{"id":"https://openalex.org/W7123346586","doi":"https://doi.org/10.1109/taffc.2026.3652228","title":"HEART: Emotionally Grounded Video Captioning via Hierarchical Emotion-Aligned Representation","display_name":"HEART: Emotionally Grounded Video Captioning via Hierarchical Emotion-Aligned Representation","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7123346586","doi":"https://doi.org/10.1109/taffc.2026.3652228"},"language":null,"primary_location":{"id":"doi:10.1109/taffc.2026.3652228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2026.3652228","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"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 Affective Computing","raw_type":"journal-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":null,"display_name":"Tingting Han","orcid":"https://orcid.org/0000-0002-2131-9200"},"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":"Tingting Han","raw_affiliation_strings":["School of Computer, Hangzhou Dianzi University, HangZhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2131-9200","affiliations":[{"raw_affiliation_string":"School of Computer, Hangzhou Dianzi University, HangZhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032749504","display_name":"Yuxuan Gong","orcid":null},"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":"Yuxuan Gong","raw_affiliation_strings":["School of Computer, Hangzhou Dianzi University, HangZhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, Hangzhou Dianzi University, HangZhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122882012","display_name":"Sicheng Zhao","orcid":null},"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":"Sicheng Zhao","raw_affiliation_strings":["Department of Psychological and Cognitive Sciences, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5843-6411","affiliations":[{"raw_affiliation_string":"Department of Psychological and Cognitive Sciences, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122909197","display_name":"Min Tan","orcid":null},"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":"Min Tan","raw_affiliation_strings":["School of Computer, Hangzhou Dianzi University, HangZhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1842-4050","affiliations":[{"raw_affiliation_string":"School of Computer, Hangzhou Dianzi University, HangZhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122901409","display_name":"Zhou Yu","orcid":null},"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":"Zhou Yu","raw_affiliation_strings":["School of Computer, Hangzhou Dianzi University, HangZhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, Hangzhou Dianzi University, HangZhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122906767","display_name":"Hongxun Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxun Yao","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0444938,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"2","first_page":"1709","last_page":"1720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9678999781608582,"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":0.9678999781608582,"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":0.00800000037997961,"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/T11439","display_name":"Video Analysis and Summarization","score":0.005499999970197678,"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":0.7857999801635742},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6093000173568726},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.526199996471405},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4318999946117401},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4138000011444092},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4122999906539917},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3675000071525574}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7857999801635742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806000113487244},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6093000173568726},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5999000072479248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5924000144004822},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.526199996471405},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4318999946117401},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4138000011444092},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4122999906539917},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2615000009536743},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25619998574256897},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taffc.2026.3652228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2026.3652228","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"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 Affective Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1690291968","display_name":null,"funder_award_id":"62422204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4067506605","display_name":null,"funder_award_id":"62472133","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4144755178","display_name":null,"funder_award_id":"62571294","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6036694980","display_name":null,"funder_award_id":"L252009","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G796335958","display_name":null,"funder_award_id":"62441614","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/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2003238582","https://openalex.org/W2078833921","https://openalex.org/W2093862925","https://openalex.org/W2101105183","https://openalex.org/W2188687388","https://openalex.org/W2425121537","https://openalex.org/W2790763247","https://openalex.org/W2952131827","https://openalex.org/W2954231566","https://openalex.org/W2962934715","https://openalex.org/W2963321416","https://openalex.org/W3131477521","https://openalex.org/W3137274787","https://openalex.org/W3206577156","https://openalex.org/W3207379732","https://openalex.org/W3216659302","https://openalex.org/W4214884471","https://openalex.org/W4223592162","https://openalex.org/W4283396608","https://openalex.org/W4285200050","https://openalex.org/W4293205624","https://openalex.org/W4323663038","https://openalex.org/W4328007250","https://openalex.org/W4362714356","https://openalex.org/W4377235647","https://openalex.org/W4387969035","https://openalex.org/W4391454521","https://openalex.org/W4393147709","https://openalex.org/W4402170672","https://openalex.org/W4402917229","https://openalex.org/W4403792461","https://openalex.org/W4406982839","https://openalex.org/W4409346360","https://openalex.org/W4409346432","https://openalex.org/W4409346483","https://openalex.org/W4409346520","https://openalex.org/W4409363250","https://openalex.org/W4410774519","https://openalex.org/W4413371217"],"related_works":[],"abstract_inverted_index":{"Emotional":[0],"Video":[1],"Captioning":[2],"(EVC)":[3],"seeks":[4],"to":[5,30,105],"generate":[6,106],"video":[7],"descriptions":[8],"that":[9,47,65,108,144],"are":[10,109],"both":[11,110,151],"factually":[12],"accurate":[13],"and":[14,25,53,72,89,113,134,140,153],"emotionally":[15,33,111],"expressive.":[16],"However,":[17],"existing":[18],"approaches":[19],"often":[20],"lack":[21],"structured":[22],"semantic":[23,152],"grounding":[24],"fine-grained":[26,128],"temporal":[27,55,91],"modeling,":[28],"leading":[29],"incomplete":[31],"or":[32],"inconsistent":[34],"captions.":[35],"To":[36,116],"address":[37],"these":[38,101],"issues,":[39],"we":[40,120],"proposeHEART(HierarchicalEmotion-AlignedRepresentation":[41],"withTemporal":[42],"structure),":[43],"a":[44,60,76,123],"unified":[45],"framework":[46],"jointly":[48],"models":[49],"hierarchical":[50],"visual":[51,67],"semantics":[52],"multi-scale":[54,94],"context.":[56],"Specifically,":[57],"HEART":[58,104,145],"introduces":[59],"Hierarchical":[61],"Semantic":[62],"Extraction":[63],"Module":[64,86],"decomposes":[66],"content":[68],"into":[69],"entity-,":[70],"action-,":[71],"event-level":[73],"representations,":[74],"providing":[75],"rich":[77],"foundation":[78],"for":[79],"multi-level":[80],"emotional":[81,129,154],"alignment.":[82],"A":[83],"Temporal":[84],"Pyramid":[85],"captures":[87],"short-":[88],"long-range":[90],"dependencies":[92],"through":[93],"convolution,":[95],"enabling":[96],"temporally":[97,114],"coherent":[98],"captioning.":[99],"Together,":[100],"components":[102],"enable":[103],"captions":[107],"grounded":[112],"complete.":[115],"support":[117],"this":[118],"framework,":[119],"construct":[121],"EmoStruct,":[122],"new":[124],"benchmark":[125],"dataset":[126],"with":[127],"annotations":[130],"at":[131],"the":[132],"subject":[133],"predicate":[135],"levels.":[136],"Experiments":[137],"on":[138],"EmoStruct":[139],"public":[141],"datasets":[142],"demonstrate":[143],"significantly":[146],"outperforms":[147],"prior":[148],"methods":[149],"in":[150],"dimensions.":[155]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-01-14T00:00:00"}
