{"id":"https://openalex.org/W4379932896","doi":"https://doi.org/10.1145/3590837.3590929","title":"Fusion Techniques in Neural Network Model for Image Captioning","display_name":"Fusion Techniques in Neural Network Model for Image Captioning","publication_year":2022,"publication_date":"2022-12-23","ids":{"openalex":"https://openalex.org/W4379932896","doi":"https://doi.org/10.1145/3590837.3590929"},"language":"en","primary_location":{"id":"doi:10.1145/3590837.3590929","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3590837.3590929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Information Management & Machine Intelligence","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/A5052504383","display_name":"Varun Prakash Saxena","orcid":"https://orcid.org/0000-0002-2525-642X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Varun Prakash Saxena","raw_affiliation_strings":["Computer Engineering Department, Govt. Women Engineering College Ajmer, Rajasthan, India,"],"raw_orcid":"https://orcid.org/0000-0002-2525-642X","affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Govt. Women Engineering College Ajmer, Rajasthan, India,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092120523","display_name":"Christabell Fredrick","orcid":"https://orcid.org/0009-0001-0247-3915"},"institutions":[{"id":"https://openalex.org/I56287899","display_name":"Maharshi Dayanand Saraswati University","ror":"https://ror.org/0229k3q35","country_code":"IN","type":"education","lineage":["https://openalex.org/I56287899"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Christabell Fredrick","raw_affiliation_strings":["Computer Engineering Department, Govt. Women Engineering College Ajmer, Rajasthan, India"],"raw_orcid":"https://orcid.org/0009-0001-0247-3915","affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Govt. Women Engineering College Ajmer, Rajasthan, India","institution_ids":["https://openalex.org/I56287899"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052504383"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3061,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.57144945,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9976000189781189,"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":0.9965000152587891,"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":0.9915571212768555},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.852231502532959},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6815427541732788},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6436040997505188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5984666347503662},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5360657572746277},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.514710009098053},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.5112378597259521},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4390050172805786},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32981613278388977},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32848337292671204}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9915571212768555},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.852231502532959},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6815427541732788},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6436040997505188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5984666347503662},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5360657572746277},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.514710009098053},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.5112378597259521},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4390050172805786},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32981613278388977},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32848337292671204},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3590837.3590929","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3590837.3590929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Information Management & Machine Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2064675550","https://openalex.org/W2463955103","https://openalex.org/W2506483933","https://openalex.org/W2741609678","https://openalex.org/W2930957955","https://openalex.org/W2969804587","https://openalex.org/W4245551996","https://openalex.org/W4297683907","https://openalex.org/W4313444565"],"related_works":["https://openalex.org/W2795359650","https://openalex.org/W3008515501","https://openalex.org/W2923366293","https://openalex.org/W4293069178","https://openalex.org/W2547835662","https://openalex.org/W4287776258","https://openalex.org/W3027997911","https://openalex.org/W3010872046","https://openalex.org/W4220800343","https://openalex.org/W3162527929"],"abstract_inverted_index":{"Unmanned":[0],"generation":[1],"of":[2,5,19,51,81,102],"the":[3,20,42,48,86,100],"caption":[4],"any":[6],"given":[7],"image":[8,13,112],"can":[9],"be":[10],"defined":[11],"as":[12,26,127],"captioning.":[14,136],"It":[15],"is":[16,28],"still":[17],"one":[18],"most":[21],"important":[22],"and":[23,75,120],"researched":[24],"topics":[25],"it":[27,93],"used":[29,126,134],"in":[30,135],"many":[31,44],"tools":[32],"like":[33],"virtual":[34],"assistants,":[35],"chatbots,":[36],"visual":[37],"question-and-answering":[38],"systems,":[39],"etc.":[40],"In":[41],"past,":[43],"researchers":[45],"have":[46,89],"improved":[47],"captioning":[49,113],"quality":[50],"an":[52,111],"image.":[53],"Recurrent":[54],"Neural":[55],"Network":[56],"using":[57,94,115],"long":[58],"short-term":[59],"memory":[60],"(LSTM)":[61],"units":[62],"has":[63],"contributed":[64],"a":[65,95,116,128,132],"lot":[66],"despite":[67],"their":[68],"disadvantages.":[69],"LSTM":[70],"cells":[71],"are":[72,125],"very":[73],"multiplex":[74],"intrinsically":[76],"progressive":[77],"at":[78],"different":[79],"intervals":[80],"time":[82],"therefore":[83],"to":[84,91],"mark":[85],"problem":[87],"we":[88,109],"tried":[90],"solve":[92],"convolutional":[96],"neural":[97],"network":[98],"considering":[99],"advantages":[101],"this":[103],"network.":[104],"Motivated":[105],"by":[106],"past":[107],"research":[108],"modeled":[110],"model":[114,133],"masked":[117],"convolutions":[118],"layer":[119],"attention":[121],"mechanism.":[122],"MSCOCO":[123],"datasets":[124],"dataset":[129],"for":[130],"developing":[131]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}