{"id":"https://openalex.org/W2965336788","doi":"https://doi.org/10.1109/tip.2019.2930176","title":"Unambiguous Scene Text Segmentation With Referring Expression Comprehension","display_name":"Unambiguous Scene Text Segmentation With Referring Expression Comprehension","publication_year":2019,"publication_date":"2019-07-26","ids":{"openalex":"https://openalex.org/W2965336788","doi":"https://doi.org/10.1109/tip.2019.2930176","mag":"2965336788","pmid":"https://pubmed.ncbi.nlm.nih.gov/31369378"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2019.2930176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2019.2930176","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100617159","display_name":"Xuejian Rong","orcid":"https://orcid.org/0000-0001-6617-9582"},"institutions":[{"id":"https://openalex.org/I125687163","display_name":"City College of New York","ror":"https://ror.org/00wmhkr98","country_code":"US","type":"education","lineage":["https://openalex.org/I125687163"]},{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]},{"id":"https://openalex.org/I4210093530","display_name":"City College","ror":"https://ror.org/00h90tg62","country_code":"US","type":"education","lineage":["https://openalex.org/I4210093530"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xuejian Rong","raw_affiliation_strings":["Department of Electrical Engineering, The City College, The City University of New York, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The City College, The City University of New York, New York, NY, USA","institution_ids":["https://openalex.org/I174216632","https://openalex.org/I4210093530","https://openalex.org/I125687163"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038048230","display_name":"Chucai Yi","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chucai Yi","raw_affiliation_strings":["Google on Augmented Reality, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google on Augmented Reality, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074244244","display_name":"Yingli Tian","orcid":"https://orcid.org/0000-0003-4458-360X"},"institutions":[{"id":"https://openalex.org/I125687163","display_name":"City College of New York","ror":"https://ror.org/00wmhkr98","country_code":"US","type":"education","lineage":["https://openalex.org/I125687163"]},{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]},{"id":"https://openalex.org/I4210093530","display_name":"City College","ror":"https://ror.org/00h90tg62","country_code":"US","type":"education","lineage":["https://openalex.org/I4210093530"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingli Tian","raw_affiliation_strings":["Department of Electrical Engineering, The City College, The City University of New York, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The City College, The City University of New York, New York, NY, USA","institution_ids":["https://openalex.org/I174216632","https://openalex.org/I4210093530","https://openalex.org/I125687163"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100617159"],"corresponding_institution_ids":["https://openalex.org/I125687163","https://openalex.org/I174216632","https://openalex.org/I4210093530"],"apc_list":null,"apc_paid":null,"fwci":2.8611,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.92903093,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"591","last_page":"601"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9983000159263611,"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":0.9965999722480774,"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":0.778232991695404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7210482358932495},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6956210136413574},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6069908738136292},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5388389229774475},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4882235825061798},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.47498220205307007},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4748699367046356},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.46418896317481995},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.42171812057495117},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41551318764686584},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40656834840774536},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15654146671295166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.778232991695404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7210482358932495},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6956210136413574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6069908738136292},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5388389229774475},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4882235825061798},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47498220205307007},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4748699367046356},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.46418896317481995},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.42171812057495117},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41551318764686584},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40656834840774536},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15654146671295166},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2019.2930176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2019.2930176","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:31369378","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31369378","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3930469214","display_name":null,"funder_award_id":"IIS-1400802","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":97,"referenced_works":["https://openalex.org/W70975097","https://openalex.org/W284368147","https://openalex.org/W1510835000","https://openalex.org/W1686810756","https://openalex.org/W1745334888","https://openalex.org