{"id":"https://openalex.org/W4372267409","doi":"https://doi.org/10.1109/icassp49357.2023.10096625","title":"Motion-Aware Video Paragraph Captioning via Exploring Object-Centered Internal Knowledge","display_name":"Motion-Aware Video Paragraph Captioning via Exploring Object-Centered Internal Knowledge","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267409","doi":"https://doi.org/10.1109/icassp49357.2023.10096625"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/Motion-Aware_Video_Paragraph_Captioning_via_Exploring_Object-Centered_Internal_Knowledge/24978249","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"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/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":false,"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/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/A5017732945","display_name":"Rui Feng","orcid":"https://orcid.org/0000-0001-5918-8712"},"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":"middle","author":{"id":"https://openalex.org/A5019288783","display_name":"Xuequan Lu","orcid":"https://orcid.org/0000-0003-0959-408X"},"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":"Xuequan Lu","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"]}]},{"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/A5086217776"],"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":0.03644623,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9987000226974487,"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":0.9847000241279602,"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":0.9164706468582153},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.8757337331771851},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8593499660491943},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6563193202018738},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5986550450325012},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5849499702453613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5546471476554871},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5385329723358154},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5338605046272278},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5335133075714111},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44456028938293457},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42724665999412537},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4168052077293396},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.41060003638267517},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3471492528915405},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33038830757141113},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12873238325119019},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09471359848976135}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9164706468582153},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.8757337331771851},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8593499660491943},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6563193202018738},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5986550450325012},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5849499702453613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5546471476554871},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5385329723358154},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5338605046272278},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5335133075714111},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44456028938293457},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42724665999412537},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4168052077293396},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.41060003638267517},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3471492528915405},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33038830757141113},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12873238325119019},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09471359848976135},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/24978249","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Motion-Aware_Video_Paragraph_Captioning_via_Exploring_Object-Centered_Internal_Knowledge/24978249","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/24978249","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Motion-Aware_Video_Paragraph_Captioning_via_Exploring_Object-Centered_Internal_Knowledge/24978249","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6100000143051147}],"awards":[],"funders":[{"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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2133459682","https://openalex.org/W2250378130","https://openalex.org/W2739107216","https://openalex.org/W2883910824","https://openalex.org/W2944165510","https://openalex.org/W2963351113","https://openalex.org/W2963576560","https://openalex.org/W2963811641","https://openalex.org/W2963916161","https://openalex.org/W2964110616","https://openalex.org/W2968101724","https://openalex.org/W2968297680","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/W6762082143","https://openalex.org/W6767057552","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","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"],"abstract_inverted_index":{"Video":[0],"paragraph":[1,12],"captioning":[2],"task":[3],"aims":[4],"at":[5],"generating":[6],"a":[7,14,81,120],"fine-grained,":[8],"coherent":[9],"and":[10,115,124],"relevant":[11],"for":[13],"video.":[15],"Different":[16],"from":[17],"the":[18,24,41,52,57,60,63,90,99,102,106,108,111,126,131,140],"images":[19],"where":[20],"objects":[21,28,58],"are":[22,29,68],"static,":[23],"temporal":[25,91],"states":[26],"of":[27,56,94,101,110,142],"changing":[30,54],"in":[31,59,66,73,105],"videos.":[32],"The":[33],"dynamic":[34,53],"information":[35,109,128],"could":[36],"be":[37],"contributed":[38],"to":[39,98,129],"understanding":[40],"whole":[42],"video":[43,112],"content.":[44],"Existing":[45],"works":[46],"rarely":[47],"put":[48],"focus":[49],"on":[50,136],"modeling":[51],"state":[55,92],"videos,":[61,107],"causing":[62],"activities":[64],"occurred":[65],"videos":[67],"poorly":[69],"or":[70],"wrongly":[71],"depicted":[72],"paragraphs.":[74],"To":[75],"address":[76],"this":[77],"problem,":[78],"we":[79],"propose":[80,119],"novel":[82],"Object":[83],"State":[84],"Tracking":[85],"Network,":[86],"which":[87],"can":[88],"capture":[89],"change":[93],"objects.":[95],"However,":[96],"due":[97],"similarity":[100],"consecutive":[103],"frames":[104],"is":[113],"redundant":[114],"noisy.":[116],"We":[117],"further":[118],"semantic":[121],"alignment":[122],"mechanism,":[123],"enable":[125],"sentence":[127],"refine":[130],"visual":[132],"information.":[133],"Extensive":[134],"experiments":[135],"ActivityNet":[137],"Captions":[138],"demonstrate":[139],"effectiveness":[141],"our":[143],"method.":[144]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
