{"id":"https://openalex.org/W3209229003","doi":"https://doi.org/10.1109/tip.2021.3120867","title":"Hierarchical Representation Network With Auxiliary Tasks for Video Captioning and Video Question Answering","display_name":"Hierarchical Representation Network With Auxiliary Tasks for Video Captioning and Video Question Answering","publication_year":2021,"publication_date":"2021-10-28","ids":{"openalex":"https://openalex.org/W3209229003","doi":"https://doi.org/10.1109/tip.2021.3120867","mag":"3209229003","pmid":"https://pubmed.ncbi.nlm.nih.gov/34710043"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2021.3120867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3120867","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":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2522-6394","affiliations":[{"raw_affiliation_string":"Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445935","display_name":"Lei Yu","orcid":"https://orcid.org/0000-0002-9188-6112"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Lei","raw_affiliation_strings":["Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-9188-6112","affiliations":[{"raw_affiliation_string":"Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087623065","display_name":"Pengpeng Zeng","orcid":"https://orcid.org/0000-0002-0672-3790"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengpeng Zeng","raw_affiliation_strings":["Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-0672-3790","affiliations":[{"raw_affiliation_string":"Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2549-8322","affiliations":[{"raw_affiliation_string":"Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377147","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-3094-7735"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3094-7735","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.3126,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":{"value":0.97569277,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"202","last_page":"215"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9986000061035156,"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":0.9930999875068665,"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/computer-science","display_name":"Computer science","score":0.8594955205917358},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8051785230636597},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.6345167756080627},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5953475832939148},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5596284866333008},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5272050499916077},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5249747633934021},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49302050471305847},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47932517528533936},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4547807276248932},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.43992945551872253},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.42857831716537476},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42371487617492676},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4217953383922577},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.36556220054626465},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10212928056716919}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8594955205917358},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8051785230636597},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.6345167756080627},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5953475832939148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5596284866333008},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5272050499916077},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5249747633934021},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49302050471305847},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47932517528533936},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4547807276248932},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.43992945551872253},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.42857831716537476},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42371487617492676},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4217953383922577},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.36556220054626465},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10212928056716919},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2021.3120867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3120867","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:34710043","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34710043","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":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2546663186","display_name":null,"funder_award_id":"62020106008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5133417063","display_name":null,"funder_award_id":"2018AAA0102200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5932195961","display_name":null,"funder_award_id":"No.2019JDTD0005","funder_id":"https://openalex.org/F4320333335","funder_display_name":"Sichuan Province Science and Technology Support Program"},{"id":"https://openalex.org/G6151690139","display_name":null,"funder_award_id":"62020106007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7314976618","display_name":"\u878d\u5408\u81ea\u7136\u8bed\u8a00\u5904\u7406\u7684\u6df1\u5ea6\u89c6\u89c9\u7406\u89e3\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61872064","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8027008232","display_name":"\u534f\u540c\u6df1\u5ea6\u89c6\u9891\u7406\u89e3\u3001\u63cf\u8ff0\u548c\u89c6\u89c9\u95ee\u7b54\u7684\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61772116","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/F4320333335","display_name":"Sichuan