{"id":"https://openalex.org/W4220863475","doi":"https://doi.org/10.1109/tip.2022.3159472","title":"I<sup>2</sup>Transformer: Intra- and Inter-Relation Embedding Transformer for TV Show Captioning","display_name":"I<sup>2</sup>Transformer: Intra- and Inter-Relation Embedding Transformer for TV Show Captioning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4220863475","doi":"https://doi.org/10.1109/tip.2022.3159472","pmid":"https://pubmed.ncbi.nlm.nih.gov/35312620"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2022.3159472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3159472","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yunbin Tu","orcid":"https://orcid.org/0000-0002-9525-9060"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yunbin Tu","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liang Li","orcid":"https://orcid.org/0000-0001-8437-4824"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li Su","orcid":"https://orcid.org/0000-0003-4038-753X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Su","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shengxiang Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengxiang Gao","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenggang Yan","orcid":"https://orcid.org/0000-0003-1204-0512"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenggang Yan","raw_affiliation_strings":["School of Automation, Hangzhou Dianzi University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-Jun Zha","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhengtao Yu","orcid":"https://orcid.org/0000-0002-4012-461X"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengtao Yu","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"last","author":{"id":null,"display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I10660446"],"apc_list":null,"apc_paid":null,"fwci":2.1438,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.88528574,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"3565","last_page":"3577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8841999769210815,"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":0.8841999769210815,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.025599999353289604,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.020999999716877937,"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":0.9386000037193298},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7092000246047974},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6815000176429749},{"id":"https://openalex.org/keywords/subtitle","display_name":"Subtitle","score":0.6177999973297119},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5943999886512756},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.40689998865127563},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.34209999442100525}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9386000037193298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753000020980835},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7092000246047974},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6815000176429749},{"id":"https://openalex.org/C2780364048","wikidata":"https://www.wikidata.org/wiki/Q204028","display_name":"Subtitle","level":2,"score":0.6177999973297119},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5943999886512756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5047000050544739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4388999938964844},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42890000343322754},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.40689998865127563},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34209999442100525},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2578999996185303},{"id":"https://openalex.org/C2777152325","wikidata":"https://www.wikidata.org/wiki/Q108163","display_name":"Proposition","level":2,"score":0.25049999356269836}],"mesh":[{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D033182","descriptor_name":"Intention","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D033182","descriptor_name":"Intention","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D033182","descriptor_name":"Intention","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2022.3159472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3159472","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:35312620","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35312620","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G230809083","display_name":null,"funder_award_id":"61972186","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2446480051","display_name":null,"funder_award_id":"2020108","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G3929375146","display_name":null,"funder_award_id":"202002AD080001-5","funder_id":"https://openalex.org/F4320336602","funder_display_name":"Major Science and Technology Projects in Yunnan