{"id":"https://openalex.org/W3022895911","doi":"https://doi.org/10.1145/3293353.3293391","title":"A Bottom-Up and Top-Down Approach for Image Captioning using Transformer","display_name":"A Bottom-Up and Top-Down Approach for Image Captioning using Transformer","publication_year":2018,"publication_date":"2018-12-18","ids":{"openalex":"https://openalex.org/W3022895911","doi":"https://doi.org/10.1145/3293353.3293391","mag":"3022895911"},"language":"en","primary_location":{"id":"doi:10.1145/3293353.3293391","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3293353.3293391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Indian Conference on Computer Vision, Graphics and Image Processing","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/A5021714082","display_name":"S. Parameswaran","orcid":"https://orcid.org/0000-0002-5146-5137"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sandeep Narayan Parameswaran","raw_affiliation_strings":["Indian Institute of Technology Madras, Chennai, Tamil Nadu, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, Chennai, Tamil Nadu, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000019969","display_name":"Sukhendu Das","orcid":"https://orcid.org/0000-0002-2823-9211"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sukhendu Das","raw_affiliation_strings":["Indian Institute of Technology Madras, Chennai, Tamil Nadu, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, Chennai, Tamil Nadu, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021714082"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.26080286,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"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":0.9994999766349792,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9973000288009644,"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":0.9126671552658081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8200353384017944},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6981409788131714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6065177917480469},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.54074627161026},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5062553286552429},{"id":"https://openalex.org/keywords/top-down-and-bottom-up-design","display_name":"Top-down and bottom-up design","score":0.5022952556610107},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4928550720214844},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4680599570274353},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.39749112725257874},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37545329332351685},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32829684019088745}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9126671552658081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8200353384017944},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6981409788131714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6065177917480469},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.54074627161026},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5062553286552429},{"id":"https://openalex.org/C135798126","wikidata":"https://www.wikidata.org/wiki/Q2167279","display_name":"Top-down and bottom-up design","level":2,"score":0.5022952556610107},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4928550720214844},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4680599570274353},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39749112725257874},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37545329332351685},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32829684019088745},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3293353.3293391","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3293353.3293391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Indian Conference on Computer Vision, Graphics and Image Processing","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":14,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2506483933","https://openalex.org/W2540404261","https://openalex.org/W2544271936","https://openalex.org/W2560920409","https://openalex.org/W2745461083","https://openalex.org/W2800782462"],"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/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2064871819","https://openalex.org/W2054945203"],"abstract_inverted_index":{"Describing":[0],"the":[1,13,57,86,95,125,130,144,152,178,187,191,198],"contents":[2],"of":[3,15,32,52,62,80,132,146,169,186,200],"an":[4,33,53,156],"image":[5,34,54,87,157,179],"automatically":[6,180],"has":[7],"been":[8],"a":[9,29,39,60,77,116,119,133,135,159],"fundamental":[10],"problem":[11],"in":[12,155,177],"field":[14],"artificial":[16],"intelligence":[17],"and":[18,35,99,118,158],"computer":[19],"vision.":[20],"Existing":[21],"approaches":[22],"are":[23,103],"either":[24],"top-down,":[25],"which":[26,44,123],"start":[27],"from":[28],"simple":[30],"representation":[31],"convert":[36],"it":[37],"into":[38],"textual":[40],"description;":[41],"or":[42,59],"bottom-up,":[43],"come":[45],"up":[46],"with":[47],"attributes":[48],"describing":[49],"numerous":[50],"aspects":[51],"to":[55,93,172,196],"form":[56],"caption":[58],"combination":[61],"both.":[63],"Recurrent":[64],"neural":[65],"networks":[66,73],"(RNN)":[67],"enhanced":[68],"by":[69,128],"Long":[70],"Short-Term":[71],"Memory":[72],"(LSTM)":[74],"have":[75],"become":[76],"dominant":[78],"component":[79],"several":[81],"frameworks":[82],"designed":[83],"for":[84,138,151],"solving":[85],"captioning":[88],"task.":[89],"Despite":[90],"their":[91],"ability":[92,168],"reduce":[94],"vanishing":[96],"gradient":[97],"problem,":[98],"capture":[100],"dependencies,":[101],"they":[102],"inherently":[104],"sequential":[105],"across":[106],"time.":[107],"In":[108],"this":[109],"work,":[110],"we":[111],"propose":[112],"two":[113],"novel":[114],"approaches,":[115],"top-down":[117],"bottom-up":[120],"approach":[121],"independently,":[122],"dispenses":[124],"recurrence":[126],"entirely":[127,142],"incorporating":[129],"use":[131],"Transformer,":[134],"network":[136],"architecture":[137,189],"generating":[139],"sequences":[140],"relying":[141],"on":[143,174,190],"mechanism":[145],"attention.":[147],"Adaptive":[148],"positional":[149],"encodings":[150],"spatial":[153],"locations":[154],"new":[160],"regularization":[161],"cost":[162],"during":[163],"training":[164],"is":[165,181,194],"introduced.":[166],"The":[167],"our":[170,201],"model":[171],"focus":[173],"salient":[175],"regions":[176],"demonstrated":[182],"visually.":[183],"Experimental":[184],"evaluation":[185],"proposed":[188],"MS-COCO":[192],"dataset":[193],"performed":[195],"exhibit":[197],"superiority":[199],"method.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}