Province Science and Technology Support Program","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W648786980","https://openalex.org/W1502131265","https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W1586939924","https://openalex.org/W1889081078","https://openalex.org/W1933349210","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2060300932","https://openalex.org/W2064675550","https://openalex.org/W2096621047","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2133564696","https://openalex.org/W2136036867","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2152984213","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2547875792","https://openalex.org/W2554906389","https://openalex.org/W2560023338","https://openalex.org/W2565656701","https://openalex.org/W2606982687","https://openalex.org/W2739107216","https://openalex.org/W2751525844","https://openalex.org/W2765716052","https://openalex.org/W2788738262","https://openalex.org/W2808181286","https://openalex.org/W2887712318","https://openalex.org/W2904291752","https://openalex.org/W2904452845","https://openalex.org/W2904551248","https://openalex.org/W2945223572","https://openalex.org/W2948358897","https://openalex.org/W2950096400","https://openalex.org/W2950872548","https://openalex.org/W2951390634","https://openalex.org/W2954199749","https://openalex.org/W2962681491","https://openalex.org/W2962949233","https://openalex.org/W2962958773","https://openalex.org/W2962990649","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963523627","https://openalex.org/W2963524571","https://openalex.org/W2963843052","https://openalex.org/W2963971014","https://openalex.org/W2963976294","https://openalex.org/W2964057271","https://openalex.org/W2964065937","https://openalex.org/W2964350391","https://openalex.org/W2969897437","https://openalex.org/W2974161034","https://openalex.org/W2981750519","https://openalex.org/W2982139784","https://openalex.org/W2983141445","https://openalex.org/W2984862483","https://openalex.org/W2988753485","https://openalex.org/W2989322838","https://openalex.org/W2996984511","https://openalex.org/W3009192917","https://openalex.org/W3019301826","https://openalex.org/W3034730770","https://openalex.org/W3035232877","https://openalex.org/W3035356601","https://openalex.org/W3035365026","https://openalex.org/W3035372819","https://openalex.org/W3176398504","https://openalex.org/W4221148458","https://openalex.org/W4246193833","https://openalex.org/W4288373939","https://openalex.org/W6621543089","https://openalex.org/W6630200889","https://openalex.org/W6631190155","https://openalex.org/W6639432524","https://openalex.org/W6679434410","https://openalex.org/W6680145277","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6719057275","https://openalex.org/W6729448088","https://openalex.org/W6729482032","https://openalex.org/W6729556111","https://openalex.org/W6760837195","https://openalex.org/W6767015469"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Recently,":[0],"integrating":[1],"vision":[2],"and":[3,12,51,56,88,116,149,159,176,188],"language":[4],"for":[5,21,84,165],"in-depth":[6],"video":[7,10,13,30,38,66,91,132,157,160],"understanding":[8],"e.g.,":[9],"captioning":[11,158],"question":[14,161],"answering,":[15],"has":[16],"become":[17],"a":[18,37,73],"promising":[19],"direction":[20],"artificial":[22],"intelligence.":[23],"However,":[24],"due":[25],"to":[26,35,121,130,137,155],"the":[27,94,99,108,117,131,138,166,174,184],"complexity":[28],"of":[29,46,101,104,111,144,178],"information,":[31],"it":[32],"is":[33],"challenging":[34],"extract":[36],"feature":[39],"that":[40],"can":[41,151],"well":[42],"represent":[43],"multiple":[44],"levels":[45],"concepts":[47],"i.e.,":[48],"objects,":[49],"actions":[50],"events.":[52],"Meanwhile,":[53],"content":[54],"completeness":[55],"syntactic":[57],"consistency":[58],"play":[59],"an":[60],"important":[61],"role":[62],"in":[63],"high-quality":[64],"language-related":[65],"understanding.":[67],"Motivated":[68],"by":[69,107],"these,":[70],"we":[71],"propose":[72],"novel":[74],"framework,":[75],"named":[76],"Hierarchical":[77],"Representation":[78],"Network":[79],"with":[80,183],"Auxiliary":[81],"Tasks":[82],"(HRNAT),":[83],"learning":[85,100],"multi-level":[86],"representations":[87],"obtaining":[89],"syntax-aware":[90],"captions.":[92],"Specifically,":[93],"Cross-modality":[95],"Matching":[96],"Task":[97,115,119],"enables":[98],"hierarchical":[102],"representation":[103,110],"videos,":[105],"guided":[106],"three-level":[109],"languages.":[112],"The":[113,141],"Syntax-guiding":[114],"Vision-assist":[118],"contribute":[120],"generating":[122],"descriptions":[123],"which":[124],"are":[125,147,190],"not":[126],"only":[127],"globally":[128],"similar":[129],"content,":[133],"but":[134],"also":[135,191],"syntax-consistent":[136],"ground-truth":[139],"description.":[140],"key":[142],"components":[143],"our":[145,179],"model":[146],"general":[148],"they":[150],"be":[152],"readily":[153],"applied":[154],"both":[156],"answering":[162],"tasks.":[163],"Performances":[164],"above":[167],"tasks":[168],"on":[169],"several":[170],"benchmark":[171],"datasets":[172],"validate":[173],"effectiveness":[175],"superiority":[177],"proposed":[180],"method":[181],"compared":[182],"state-of-the-art":[185],"methods.":[186],"Codes":[187],"models":[189],"released":[192],"https://github.com/riesling00/HRNAT.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":38},{"year":2022,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}