{"id":"https://openalex.org/W4200625668","doi":"https://doi.org/10.1109/iscmi53840.2021.9654828","title":"A Linear Sub-Structure with Co-Variance Shift for Image Captioning","display_name":"A Linear Sub-Structure with Co-Variance Shift for Image Captioning","publication_year":2021,"publication_date":"2021-11-26","ids":{"openalex":"https://openalex.org/W4200625668","doi":"https://doi.org/10.1109/iscmi53840.2021.9654828"},"language":"en","primary_location":{"id":"doi:10.1109/iscmi53840.2021.9654828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscmi53840.2021.9654828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI)","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/A5102965905","display_name":"Shaik Rafi","orcid":"https://orcid.org/0000-0002-7262-8193"},"institutions":[{"id":"https://openalex.org/I91277730","display_name":"Maulana Azad National Institute of Technology","ror":"https://ror.org/026vtd268","country_code":"IN","type":"education","lineage":["https://openalex.org/I91277730"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Shaik Rafi","raw_affiliation_strings":["Department of Computer Science and Engineering, National Institute of Technology Mizoram, Aizawl, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, National Institute of Technology Mizoram, Aizawl, India","institution_ids":["https://openalex.org/I91277730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077717775","display_name":"Ranjita Das","orcid":"https://orcid.org/0000-0001-6184-6294"},"institutions":[{"id":"https://openalex.org/I91277730","display_name":"Maulana Azad National Institute of Technology","ror":"https://ror.org/026vtd268","country_code":"IN","type":"education","lineage":["https://openalex.org/I91277730"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ranjita Das","raw_affiliation_strings":["Department of Computer Science and Engineering, National Institute of Technology Mizoram, Aizawl, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, National Institute of Technology Mizoram, Aizawl, India","institution_ids":["https://openalex.org/I91277730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102965905"],"corresponding_institution_ids":["https://openalex.org/I91277730"],"apc_list":null,"apc_paid":null,"fwci":0.6725,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.72104575,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"242","last_page":"246"},"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":0.9975000023841858,"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":0.9918000102043152,"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":0.934711217880249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7925454378128052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6792705059051514},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6059718728065491},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5759903192520142},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5078127980232239},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48630937933921814},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.46736738085746765},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4194166362285614},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3347880244255066},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1187029778957367}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.934711217880249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925454378128052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6792705059051514},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6059718728065491},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5759903192520142},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5078127980232239},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48630937933921814},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.46736738085746765},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4194166362285614},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3347880244255066},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1187029778957367},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscmi53840.2021.9654828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscmi53840.2021.9654828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 8th International Conference on Soft Computing & Machine Intelligence (ISCMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1514535095","https://openalex.org/W1811254738","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1931639407","https://openalex.org/W2109586012","https://openalex.org/W2117539524","https://openalex.org/W2220981600","https://openalex.org/W2481240925","https://openalex.org/W2552161745","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2885013662","https://openalex.org/W2893345206","https://openalex.org/W2913618459","https://openalex.org/W2943885184","https://openalex.org/W2979739834","https://openalex.org/W2990349092","https://openalex.org/W6630875275","https://openalex.org/W6638742206","https://openalex.org/W6639657675","https://openalex.org/W6639694449","https://openalex.org/W6676497082"],"related_works":["https://openalex.org/W3217195652","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/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Automatic":[0],"description":[1,169],"of":[2,11,29,54,74,78,82,97,126,141,163,170,196,202,217],"image":[3,17,32,55,65,124,152,165,172,185],"has":[4,213],"attracted":[5],"many":[6],"researchers":[7],"in":[8,18,110,129,205],"the":[9,16,87,92,106,164,171,181,187,189,194],"field":[10],"computer":[12],"vision":[13],"for":[14,63,86,143,184],"captioning":[15,144],"artificial":[19],"intelligence":[20],"which":[21,72,99,116,157,199],"connects":[22],"with":[23,102,193,210],"Natural":[24],"Language":[25],"Processing.":[26],"Exact":[27],"generation":[28],"captions":[30],"to":[31,39,90,104,122,137,166,173],"is":[33,117],"necessary":[34],"but":[35],"it":[36],"lacks":[37],"due":[38],"Gradient":[40],"Diminishing":[41],"problem,":[42],"LSTM":[43],"can":[44],"overcome":[45],"this":[46],"problem":[47],"by":[48,145],"fusing":[49],"local":[50,95],"and":[51,56,94],"global":[52,93],"characteristics":[53],"text":[57,75,183],"that":[58,135,212],"generates":[59],"sequenced":[60,139],"word":[61,88],"prediction":[62],"accurate":[64,168],"captioning.":[66],"We":[67,131],"consider":[68,91],"Flickr":[69],"8k":[70],"data-set":[71],"consists":[73],"as":[76,186],"descriptions":[77],"images.":[79],"The":[80],"use":[81],"GLoVe":[83],"embedding":[84],"helps":[85,136],"representation":[89],"features":[96,125,153],"images":[98],"finds":[100],"distance":[101],"Euclidean":[103],"understand":[105],"relationship":[107,147,179],"between":[108,148,180],"words":[109,142],"vector":[111],"space.":[112],"Inception":[113],"V3":[114],"architecture":[115],"pretrained":[118],"on":[119,160],"ImageNet":[120],"used":[121],"extract":[123],"different":[127],"objects":[128],"scenes.":[130],"propose":[132],"Linear":[133],"Sub-Structure":[134],"generate":[138,167],"order":[140],"understanding":[146],"words.":[149],"For":[150],"extracting":[151],"considers":[154],"co-variance":[155],"shift":[156],"mainly":[158],"concentrates":[159],"moving":[161],"parts":[162],"maintain":[174],"a":[175],"semantic":[176],"visual":[177],"grammar":[178],"predicted":[182],"caption,":[188],"proposed":[190],"model":[191,204],"evaluated":[192],"help":[195],"BLEU":[197],"score":[198],"achieves":[200],"state":[201],"art":[203],"our":[206],"work":[207],"while":[208],"compared":[209],"others":[211],"greater":[214],"than":[215],"81%":[216],"accuracy.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}