{"id":"https://openalex.org/W3096258227","doi":"https://doi.org/10.48550/arxiv.2011.01753","title":"Attention Beam: An Image Captioning Approach","display_name":"Attention Beam: An Image Captioning Approach","publication_year":2020,"publication_date":"2020-11-03","ids":{"openalex":"https://openalex.org/W3096258227","doi":"https://doi.org/10.48550/arxiv.2011.01753","mag":"3096258227"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2011.01753","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.01753","pdf_url":"https://arxiv.org/pdf/2011.01753","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.01753","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072543351","display_name":"Anubhav Shrimal","orcid":"https://orcid.org/0000-0002-6269-5771","observed_orcids":["https://orcid.org/0000-0002-6269-5771"]},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shrimal, Anubhav","raw_affiliation_strings":["Department of Computer Science & Engineering IIIT- Delhi , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering IIIT- Delhi , India","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046521217","display_name":"Tanmoy Chakraborty","orcid":"https://orcid.org/0000-0002-0210-0369","observed_orcids":["https://orcid.org/0000-0002-0210-0369"]},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chakraborty, Tanmoy","raw_affiliation_strings":["Department of Computer Science & Engineering IIIT- Delhi , India","Indraprastha Institute of Information Technology-Delhi;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering IIIT- Delhi , India","institution_ids":["https://openalex.org/I119939252"]},{"raw_affiliation_string":"Indraprastha Institute of Information Technology-Delhi;","institution_ids":["https://openalex.org/I119939252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I119939252"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T10824","display_name":"Image Retrieval and Classification Techniques","score":9.999999747378752e-05,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":9.999999747378752e-05,"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/image-captioning","display_name":"image captioning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/beam-search","display_name":"beam search","score":0.8930000066757202},{"id":"https://openalex.org/keywords/encoder-decoder-architecture","display_name":"encoder-decoder architecture","score":0.8500000238418579},{"id":"https://openalex.org/keywords/caption-quality","display_name":"caption quality","score":0.6110000014305115},{"id":"https://openalex.org/keywords/flickr8k","display_name":"Flickr8k","score":0.9279999732971191},{"id":"https://openalex.org/keywords/flickr30k","display_name":"Flickr30k","score":0.9990000128746033},{"id":"https://openalex.org/keywords/ms-coco","display_name":"MS COCO","score":0.8920000195503235}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9740505218505859},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973332405090332},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.7010009288787842},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6781796216964722},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6027694344520569},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5815584063529968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5621306896209717},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4914742708206177},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.45974570512771606},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4584798812866211},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39803415536880493},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3655044436454773},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3649948239326477},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06546762585639954},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2011.01753","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.01753","pdf_url":"https://arxiv.org/pdf/2011.01753","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3096258227","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2011.01753","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.01753","doi":"https://doi.org/10.48550/arxiv.2011.01753","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.01753","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.01753","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.01753","pdf_url":"https://arxiv.org/pdf/2011.01753","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3096258227.pdf","grobid_xml":"https://content.openalex.org/works/W3096258227.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2951912364"],"related_works":["https://openalex.org/W3176769434","https://openalex.org/W3200965450","https://openalex.org/W4205983318","https://openalex.org/W2894206117","https://openalex.org/W4387780895","https://openalex.org/W4324137436","https://openalex.org/W4226160867","https://openalex.org/W4400810498","https://openalex.org/W7168146278","https://openalex.org/W3099592174"],"abstract_inverted_index":{"The":[0],"aim":[1],"of":[2,10,67,72],"image":[3,34,45,60],"captioning":[4],"is":[5,22],"to":[6,31],"generate":[7,39],"textual":[8],"description":[9,42],"a":[11,40,65],"given":[12],"image.":[13],"Though":[14],"seemingly":[15],"an":[16],"easy":[17],"task":[18],"for":[19,24,43,59],"humans,":[20],"it":[21,27],"challenging":[23],"machines":[25],"as":[26],"requires":[28],"the":[29,33,44,73],"ability":[30],"comprehend":[32],"(computer":[35],"vision)":[36],"and":[37,88],"consequently":[38],"human-like":[41],"(natural":[46],"language":[47],"understanding).":[48],"In":[49],"recent":[50],"times,":[51],"encoder-decoder":[52,74],"based":[53,75],"architectures":[54],"have":[55],"achieved":[56],"state-of-the-art":[57],"results":[58],"captioning.":[61],"Here,":[62],"we":[63],"present":[64],"heuristic":[66],"beam":[68],"search":[69],"on":[70,82],"top":[71],"architecture":[76],"that":[77],"gives":[78],"better":[79],"quality":[80],"captions":[81],"three":[83],"benchmark":[84],"datasets:":[85],"Flickr8k,":[86],"Flickr30k":[87],"MS":[89],"COCO.":[90]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2020-11-09T00:00:00"}