{"id":"https://openalex.org/W7084766561","doi":"https://doi.org/10.1109/lsp.2025.3618767","title":"Seeing the Rare: Meta-Aware Pointer Networks for Long-Tailed Video Captioning","display_name":"Seeing the Rare: Meta-Aware Pointer Networks for Long-Tailed Video Captioning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7084766561","doi":"https://doi.org/10.1109/lsp.2025.3618767"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3618767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3618767","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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":"Deepali Verma","orcid":"https://orcid.org/0000-0002-7916-8441"},"institutions":[{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]},{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Deepali Verma","raw_affiliation_strings":["Indian Institute of Technology (BHU), Varanasi, Uttar Pradesh, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology (BHU), Varanasi, Uttar Pradesh, India","institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}]},{"author_position":"last","author":{"id":null,"display_name":"Tanima Dutta","orcid":"https://orcid.org/0000-0002-2801-0687"},"institutions":[{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289"]},{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tanima Dutta","raw_affiliation_strings":["Indian Institute of Technology (BHU), Varanasi, Uttar Pradesh, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology (BHU), Varanasi, Uttar Pradesh, India","institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.55892363,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"4269","last_page":"4273"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11244","display_name":"Climate Change and Health Impacts","score":0.9526000022888184,"subfield":{"id":"https://openalex.org/subfields/2307","display_name":"Health, Toxicology and Mutagenesis"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11244","display_name":"Climate Change and Health Impacts","score":0.9526000022888184,"subfield":{"id":"https://openalex.org/subfields/2307","display_name":"Health, Toxicology and Mutagenesis"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12492","display_name":"Zoonotic diseases and public health","score":0.013000000268220901,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12816","display_name":"Global Public Health Policies and Epidemiology","score":0.002199999988079071,"subfield":{"id":"https://openalex.org/subfields/1407","display_name":"Organizational Behavior and Human Resource Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9779999852180481},{"id":"https://openalex.org/keywords/copying","display_name":"Copying","score":0.5978999733924866},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5486000180244446},{"id":"https://openalex.org/keywords/pointer","display_name":"Pointer (user interface)","score":0.5047000050544739},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.45910000801086426},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.44929999113082886}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9779999852180481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8598999977111816},{"id":"https://openalex.org/C2779151265","wikidata":"https://www.wikidata.org/wiki/Q1156791","display_name":"Copying","level":2,"score":0.5978999733924866},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5486000180244446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5353000164031982},{"id":"https://openalex.org/C150202949","wikidata":"https://www.wikidata.org/wiki/Q107602","display_name":"Pointer (user interface)","level":2,"score":0.5047000050544739},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4203999936580658},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3718000054359436},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3312000036239624},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28189998865127563},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3618767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3618767","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2425121537","https://openalex.org/W2948358897","https://openalex.org/W2951390634","https://openalex.org/W2962681491","https://openalex.org/W2981368934","https://openalex.org/W2984862483","https://openalex.org/W2988753485","https://openalex.org/W3009192917","https://openalex.org/W3009448441","https://openalex.org/W3015790009","https://openalex.org/W3034221024","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3035730922","https://openalex.org/W3096935578","https://openalex.org/W3134875898","https://openalex.org/W3153232703","https://openalex.org/W3163971663","https://openalex.org/W3176689360","https://openalex.org/W3193767255","https://openalex.org/W4285118488","https://openalex.org/W4292974679","https://openalex.org/W4293061975","https://openalex.org/W4364373974","https://openalex.org/W4382469109","https://openalex.org/W4385768107","https://openalex.org/W4386057717","https://openalex.org/W4389829555","https://openalex.org/W4408398719","https://openalex.org/W4409671312"],"related_works":[],"abstract_inverted_index":{"Fine-grained":[0],"video":[1,46],"captioning":[2,47],"systems":[3],"often":[4],"struggle":[5],"with":[6,55,76,110,126],"long-tailed":[7],"vocabulary":[8],"distributions,":[9],"where":[10],"rare":[11,66,114,122],"events":[12],"and":[13,29,70,99,117],"objects":[14],"are":[15,24],"significantly":[16],"underrepresented.":[17],"This":[18],"imbalance":[19],"leads":[20],"to":[21,85],"captions":[22],"that":[23,49,103],"overly":[25],"generic,":[26],"lacking":[27],"specificity":[28],"relevance":[30],"for":[31],"less":[32],"frequent":[33],"but":[34],"semantically":[35],"important":[36],"content.":[37],"To":[38],"address":[39],"this":[40],"challenge,":[41],"we":[42],"propose":[43],"a":[44,51,56,118],"novel":[45],"framework":[48],"integrates":[50],"hybrid":[52],"pointer-generator":[53,60],"decoder":[54],"meta-learning":[57,81],"strategy.":[58],"The":[59],"mechanism":[61],"enables":[62],"dynamic":[63],"copying":[64],"of":[65],"terms":[67],"from":[68],"visual":[69],"semantic":[71],"graphs,":[72],"ensuring":[73],"better":[74],"alignment":[75],"underrepresented":[77],"concepts.":[78],"Complementarily,":[79],"the":[80,97],"component":[82],"encourages":[83],"generalization":[84],"infrequent":[86],"instances":[87],"by":[88],"simulating":[89],"few-shot":[90],"learning":[91],"scenarios":[92],"during":[93],"training.":[94],"Experiments":[95],"on":[96],"MSVD":[98],"MSR-VTT":[100],"datasets":[101],"show":[102],"our":[104],"method":[105],"consistently":[106],"outperforms":[107],"strong":[108],"baselines,":[109],"significant":[111],"gains":[112],"in":[113,121,129],"concept":[115],"recall":[116],"12%":[119],"improvement":[120],"term":[123],"coverage,":[124],"along":[125],"notable":[127],"improvements":[128],"CIDEr":[130],"scores.":[131]},"counts_by_year":[],"updated_date":"2025-11-18T23:42:31.664661","created_date":"2025-10-10T00:00:00"}