{"id":"https://openalex.org/W4308236060","doi":"https://doi.org/10.1109/icip46576.2022.9897564","title":"Residual Graph Attention Network and Expression-Respect Data Augmentation Aided Visual Grounding","display_name":"Residual Graph Attention Network and Expression-Respect Data Augmentation Aided Visual Grounding","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308236060","doi":"https://doi.org/10.1109/icip46576.2022.9897564"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897564","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5100404631","display_name":"Jia Wang","orcid":"https://orcid.org/0000-0002-0998-251X"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Jia Wang","raw_affiliation_strings":["National Yang Ming Chiao Tung University"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043430724","display_name":"Hung\u2010Yi Wu","orcid":"https://orcid.org/0000-0002-1260-6259"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Wu","raw_affiliation_strings":["National Yang Ming Chiao Tung University"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010007692","display_name":"Jun-Cheng Chen","orcid":"https://orcid.org/0000-0002-0209-8932"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jun-Cheng Chen","raw_affiliation_strings":["Academia Sinica"],"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040050806","display_name":"Hong-Han Shuai","orcid":"https://orcid.org/0000-0003-2216-077X"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hong-Han Shuai","raw_affiliation_strings":["National Yang Ming Chiao Tung University"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000780442","display_name":"Wen-Huang Cheng","orcid":"https://orcid.org/0000-0002-4662-7875"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Huang Cheng","raw_affiliation_strings":["National Yang Ming Chiao Tung University"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100404631"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.1806,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51497219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"326","last_page":"330"},"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":0.998199999332428,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9973999857902527,"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":0.7318006157875061},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.618793249130249},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6161742210388184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5801522731781006},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5157487988471985},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4519892632961273},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4407833218574524},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4287009537220001},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3634284436702728},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3547065556049347},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32644861936569214},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1498751938343048},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08514583110809326}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7318006157875061},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.618793249130249},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6161742210388184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5801522731781006},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5157487988471985},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4519892632961273},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4407833218574524},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4287009537220001},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3634284436702728},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3547065556049347},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32644861936569214},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1498751938343048},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08514583110809326},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897564","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322108","display_name":"Ministry of Science and Technology","ror":"https://ror.org/032e49973"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2097117768","https://openalex.org/W2109586012","https://openalex.org/W2131774270","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2745461083","https://openalex.org/W2886641317","https://openalex.org/W2904910963","https://openalex.org/W2960655175","https://openalex.org/W2963518342","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2986755220","https://openalex.org/W2992308087","https://openalex.org/W3006154882","https://openalex.org/W3035268124","https://openalex.org/W3035688398","https://openalex.org/W3048341138","https://openalex.org/W3090449556","https://openalex.org/W3159619744","https://openalex.org/W3173364567","https://openalex.org/W3176659256","https://openalex.org/W4214490042","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6676497082","https://openalex.org/W6739901393","https://openalex.org/W6779473860"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W2560215812","https://openalex.org/W2949601986","https://openalex.org/W3124914020","https://openalex.org/W2141033859","https://openalex.org/W2788972299","https://openalex.org/W2498789492","https://openalex.org/W2521347458","https://openalex.org/W2077542787","https://openalex.org/W4300237897"],"abstract_inverted_index":{"Visual":[0],"grounding":[1,90],"aims":[2],"to":[3,18,30,37,104,121],"localize":[4],"a":[5,13,27,57],"target":[6,83,126],"object":[7,47],"in":[8,48],"an":[9,49,70,113],"image":[10],"based":[11,117],"on":[12,118],"given":[14],"text":[15],"description.":[16],"Due":[17],"the":[19,39,43,46,82,106],"innate":[20],"complexity":[21],"of":[22,33,108,123],"language,":[23],"it":[24],"is":[25],"still":[26],"challenging":[28],"problem":[29],"perform":[31,112],"reasoning":[32,78],"complex":[34,92],"expressions":[35,93],"and":[36,45,74,125,143],"infer":[38],"underlying":[40],"relationship":[41],"between":[42],"expression":[44],"image.":[50],"To":[51],"address":[52],"these":[53],"issues,":[54],"we":[55,111],"propose":[56],"residual":[58],"graph":[59,73,100,140],"attention":[60],"network":[61,101],"for":[62],"visual":[63,89],"grounding.":[64],"The":[65,128],"proposed":[66,129],"approach":[67,130],"first":[68],"builds":[69],"expression-guided":[71],"relation":[72],"then":[75],"performs":[76],"multi-step":[77],"followed":[79],"by":[80,94],"matching":[81],"object.":[84],"It":[85],"allows":[86],"performing":[87],"better":[88,132],"with":[91,134],"using":[95],"deeper":[96],"layers":[97],"than":[98,137],"other":[99,138],"approaches.":[102],"Moreover,":[103],"increase":[105],"diversity":[107],"training":[109],"data,":[110],"expression-respect":[114],"data":[115],"augmentation":[116],"copy-paste":[119],"operations":[120],"pairs":[122],"source":[124],"images.":[127],"achieves":[131],"performance":[133],"extensive":[135],"experiments":[136],"state-of-the-art":[139],"network-based":[141],"approaches":[142],"demonstrates":[144],"its":[145],"effectiveness.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}