{"id":"https://openalex.org/W4401413938","doi":"https://doi.org/10.1109/icra57147.2024.10610654","title":"Automatic Captioning based on Visible and Infrared Images","display_name":"Automatic Captioning based on Visible and Infrared Images","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401413938","doi":"https://doi.org/10.1109/icra57147.2024.10610654"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100322712","display_name":"Yan Wang","orcid":"https://orcid.org/0000-0002-5344-1884"},"institutions":[{"id":"https://openalex.org/I18452120","display_name":"Yantai University","ror":"https://ror.org/01rp41m56","country_code":"CN","type":"education","lineage":["https://openalex.org/I18452120"]},{"id":"https://openalex.org/I4210087549","display_name":"La Jolla Science Applications (United States)","ror":"https://ror.org/0057tdk10","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087549"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yan Wang","raw_affiliation_strings":["La Jolla County day School","Yantai University,Department of Physics and Electronic Information"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"La Jolla County day School","institution_ids":["https://openalex.org/I4210087549"]},{"raw_affiliation_string":"Yantai University,Department of Physics and Electronic Information","institution_ids":["https://openalex.org/I18452120"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111843758","display_name":"Shuli Lou","orcid":null},"institutions":[{"id":"https://openalex.org/I18452120","display_name":"Yantai University","ror":"https://ror.org/01rp41m56","country_code":"CN","type":"education","lineage":["https://openalex.org/I18452120"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuli Lou","raw_affiliation_strings":["Yantai University,Department of Physics and Electronic Information"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yantai University,Department of Physics and Electronic Information","institution_ids":["https://openalex.org/I18452120"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437115","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0003-3044-9047"},"institutions":[{"id":"https://openalex.org/I18452120","display_name":"Yantai University","ror":"https://ror.org/01rp41m56","country_code":"CN","type":"education","lineage":["https://openalex.org/I18452120"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Wang","raw_affiliation_strings":["Yantai University,Department of Physics and Electronic Information"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yantai University,Department of Physics and Electronic Information","institution_ids":["https://openalex.org/I18452120"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102956206","display_name":"Yunzhe Wang","orcid":"https://orcid.org/0000-0002-1755-6430"},"institutions":[{"id":"https://openalex.org/I18452120","display_name":"Yantai University","ror":"https://ror.org/01rp41m56","country_code":"CN","type":"education","lineage":["https://openalex.org/I18452120"]},{"id":"https://openalex.org/I4210087549","display_name":"La Jolla Science Applications (United States)","ror":"https://ror.org/0057tdk10","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087549"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yunzhe Wang","raw_affiliation_strings":["La Jolla County day School","Yantai University,Department of Physics and Electronic Information"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"La Jolla County day School","institution_ids":["https://openalex.org/I4210087549"]},{"raw_affiliation_string":"Yantai University,Department of Physics and Electronic Information","institution_ids":["https://openalex.org/I18452120"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013721700","display_name":"Xiaohu Yuan","orcid":"https://orcid.org/0009-0008-4239-2889"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohu Yuan","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041101317","display_name":"Huaping Liu","orcid":"https://orcid.org/0000-0002-4042-6044"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaping Liu","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11312","last_page":"11318"},"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":0.9990000128746033,"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":0.9970999956130981,"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":0.8807644844055176},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6798891425132751},{"id":"https://openalex.org/keywords/infrared","display_name":"Infrared","score":0.6612842679023743},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4290081262588501},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4222791790962219},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2108510136604309},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.10469120740890503},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0567130446434021}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8807644844055176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6798891425132751},{"id":"https://openalex.org/C158355884","wikidata":"https://www.wikidata.org/wiki/Q11388","display_name":"Infrared","level":2,"score":0.6612842679023743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4290081262588501},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4222791790962219},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2108510136604309},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.10469120740890503},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0567130446434021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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":29,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2154652894","https://openalex.org/W2575842049","https://openalex.org/W2584992898","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2913269858","https://openalex.org/W2942105358","https://openalex.org/W2963084599","https://openalex.org/W2963448089","https://openalex.org/W2997281059","https://openalex.org/W3015625772","https://openalex.org/W3032081758","https://openalex.org/W3034984754","https://openalex.org/W3093596336","https://openalex.org/W3119358226","https://openalex.org/W3154766321","https://openalex.org/W3190386169","https://openalex.org/W3205633134","https://openalex.org/W4213189167","https://openalex.org/W4292968451","https://openalex.org/W4319300753","https://openalex.org/W4377289753","https://openalex.org/W4383097401","https://openalex.org/W4383108879","https://openalex.org/W6682631176"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0,54],"this":[1,22],"paper,":[2],"we":[3,24,48,56,74],"tackle":[4],"the":[5,11,80],"task":[6],"of":[7,13,37,66],"image":[8,28],"captioning":[9,30],"with":[10],"complementarity":[12],"visible":[14,38],"light":[15,39],"images":[16,40,43,68],"and":[17,41,58,82,91,99],"infrared":[18,42],"images.":[19],"To":[20],"address":[21],"problem,":[23],"propose":[25],"an":[26],"RGBIR":[27],"fusion":[29],"model,":[31],"which":[32],"can":[33],"take":[34],"full":[35],"advantage":[36],"under":[44],"different":[45],"conditions.":[46],"Meanwhile,":[47],"develop":[49],"a":[50,60],"wearable":[51],"environment-assisted":[52],"system.":[53,83],"addition,":[55],"collect":[57],"annotate":[59],"new":[61,89],"dataset":[62],"containing":[63],"3510":[64],"pairs":[65],"RGB-IR":[67],"to":[69,78],"support":[70],"model":[71,81],"training.":[72],"Finally,":[73],"conduct":[75],"extensive":[76],"experiments":[77],"evaluate":[79],"Experimental":[84],"results":[85],"show":[86],"that":[87],"our":[88],"method":[90],"system":[92],"significantly":[93],"outperform":[94],"baselines":[95],"on":[96],"multiple":[97],"metrics":[98],"have":[100],"potential":[101],"practical":[102],"value.":[103]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}