/W1773149199","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1892016050","https://openalex.org/W1903029394","https://openalex.org/W1905882502","https://openalex.org/W1922126009","https://openalex.org/W1947481528","https://openalex.org/W1967140047","https://openalex.org/W1999284580","https://openalex.org/W2008806374","https://openalex.org/W2013237800","https://openalex.org/W2019478948","https://openalex.org/W2044883027","https://openalex.org/W2049705550","https://openalex.org/W2060560731","https://openalex.org/W2061802763","https://openalex.org/W2064675550","https://openalex.org/W2077069816","https://openalex.org/W2112912048","https://openalex.org/W2117539524","https://openalex.org/W2121947860","https://openalex.org/W2124351162","https://openalex.org/W2124592697","https://openalex.org/W2127426251","https://openalex.org/W2130942839","https://openalex.org/W2135231474","https://openalex.org/W2148214126","https://openalex.org/W2150259535","https://openalex.org/W2150427047","https://openalex.org/W2161131193","https://openalex.org/W2166949156","https://openalex.org/W2193145675","https://openalex.org/W2247513039","https://openalex.org/W2251512949","https://openalex.org/W2253806798","https://openalex.org/W2281288138","https://openalex.org/W2294834600","https://openalex.org/W2302548814","https://openalex.org/W2333563142","https://openalex.org/W2339589954","https://openalex.org/W2343052201","https://openalex.org/W2344822769","https://openalex.org/W2395611524","https://openalex.org/W2462848072","https://openalex.org/W2479423890","https://openalex.org/W2489434015","https://openalex.org/W2519818067","https://openalex.org/W2520141964","https://openalex.org/W2520859141","https://openalex.org/W2550687635","https://openalex.org/W2561196672","https://openalex.org/W2574887079","https://openalex.org/W2592939477","https://openalex.org/W2604243686","https://openalex.org/W2605076167","https://openalex.org/W2605127024","https://openalex.org/W2605982830","https://openalex.org/W2725486421","https://openalex.org/W2747107070","https://openalex.org/W2772800855","https://openalex.org/W2875814315","https://openalex.org/W2962706528","https://openalex.org/W2962773189","https://openalex.org/W2962810613","https://openalex.org/W2962986948","https://openalex.org/W2963109634","https://openalex.org/W2963115613","https://openalex.org/W2963536419","https://openalex.org/W2963735856","https://openalex.org/W2963758027","https://openalex.org/W2963977642","https://openalex.org/W2964018263","https://openalex.org/W2964114039","https://openalex.org/W3098232790","https://openalex.org/W3106250896","https://openalex.org/W4295246343","https://openalex.org/W6610281778","https://openalex.org/W6637373629","https://openalex.org/W6638742206","https://openalex.org/W6676647902","https://openalex.org/W6678846912","https://openalex.org/W6679436768","https://openalex.org/W6691603626","https://openalex.org/W6702842988","https://openalex.org/W6729791593","https://openalex.org/W6730587030","https://openalex.org/W6734061528","https://openalex.org/W6739844568","https://openalex.org/W6746206475","https://openalex.org/W6747438827","https://openalex.org/W6757081750"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W2012262991","https://openalex.org/W2373794620","https://openalex.org/W2060629350","https://openalex.org/W2357294589","https://openalex.org/W2386861027","https://openalex.org/W2349302580","https://openalex.org/W2390154576","https://openalex.org/W3112772842","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Text":[0],"instance":[1,170],"provides":[2],"valuable":[3],"information":[4,115],"for":[5,25],"the":[6,20,27,99,161,164,168],"understanding":[7,26],"and":[8,31,56,113,120,132,193],"interpretation":[9],"of":[10,36,87,94,124,140,163],"natural":[11,68,125,194],"scenes.":[12],"The":[13,85],"rich,":[14],"precise":[15],"high-level":[16],"semantics":[17],"embodied":[18],"in":[19,80],"text":[21,60,65,75,96,141,152,169,191],"could":[22],"be":[23],"beneficial":[24],"world":[28],"around":[29],"us,":[30],"empower":[32],"a":[33,77,83,106,149],"wide":[34],"range":[35],"real-world":[37],"applications.":[38],"While":[39],"most":[40],"recent":[41],"visual":[42,112,122,176],"phrase":[43],"grounding":[44],"approaches":[45],"focus":[46],"on":[47,76,167,199],"general":[48],"objects,":[49],"this":[50,88],"paper":[51],"explores":[52],"extracting":[53],"designated":[54],"texts":[55],"predicting":[57],"unambiguous":[58],"scene":[59,64,95,126,151],"segmentation":[61,66,93,155,171],"mask,":[62],"i.e.":[63],"from":[67,98,189],"language":[69,195],"descriptions":[70],"(referring":[71],"expressions)":[72],"like":[73],"orange":[74],"little":[78],"boy":[79],"black":[81],"swinging":[82],"bat.":[84],"solution":[86],"novel":[89],"problem":[90],"enables":[91],"accurate":[92],"instances":[97],"complex":[100],"background.":[101],"In":[102],"our":[103,182],"proposed":[104,165],"framework,":[105],"unified":[107],"deep":[108],"network":[109],"jointly":[110],"models":[111],"linguistic":[114],"by":[116],"encoding":[117],"both":[118],"region-level":[119],"pixel-level":[121],"features":[123,177],"images":[127],"into":[128,136],"spatial":[129],"feature":[130],"maps,":[131],"then":[133],"decode":[134],"them":[135],"saliency":[137],"response":[138],"map":[139],"instances.":[142],"To":[143],"conduct":[144],"quantitative":[145],"evaluations,":[146],"we":[147],"establish":[148],"new":[150],"referring":[153],"expression":[154],"dataset:":[156],"COCO-CharRef.":[157],"Experimental":[158],"results":[159],"demonstrate":[160],"effectiveness":[162],"framework":[166,183],"task.":[172],"By":[173],"combining":[174],"image-based":[175],"with":[178],"language-based":[179],"textual":[180],"explanations,":[181],"outperforms":[184],"baselines":[185],"that":[186],"are":[187],"derived":[188],"state-of-the-art":[190],"localization":[192],"object":[196],"retrieval":[197],"methods":[198],"COCO-CharRef":[200],"dataset.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":7}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}