://openalex.org/W6719057275","https://openalex.org/W6726001474","https://openalex.org/W6739901393","https://openalex.org/W6743638068","https://openalex.org/W6748481559","https://openalex.org/W6761275059","https://openalex.org/W6764388409","https://openalex.org/W6768730002","https://openalex.org/W6775233535"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2501551404","https://openalex.org/W4385583601","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W4395685956","https://openalex.org/W2799953226","https://openalex.org/W4398146871","https://openalex.org/W1522196789"],"abstract_inverted_index":{"This":[0],"paper":[1],"aims":[2],"to":[3,30,38,61,69,115,147,186],"tackle":[4],"the":[5,16,32,40,45,49,53,63,72,84,87,92,97,104,117,122,130,144,154,159,166,187,195,201,208,211,223,228,244],"problem":[6],"of":[7,18,112,178,194,198,210],"referring":[8,33,234],"image":[9,34,235],"segmentation,":[10],"which":[11],"is":[12,36,183,218],"targeted":[13],"at":[14],"reasoning":[15],"region":[17],"interest":[19],"referred":[20],"by":[21],"a":[22,109,179,191],"query":[23,50,132,188],"natural":[24],"language":[25],"sentence.":[26,133,189],"One":[27],"key":[28],"issue":[29],"address":[31],"segmentation":[35,105,236],"how":[37,171],"establish":[39],"cross-modal":[41,73,93,99,118,145,160,213],"representation":[42,74,100,119,217],"for":[43,90,103,120,157,221,227],"encoding":[44],"two":[46,88,155,196],"modalities,":[47],"namely,":[48],"sentence":[51],"and":[52,129,149,151,165,225,243],"input":[54],"image.":[55],"Most":[56],"existing":[57],"methods":[58],"are":[59],"designed":[60],"concatenate":[62],"features":[64],"from":[65],"each":[66,76,173,176],"modality":[67],"or":[68,175],"gradually":[70],"encode":[71,116],"concerning":[75],"word’s":[77],"effect.":[78],"In":[79],"contrast,":[80],"our":[81,233,249],"approach":[82],"leverages":[83],"correlation":[85,146],"between":[86,124],"modalities":[89],"constructing":[91],"representation.":[94,161,214],"To":[95],"make":[96],"resulting":[98,216],"more":[101],"discriminative":[102],"task,":[106],"we":[107],"propose":[108],"novel":[110],"mechanism":[111],"language-driven":[113],"attention":[114,123,164,168],"reflecting":[121],"every":[125],"single":[126],"visual":[127],"element":[128],"entire":[131],"The":[134,162,215],"proposed":[135,202],"mechanism,":[136],"named":[137],"as":[138],"Language-Driven":[139],"Attention":[140],"(LDA),":[141],"first":[142],"decouples":[143],"channel-attention":[148],"spatial-attention":[150],"then":[152],"integrates":[153],"attentions":[156],"obtaining":[158],"channel":[163,174],"spatial":[167],"respectively":[169],"reveal":[170],"sensitive":[172],"pixel":[177],"particular":[180],"feature":[181,199],"map":[182],"with":[184],"respect":[185],"With":[190],"proper":[192],"fusion":[193],"kinds":[197],"attention,":[200],"LDA":[203],"model":[204,237,250],"can":[205],"effectively":[206],"guide":[207],"generation":[209],"final":[212],"further":[219],"strengthened":[220],"capturing":[222],"multi-receptive-field":[224],"multi-level-semantic":[226],"intended":[229],"segmentation.":[230],"We":[231],"assess":[232],"on":[238],"four":[239],"public":[240],"benchmark":[241],"datasets,":[242],"experimental":[245],"results":[246],"show":[247],"that":[248],"achieves":[251],"state-of-the-art":[252],"performance":[253]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}