{"id":"https://openalex.org/W4416251579","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227221","title":"What Happens in the Surroundings: A Benchmark for 360\u00b0 image Captioning","display_name":"What Happens in the Surroundings: A Benchmark for 360\u00b0 image Captioning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251579","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227221"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227221","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5030344445","display_name":"Wenhui Jiang","orcid":"https://orcid.org/0000-0002-4144-6725"},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenhui Jiang","raw_affiliation_strings":["Jiangxi University of Finance and Economics,Nanchang,China"],"affiliations":[{"raw_affiliation_string":"Jiangxi University of Finance and Economics,Nanchang,China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101987278","display_name":"Tianhua Xu","orcid":"https://orcid.org/0000-0003-3720-4130"},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiancong Xu","raw_affiliation_strings":["Jiangxi University of Finance and Economics,Nanchang,China"],"affiliations":[{"raw_affiliation_string":"Jiangxi University of Finance and Economics,Nanchang,China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100317779","display_name":"Haijun Li","orcid":"https://orcid.org/0000-0001-6631-123X"},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijun Li","raw_affiliation_strings":["Jiangxi University of Finance and Economics,Nanchang,China"],"affiliations":[{"raw_affiliation_string":"Jiangxi University of Finance and Economics,Nanchang,China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090639079","display_name":"Zichen Li","orcid":null},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zichen Li","raw_affiliation_strings":["Jiangxi University of Finance and Economics,Nanchang,China"],"affiliations":[{"raw_affiliation_string":"Jiangxi University of Finance and Economics,Nanchang,China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063013411","display_name":"Yuming Fang","orcid":"https://orcid.org/0000-0002-6946-3586"},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuming Fang","raw_affiliation_strings":["Jiangxi University of Finance and Economics,Nanchang,China"],"affiliations":[{"raw_affiliation_string":"Jiangxi University of Finance and Economics,Nanchang,China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101458063","display_name":"Zhen Tang","orcid":"https://orcid.org/0000-0002-9559-5216"},"institutions":[{"id":"https://openalex.org/I4210124264","display_name":"Sany (China)","ror":"https://ror.org/023jrwe36","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210124264"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Tang","raw_affiliation_strings":["Sany Heavy Industry CO., LTD,Sany,China"],"affiliations":[{"raw_affiliation_string":"Sany Heavy Industry CO., LTD,Sany,China","institution_ids":["https://openalex.org/I4210124264"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5030344445"],"corresponding_institution_ids":["https://openalex.org/I59649739"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34515189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9661999940872192,"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":0.9661999940872192,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.00559999980032444,"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":0.0052999998442828655,"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":0.973800003528595},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5992000102996826},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4092000126838684},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.40230000019073486},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.39649999141693115},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.37529999017715454},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3564999997615814}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.973800003528595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878000140190125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6765000224113464},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5992000102996826},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5489000082015991},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.39649999141693115},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3564999997615814},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.2782999873161316},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.2732999920845032},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227221","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322665","display_name":"Natural Science Foundation of Jiangxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1689711448","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2185175083","https://openalex.org/W2613825824","https://openalex.org/W2745461083","https://openalex.org/W2895696451","https://openalex.org/W2952122856","https://openalex.org/W2990069284","https://openalex.org/W2990818246","https://openalex.org/W3009654469","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3035547893","https://openalex.org/W3045491541","https://openalex.org/W3087221416","https://openalex.org/W3118542935","https://openalex.org/W3122686848","https://openalex.org/W3125786462","https://openalex.org/W3138516171","https://openalex.org/W3194110717","https://openalex.org/W3204380095","https://openalex.org/W3205021045","https://openalex.org/W3216130706","https://openalex.org/W4280496911","https://openalex.org/W4283822166","https://openalex.org/W4285265382","https://openalex.org/W4296613086","https://openalex.org/W4296871376","https://openalex.org/W4312289196","https://openalex.org/W4312724358","https://openalex.org/W4385245566","https://openalex.org/W4386066204","https://openalex.org/W4386162736","https://openalex.org/W4386436010","https://openalex.org/W4403851317","https://openalex.org/W4407782160"],"related_works":[],"abstract_inverted_index":{"Image":[0,81],"captioning":[1,18,53,124],"has":[2,44],"been":[3,45],"widely":[4],"studied":[5,56],"by":[6],"the":[7,59,66,107,134,156,174,185],"computer":[8],"vision":[9],"and":[10,91,129,141,172],"natural":[11],"language":[12],"processing":[13],"communities.":[14],"However,":[15,50],"conventional":[16],"image":[17,52,76,93,111,123],"models":[19],"are":[20],"mainly":[21],"built":[22],"upon":[23],"2D":[24],"images":[25,43,87,160,171],"with":[26,97,133,161],"narrow":[27],"field-of-views.":[28],"To":[29,64],"comprehensively":[30],"analyze":[31],"what":[32],"happens":[33],"in":[34],"real":[35],"scenes,":[36,90],"using":[37],"360\u00b0":[38,42,51,75,86,110,122,146,170],"cameras":[39],"to":[40,58,154],"capture":[41],"a":[46,71,116,151],"popular":[47],"research":[48,67,108],"trend.":[49],"is":[54,94],"rarely":[55],"due":[57],"lack":[60],"of":[61,109,136,145,159,169],"related":[62],"datasets.":[63],"bridge":[65],"gap,":[68],"we":[69],"introduce":[70],"novel":[72],"dataset":[73,194],"for":[74,121],"captioning,":[77],"namely":[78],"360IC":[79,182],"(360\u00b0":[80],"Captioning).":[82],"It":[83],"contains":[84],"1250":[85],"from":[88],"rich":[89,166],"each":[92],"manually":[95],"labeled":[96],"at":[98],"least":[99],"three":[100],"detailed":[101],"descriptions,":[102],"which":[103,131],"will":[104,195],"greatly":[105],"promote":[106],"captioning.":[112],"We":[113],"also":[114],"propose":[115],"Multi-View":[117],"Transformer":[118],"Network":[119],"(MVTransNet)":[120],"based":[125],"on":[126,181],"multi-view":[127],"analysis":[128],"fusion,":[130],"deals":[132],"characteristics":[135],"large":[137],"resolution,":[138],"wide":[139],"field-of-view":[140],"complex":[142],"visual":[143,167],"content":[144],"images.":[147],"Specifically,":[148],"it":[149],"builds":[150],"hierarchical":[152],"architecture":[153],"model":[155],"spatial":[157],"dependency":[158],"larger":[162],"content,":[163],"thus":[164],"forming":[165],"features":[168],"making":[173],"generated":[175],"descriptions":[176],"more":[177],"accurate.":[178],"Extensive":[179],"experiments":[180],"show":[183],"that":[184],"proposed":[186],"network":[187],"outperforms":[188],"other":[189],"competing":[190],"methods":[191],"considerably.":[192],"Our":[193],"be":[196],"released":[197],"soon.":[198]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}