{"id":"https://openalex.org/W4312266680","doi":"https://doi.org/10.1145/3561613.3561617","title":"Hybrid-Spatial Transformer for Image Captioning","display_name":"Hybrid-Spatial Transformer for Image Captioning","publication_year":2022,"publication_date":"2022-08-19","ids":{"openalex":"https://openalex.org/W4312266680","doi":"https://doi.org/10.1145/3561613.3561617"},"language":"en","primary_location":{"id":"doi:10.1145/3561613.3561617","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3561613.3561617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 The 5th International Conference on Control and Computer Vision","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/A5110964794","display_name":"Jincheng Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":true,"raw_author_name":"Jincheng Zheng","raw_affiliation_strings":["University of Macau, China"],"raw_orcid":"https://orcid.org/0000-0003-1788-3746","affiliations":[{"raw_affiliation_string":"University of Macau, China","institution_ids":["https://openalex.org/I6469544","https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005772506","display_name":"Chi\u2010Man Pun","orcid":"https://orcid.org/0000-0003-1788-3746"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I6469544","display_name":"City University of Macau","ror":"https://ror.org/04gpd4q15","country_code":"MO","type":"education","lineage":["https://openalex.org/I6469544"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Chi-Man Pun","raw_affiliation_strings":["University of Macau, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau, China","institution_ids":["https://openalex.org/I6469544","https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110964794"],"corresponding_institution_ids":["https://openalex.org/I204512498","https://openalex.org/I6469544"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12355219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22","last_page":"28"},"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":0.9988999962806702,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9980000257492065,"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/closed-captioning","display_name":"Closed captioning","score":0.8910365104675293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6670417785644531},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6259728074073792},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4096476435661316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3583267331123352},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.23100176453590393},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15128269791603088},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07363113760948181}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8910365104675293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6670417785644531},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6259728074073792},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4096476435661316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3583267331123352},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.23100176453590393},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15128269791603088},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07363113760948181}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3561613.3561617","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3561613.3561617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 The 5th International Conference on Control and Computer Vision","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2041486337","https://openalex.org/W2194775991","https://openalex.org/W2506483933","https://openalex.org/W2565770002","https://openalex.org/W2575842049","https://openalex.org/W2600463316","https://openalex.org/W2745461083","https://openalex.org/W2746403246","https://openalex.org/W2795151422","https://openalex.org/W2890531016","https://openalex.org/W2934700355","https://openalex.org/W2956367483","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2964080601","https://openalex.org/W2986670728","https://openalex.org/W2996849375","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W4234552385","https://openalex.org/W4301409532"],"related_works":["https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757"],"abstract_inverted_index":{"Recent":[0],"years,":[1],"the":[2,45,68,122],"transformer-based":[3],"model":[4,36,138],"has":[5],"achieved":[6],"great":[7],"success":[8],"in":[9,104],"many":[10],"tasks":[11,27],"such":[12],"as":[13,28,53],"machine":[14],"translation.":[15],"This":[16],"encoder-decoder":[17],"architecture":[18],"is":[19,102,112,125],"proved":[20],"to":[21,76,83,115,127],"be":[22],"useful":[23],"for":[24,37],"image":[25,38,52],"captioning":[26],"well.":[29],"We":[30],"propose":[31],"a":[32,95],"novel":[33],"Hybrid-Spatial":[34],"Transformer":[35],"captioning.":[39],"In":[40],"this":[41],"work,":[42],"we":[43,72],"combine":[44],"Global":[46],"information":[47,50,75],"and":[48,61,120,147],"Local":[49],"of":[51,55,70],"input":[54],"encoder":[56,119],"which":[57,101],"extracted":[58],"by":[59,79],"VGG16":[60],"Faster":[62],"R-CNN":[63],"respectively.":[64],"To":[65],"further":[66],"improve":[67],"performance":[69,143],"model,":[71],"add":[73],"spatial":[74],"attention":[77,84],"layer":[78],"incorporating":[80],"geometry":[81],"features":[82],"weight.":[85],"What\u2019s":[86],"more,":[87],"queries":[88],"Q,":[89],"keys":[90,128],"K,":[91],"values":[92,116],"V":[93,117],"are":[94],"bit":[96],"different":[97],"from":[98],"standard":[99],"transformer,":[100],"reflected":[103],"theses":[105],"aspects.":[106],"The":[107,132],"positional":[108,123],"encoding":[109],"or":[110],"embedding":[111,124],"not":[113],"added":[114,126],"both":[118],"decoder,":[121],"K":[129],"on":[130,144,149],"cross-attention.":[131],"experimental":[133],"results":[134],"illustrate":[135],"that":[136],"our":[137],"can":[139],"achieve":[140],"state-of-the":[141],"art":[142],"CIDEr-D,":[145],"METEROR":[146],"BLEU-1":[148],"MS-COCO":[150],"dataset.":[151]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}