{"id":"https://openalex.org/W7134251858","doi":"https://doi.org/10.1007/s11760-026-05233-5","title":"Towards explainable AI: multi-modal transformer for video-based image description generation","display_name":"Towards explainable AI: multi-modal transformer for video-based image description generation","publication_year":2026,"publication_date":"2026-03-01","ids":{"openalex":"https://openalex.org/W7134251858","doi":"https://doi.org/10.1007/s11760-026-05233-5"},"language":"en","primary_location":{"id":"doi:10.1007/s11760-026-05233-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11760-026-05233-5","pdf_url":null,"source":{"id":"https://openalex.org/S156904493","display_name":"Signal Image and Video Processing","issn_l":"1863-1703","issn":["1863-1703","1863-1711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal, Image and Video Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.16788","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128587061","display_name":"Lakshita Agarwal","orcid":null},"institutions":[{"id":"https://openalex.org/I863896202","display_name":"Delhi Technological University","ror":"https://ror.org/01ztcvt22","country_code":"IN","type":"education","lineage":["https://openalex.org/I863896202"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Lakshita Agarwal","raw_affiliation_strings":["Department of Information Technology, Delhi Technological University, Delhi, 110042, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology, Delhi Technological University, Delhi, 110042, India","institution_ids":["https://openalex.org/I863896202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128615545","display_name":"Bindu Verma","orcid":null},"institutions":[{"id":"https://openalex.org/I863896202","display_name":"Delhi Technological University","ror":"https://ror.org/01ztcvt22","country_code":"IN","type":"education","lineage":["https://openalex.org/I863896202"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Bindu Verma","raw_affiliation_strings":["Assistant Professor, Department of Information Technology, Delhi Technological University, Delhi, 110042, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Assistant Professor, Department of Information Technology, Delhi Technological University, Delhi, 110042, India","institution_ids":["https://openalex.org/I863896202"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5128615545"],"corresponding_institution_ids":["https://openalex.org/I863896202"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26219846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":"3","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":0.9397000074386597,"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":0.9397000074386597,"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":0.03610000014305115,"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":0.003700000001117587,"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/transformer","display_name":"Transformer","score":0.6947000026702881},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5514000058174133},{"id":"https://openalex.org/keywords/image-manipulation","display_name":"Image manipulation","score":0.2752000093460083},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.26330000162124634}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6947000026702881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6539000272750854},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5755000114440918},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5514000058174133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5473999977111816},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26330000162124634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2379000037908554},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2117999941110611},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.2102999985218048}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11760-026-05233-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11760-026-05233-5","pdf_url":null,"source":{"id":"https://openalex.org/S156904493","display_name":"Signal Image and Video Processing","issn_l":"1863-1703","issn":["1863-1703","1863-1711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal, Image and Video Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2504.16788","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.16788","pdf_url":"https://arxiv.org/pdf/2504.16788","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,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.16788","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.16788","pdf_url":"https://arxiv.org/pdf/2504.16788","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,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7134251858.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W2425121537","https://openalex.org/W2885138528","https://openalex.org/W2951390634","https://openalex.org/W2963916161","https://openalex.org/W2981851019","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3035237998","https://openalex.org/W3035284526","https://openalex.org/W3091588028","https://openalex.org/W3161293445","https://openalex.org/W3168640669","https://openalex.org/W4206711354","https://openalex.org/W4386066385","https://openalex.org/W4386328612","https://openalex.org/W4389828756","https://openalex.org/W4394862623","https://openalex.org/W4402671548","https://openalex.org/W4402754238","https://openalex.org/W4402917033","https://openalex.org/W4409367459"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2026-03-10T00:00:00"}