Province"},{"id":"https://openalex.org/G4479882814","display_name":null,"funder_award_id":"U21B2027","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4857188159","display_name":null,"funder_award_id":"202103AA080015","funder_id":"https://openalex.org/F4320336602","funder_display_name":"Major Science and Technology Projects in Yunnan Province"},{"id":"https://openalex.org/G8440137829","display_name":null,"funder_award_id":"61732005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320336602","display_name":"Major Science and Technology Projects in Yunnan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2110933980","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2584992898","https://openalex.org/W2737030113","https://openalex.org/W2765658575","https://openalex.org/W2807634467","https://openalex.org/W2887712318","https://openalex.org/W2890531016","https://openalex.org/W2945223572","https://openalex.org/W2953461088","https://openalex.org/W2962994439","https://openalex.org/W2963524571","https://openalex.org/W2970231061","https://openalex.org/W2979739834","https://openalex.org/W2984862483","https://openalex.org/W2985144848","https://openalex.org/W2989322838","https://openalex.org/W2997296614","https://openalex.org/W3009270862","https://openalex.org/W3019301826","https://openalex.org/W3021068338","https://openalex.org/W3034221024","https://openalex.org/W3034773362","https://openalex.org/W3034787499","https://openalex.org/W3034871396","https://openalex.org/W3035237998","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3093225449","https://openalex.org/W3093309253","https://openalex.org/W3096935578","https://openalex.org/W3104862079","https://openalex.org/W3105232955","https://openalex.org/W3109395208","https://openalex.org/W3110761028","https://openalex.org/W3120164061","https://openalex.org/W3125154076","https://openalex.org/W3136792391","https://openalex.org/W6623995992","https://openalex.org/W6631190155","https://openalex.org/W6639432524","https://openalex.org/W6678262379","https://openalex.org/W6679434410","https://openalex.org/W6682631176","https://openalex.org/W6726873649","https://openalex.org/W6739901393","https://openalex.org/W6746309015","https://openalex.org/W6766673545","https://openalex.org/W6766978945","https://openalex.org/W6780226713","https://openalex.org/W6898505805","https://openalex.org/W6955071965"],"related_works":[],"abstract_inverted_index":{"TV":[0,204],"show":[1,175,205],"captioning":[2,27,81],"aims":[3],"to":[4,18,159,166],"generate":[5],"a":[6,72,123,223],"linguistic":[7],"sentence":[8],"based":[9,153],"on":[10,154,171,193],"the":[11,22,26,40,52,66,77,90,120,126,129,136,142,161,164,167,172,177,180,186,189,217],"video":[12,85,199],"and":[13,37,57,70,89,101,113,146,191,207,219],"its":[14],"associated":[15],"subtitle.":[16],"Compared":[17],"purely":[19],"video-based":[20],"captioning,":[21],"subtitle":[23,44,87],"can":[24],"provide":[25],"model":[28,82],"with":[29,61,200],"useful":[30,148],"semantic":[31,59],"clues":[32],"such":[33],"as":[34,158,163],"actors'":[35],"sentiments":[36],"intentions.":[38],"However,":[39],"effective":[41],"use":[42],"of":[43,54,107,122,188,198],"is":[45,51,229],"also":[46,184],"very":[47],"challenging,":[48],"because":[49],"it":[50],"pieces":[53],"scrappy":[55,67],"information":[56,68,149],"has":[58],"gap":[60],"visual":[62],"modality.":[63],"To":[64],"organize":[65],"together":[69],"yield":[71],"powerful":[73],"omni-representation":[74,162],"for":[75],"all":[76],"modalities,":[78],"an":[79,99,108,114],"efficient":[80],"requires":[83],"understanding":[84],"contents,":[86],"semantics,":[88],"relations":[91],"in":[92,131],"between.":[93],"In":[94],"this":[95],"paper,":[96],"we":[97],"propose":[98],"Intra-":[100],"Inter-relation":[102,115],"Embedding":[103,110,116],"Transformer":[104],"(I<sup>2</sup>Transformer),":[105],"consisting":[106],"Intra-relation":[109],"Block":[111,117],"(IAE)":[112],"(IEE)":[118],"under":[119],"framework":[121],"Transformer.":[124,168],"First,":[125],"IAE":[127,190,218],"captures":[128],"intra-relation":[130],"each":[132,151],"modality":[133,152],"via":[134],"constructing":[135],"learnable":[137],"graphs.":[138],"Then,":[139],"IEE":[140,192,220],"learns":[141],"cross":[143],"attention":[144],"gates,":[145],"selects":[147],"from":[150],"their":[155],"inter-relations,":[156],"so":[157],"derive":[160],"input":[165],"Experimental":[169],"results":[170],"public":[173],"dataset":[174],"that":[176,216],"I<sup>2</sup>Transformer":[178],"achieves":[179],"state-of-the-art":[181],"performance.":[182],"We":[183],"evaluate":[185],"effectiveness":[187],"two":[194],"other":[195],"relevant":[196],"tasks":[197],"text":[201],"inputs,":[202],"i.e.,":[203],"retrieval":[206],"video-guided":[208],"machine":[209],"translation.":[210],"The":[211,227],"encouraging":[212],"performance":[213],"further":[214],"validates":[215],"blocks":[221],"have":[222],"good":[224],"generalization":[225],"ability.":[226],"code":[228],"available":[230],"at":[231],"https://github.com/tuyunbin/I2Transformer.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2022-04-03T00:00:00"}
