{"id":"https://openalex.org/W4308235694","doi":"https://doi.org/10.1109/icip46576.2022.9897578","title":"Spatial-Semantic Attention for Grounded Image Captioning","display_name":"Spatial-Semantic Attention for Grounded Image Captioning","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308235694","doi":"https://doi.org/10.1109/icip46576.2022.9897578"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897578","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/A5076823429","display_name":"Wenzhe Hu","orcid":"https://orcid.org/0000-0002-7941-231X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenzhe Hu","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China","University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067691968","display_name":"Lanxiao Wang","orcid":"https://orcid.org/0000-0002-3745-0262"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanxiao Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China","University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044954967","display_name":"Linfeng Xu","orcid":"https://orcid.org/0000-0002-9934-0958"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linfeng Xu","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China","University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076823429"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0602,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.28668188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"65"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9929999709129333,"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":0.9825000166893005,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8671756982803345},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8021962642669678},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6386059522628784},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.6243825554847717},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5253419280052185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5078526139259338},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4720157980918884},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45494744181632996},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4449637234210968},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41095319390296936},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32953163981437683},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07047176361083984}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8671756982803345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8021962642669678},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6386059522628784},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.6243825554847717},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5253419280052185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5078526139259338},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4720157980918884},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45494744181632996},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4449637234210968},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41095319390296936},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32953163981437683},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07047176361083984},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897578","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1773149199","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2506483933","https://openalex.org/W2552161745","https://openalex.org/W2600463316","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2890531016","https://openalex.org/W2968101724","https://openalex.org/W3035323998","https://openalex.org/W3103237788","https://openalex.org/W3187369021","https://openalex.org/W3196091473","https://openalex.org/W3207004259","https://openalex.org/W3207460436","https://openalex.org/W6631190155","https://openalex.org/W6678262379","https://openalex.org/W6785947951"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Grounded":[0],"image":[1,31],"captioning":[2,133],"models":[3,142],"usually":[4],"process":[5],"high-dimensional":[6],"vectors":[7,17],"from":[8,75,102],"the":[9,37,42,47,73,76,81,85,89,94,99,103,124,144],"feature":[10,38,104],"extractor":[11,39,105],"to":[12,79,84,111,122],"generate":[13],"descriptions.":[14],"However,":[15],"mere":[16],"do":[18],"not":[19],"provide":[20],"adequate":[21],"information.":[22,57],"The":[23],"model":[24,82],"needs":[25],"more":[26],"explicit":[27],"information":[28,53,110],"for":[29],"grounded":[30],"captioning.":[32],"Besides":[33],"high":[34,130],"dimensional":[35],"vectors,":[36],"also":[40],"predicts":[41],"locations":[43],"and":[44,54,98,108,134,137],"categories":[45],"of":[46,96],"objects,":[48],"which":[49,71],"contains":[50],"low-level":[51],"spatial":[52,107],"high-level":[55],"semantic":[56,109],"To":[58],"this":[59],"end,":[60],"we":[61,117],"propose":[62,118],"a":[63,119],"new":[64],"attention":[65,91,113],"module":[66,92],"called":[67],"Spatial-Semantic":[68],"(SS)":[69],"Attention,":[70],"utilizes":[72],"predictions":[74],"backbone":[77],"network":[78],"help":[80],"attend":[83],"correct":[86],"objects.":[87],"Specifically,":[88],"SS":[90,125],"collects":[93],"position":[95],"proposals":[97],"class":[100],"probabilities":[101],"as":[106],"assist":[112],"weighting.":[114],"In":[115],"addition,":[116],"grounding":[120,135],"loss":[121],"supervise":[123],"attention.":[126],"Our":[127],"method":[128],"achieves":[129],"performance":[131],"on":[132,143],"metrics":[136],"outperforms":[138],"some":[139],"powerful":[140],"previous":[141],"Flickr30k":[145],"Entities":[146],"dataset.":[147]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}