{"id":"https://openalex.org/W4392904510","doi":"https://doi.org/10.1109/icassp48485.2024.10448104","title":"Exploring Object-Centered External Knowledge for Fine-Grained Video Paragraph Captioning","display_name":"Exploring Object-Centered External Knowledge for Fine-Grained Video Paragraph Captioning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904510","doi":"https://doi.org/10.1109/icassp48485.2024.10448104"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448104","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Exploring_Object-Centered_External_Knowledge_for_Fine-Grained_Video_Paragraph_Captioning/26361949","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025995421","display_name":"Guorui Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guorui Yu","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing","School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086217776","display_name":"Yimin Hu","orcid":"https://orcid.org/0000-0002-1638-5393"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yimin Hu","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing","School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100802541","display_name":"Yiqian Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqian Xu","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing","School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070073283","display_name":"Yuejie Zhang","orcid":"https://orcid.org/0000-0001-7993-7223"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuejie Zhang","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing","School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101860531","display_name":"Rui Feng","orcid":"https://orcid.org/0000-0001-6648-953X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Feng","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing","School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Lab of Intelligent Information Processing","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375722","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0001-7561-0143"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["Shanghai University of Finance and Economics,School of Information Management and Engineering","School of Information Management and Engineering, Shanghai University of Finance and Economics"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics,School of Information Management and Engineering","institution_ids":["https://openalex.org/I181679659"]},{"raw_affiliation_string":"School of Information Management and Engineering, Shanghai University of Finance and Economics","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048961502","display_name":"Shang Gao","orcid":"https://orcid.org/0000-0002-2176-6553"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shang Gao","raw_affiliation_strings":["Deakin University,School of Information Technology","School of Information Technology, Deakin University"],"affiliations":[{"raw_affiliation_string":"Deakin University,School of Information Technology","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"School of Information Technology, Deakin University","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5025995421"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02573745,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11786","last_page":"11790"},"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":0.9973999857902527,"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":0.9904000163078308,"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/paragraph","display_name":"Paragraph","score":0.9086254835128784},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8767122030258179},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.838024377822876},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6844907999038696},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5621424317359924},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5291056036949158},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.522894561290741},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.47879061102867126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4666367173194885},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.44766613841056824},{"id":"https://openalex.org/keywords/semantic-role-labeling","display_name":"Semantic role labeling","score":0.4210851788520813},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4208471477031708},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.41397935152053833},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38948488235473633},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20223277807235718},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08942994475364685}],"concepts":[{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.9086254835128784},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8767122030258179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.838024377822876},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6844907999038696},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5621424317359924},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5291056036949158},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.522894561290741},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.47879061102867126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4666367173194885},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.44766613841056824},{"id":"https://openalex.org/C67277372","wikidata":"https://www.wikidata.org/wiki/Q7449085","display_name":"Semantic role labeling","level":3,"score":0.4210851788520813},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4208471477031708},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.41397935152053833},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38948488235473633},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20223277807235718},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08942994475364685},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448104","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/26361949","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Exploring_Object-Centered_External_Knowledge_for_Fine-Grained_Video_Paragraph_Captioning/26361949","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/26361949","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Exploring_Object-Centered_External_Knowledge_for_Fine-Grained_Video_Paragraph_Captioning/26361949","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315315","display_name":"Vermont Agency of Transportation","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320329878","display_name":"Central University Basic Research Fund of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1956340063","https://openalex.org/W2016089260","https://openalex.org/W2133459682","https://openalex.org/W2883910824","https://openalex.org/W2896457183","https://openalex.org/W2952132648","https://openalex.org/W2963351113","https://openalex.org/W2963811641","https://openalex.org/W2963916161","https://openalex.org/W2964110616","https://openalex.org/W2968101724","https://openalex.org/W3035237998","https://openalex.org/W3035763695","https://openalex.org/W3092659741","https://openalex.org/W3166366124","https://openalex.org/W3173891689","https://openalex.org/W4214663214","https://openalex.org/W6620707391","https://openalex.org/W6755207826","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2391800119","https://openalex.org/W2595239241","https://openalex.org/W2799181378","https://openalex.org/W2052919063","https://openalex.org/W3003711649","https://openalex.org/W2904173691","https://openalex.org/W4365517254","https://openalex.org/W270947280","https://openalex.org/W2354078889","https://openalex.org/W2391250648"],"abstract_inverted_index":{"Video":[0],"paragraph":[1,12,62],"captioning":[2],"task":[3],"aims":[4],"to":[5,102,127],"generate":[6],"a":[7,14,29,66,71,75,91],"detailed,":[8],"fluent":[9],"and":[10,45,59,79,117],"relevant":[11,61],"for":[13],"given":[15],"video.":[16],"Prior":[17],"studies":[18],"often":[19],"focus":[20],"on":[21,114],"isolating":[22],"visual":[23,86,109],"objects":[24,44],"(potential":[25],"main":[26],"components":[27],"in":[28,50],"sentence)":[30],"from":[31,74,84],"the":[32,39,85,104,108,119],"overall":[33],"video":[34,47],"content.":[35],"They":[36],"rarely":[37],"explore":[38],"latent":[40],"semantic":[41,82],"relations":[42],"between":[43],"high-level":[46],"concepts,":[48],"resulting":[49],"dull":[51],"or":[52],"even":[53],"incorrect":[54],"descriptions.":[55],"To":[56],"create":[57],"fine-grained":[58],"contextually":[60],"captions,":[63],"we":[64,89],"propose":[65],"novel":[67],"framework":[68],"that":[69,96],"constructs":[70],"concept":[72],"graph":[73],"commonsense":[76],"knowledge":[77,106],"base":[78],"infers":[80],"richer":[81],"meaning":[83],"objects.":[87],"Moreover,":[88],"employ":[90],"Vision-Guided":[92],"Concept":[93],"Selection":[94],"Network":[95],"incorporates":[97],"an":[98],"under-sentence":[99],"supervision":[100],"mechanism":[101],"align":[103],"external":[105],"with":[107],"information.":[110],"Through":[111],"extensive":[112],"experiments":[113],"ActivityNet":[115],"captions":[116],"YouCook2,":[118],"effectiveness":[120],"of":[121],"our":[122],"method":[123],"is":[124],"demonstrated":[125],"compared":[126],"state-of-the-art":[128],"methods.":[129]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
