{"id":"https://openalex.org/W4407360955","doi":"https://doi.org/10.1109/ispacs62486.2024.10867899","title":"Segmentation-Based Attention with Spatial Encoding for Image Captioning","display_name":"Segmentation-Based Attention with Spatial Encoding for Image Captioning","publication_year":2024,"publication_date":"2024-12-10","ids":{"openalex":"https://openalex.org/W4407360955","doi":"https://doi.org/10.1109/ispacs62486.2024.10867899"},"language":"en","primary_location":{"id":"doi:10.1109/ispacs62486.2024.10867899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispacs62486.2024.10867899","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","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/A5113975920","display_name":"Shih-Shinh Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4387154394","display_name":"National Kaohsiung University of Science and Technology","ror":"https://ror.org/00hfj7g70","country_code":null,"type":"education","lineage":["https://openalex.org/I4387154394"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Shih-Shinh Huang","raw_affiliation_strings":["National Kaohsiung University of Science and Technology,Department of Computer and Communication Engineering,Kaohsiung,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Kaohsiung University of Science and Technology,Department of Computer and Communication Engineering,Kaohsiung,Taiwan","institution_ids":["https://openalex.org/I4387154394","https://openalex.org/I4387154394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050896395","display_name":"Feng-Chia Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I189290911","display_name":"National Chung Shan Institute of Science and Technology","ror":"https://ror.org/034ezwg26","country_code":"TW","type":"government","lineage":["https://openalex.org/I189290911"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Feng-Chia Chang","raw_affiliation_strings":["National Chung-Shan Institute Science and Technology,Taoyuan,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Chung-Shan Institute Science and Technology,Taoyuan,Taiwan","institution_ids":["https://openalex.org/I189290911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044278469","display_name":"Shih-Huan Tseng","orcid":"https://orcid.org/0000-0003-3572-5274"},"institutions":[{"id":"https://openalex.org/I4387154394","display_name":"National Kaohsiung University of Science and Technology","ror":"https://ror.org/00hfj7g70","country_code":null,"type":"education","lineage":["https://openalex.org/I4387154394"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shih-Huan Tseng","raw_affiliation_strings":["National Kaohsiung University of Science and Technology,Department of Computer and Communication Engineering,Kaohsiung,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Kaohsiung University of Science and Technology,Department of Computer and Communication Engineering,Kaohsiung,Taiwan","institution_ids":["https://openalex.org/I4387154394","https://openalex.org/I4387154394"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113975920"],"corresponding_institution_ids":["https://openalex.org/I4387154394"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28010015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9933000206947327,"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":0.9868000149726868,"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":0.9649834632873535},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7932936549186707},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7780231237411499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6046807169914246},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5831505060195923},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.547984778881073},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.528772234916687},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.48126858472824097},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32968670129776}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9649834632873535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7932936549186707},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7780231237411499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6046807169914246},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5831505060195923},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.547984778881073},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.528772234916687},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.48126858472824097},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32968670129776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispacs62486.2024.10867899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispacs62486.2024.10867899","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","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":8,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1895577753","https://openalex.org/W2064675550","https://openalex.org/W2745461083","https://openalex.org/W2890531016","https://openalex.org/W2983141445","https://openalex.org/W6685230081","https://openalex.org/W6735463952"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W1522196789"],"abstract_inverted_index":{"With":[0],"the":[1,45,56,65,70,79,84],"proliferation":[2],"and":[3,12,62],"widespread":[4],"deployment":[5],"of":[6,18,25,44],"cameras,":[7],"image":[8,19,35],"captioning":[9,36],"for":[10,34],"automatically":[11],"concisely":[13],"generating":[14],"natural":[15],"language":[16],"descriptions":[17],"contents":[20],"has":[21],"attracted":[22],"a":[23,32],"lot":[24],"attentions.":[26],"In":[27],"this":[28],"work,":[29],"we":[30],"propose":[31],"method":[33,81],"based":[37],"on":[38],"segmentation":[39,42,53],"attention.":[40],"The":[41,51,68,75],"masks":[43],"objects":[46],"are":[47],"from":[48],"Mask":[49],"R-CNN.":[50],"proposed":[52,80],"attention":[54,57],"performs":[55],"in":[58,88],"object":[59],"mask":[60],"level":[61],"further":[63],"encodes":[64],"spatial":[66],"information.":[67],"makes":[69],"generated":[71],"caption":[72],"more":[73],"accurate.":[74],"experiment":[76],"exhibits":[77],"that":[78],"can":[82],"achieve":[83],"high":[85],"BLUE":[86],"scores":[87],"Flickr":[89],"8K":[90],"dataset.":[91]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
