{"id":"https://openalex.org/W4372260149","doi":"https://doi.org/10.1109/icassp49357.2023.10097128","title":"CLIP4VideoCap: Rethinking Clip for Video Captioning with Multiscale Temporal Fusion and Commonsense Knowledge","display_name":"CLIP4VideoCap: Rethinking Clip for Video Captioning with Multiscale Temporal Fusion and Commonsense Knowledge","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260149","doi":"https://doi.org/10.1109/icassp49357.2023.10097128"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097128","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014251585","display_name":"Tanvir Mahmud","orcid":"https://orcid.org/0000-0003-0529-2826"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tanvir Mahmud","raw_affiliation_strings":["The University of Texas at Austin,Austin,TX,USA","The University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin,Austin,TX,USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083793844","display_name":"Feng Liang","orcid":"https://orcid.org/0009-0006-4470-4423"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng Liang","raw_affiliation_strings":["The University of Texas at Austin,Austin,TX,USA","The University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin,Austin,TX,USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063459507","display_name":"Yaling Qing","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaling Qing","raw_affiliation_strings":["The University of Texas at Austin,Austin,TX,USA","The University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin,Austin,TX,USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065985595","display_name":"Diana Marculescu","orcid":"https://orcid.org/0000-0002-5734-4221"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diana Marculescu","raw_affiliation_strings":["The University of Texas at Austin,Austin,TX,USA","The University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin,Austin,TX,USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014251585"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.4913,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.63632749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9980000257492065,"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":0.9972000122070312,"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":0.949580192565918},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8426830768585205},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.7277098298072815},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6564162969589233},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6370171308517456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6083866357803345},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.5827085375785828},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5135193467140198},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4820290803909302},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43123096227645874},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40478795766830444},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.39425814151763916},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3630291819572449},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.18242213129997253}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.949580192565918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8426830768585205},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.7277098298072815},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6564162969589233},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6370171308517456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6083866357803345},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.5827085375785828},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5135193467140198},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4820290803909302},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43123096227645874},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40478795766830444},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39425814151763916},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3630291819572449},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.18242213129997253},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097128","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2139501017","https://openalex.org/W2425121537","https://openalex.org/W2750969225","https://openalex.org/W2913822893","https://openalex.org/W2955189310","https://openalex.org/W2963890755","https://openalex.org/W2965432789","https://openalex.org/W2971775690","https://openalex.org/W3000303105","https://openalex.org/W3023993913","https://openalex.org/W3101767943","https://openalex.org/W3120164061","https://openalex.org/W3152798676","https://openalex.org/W3160891393","https://openalex.org/W3166396011","https://openalex.org/W3205021045","https://openalex.org/W4292958273","https://openalex.org/W4307106676","https://openalex.org/W4394659899","https://openalex.org/W6772619176","https://openalex.org/W6791353385","https://openalex.org/W6793759846","https://openalex.org/W6803567076","https://openalex.org/W6841484515","https://openalex.org/W6864544085"],"related_works":["https://openalex.org/W3035583586","https://openalex.org/W4320165839","https://openalex.org/W2151799802","https://openalex.org/W4385488510","https://openalex.org/W2196562041","https://openalex.org/W2073302931","https://openalex.org/W3206107299","https://openalex.org/W3082691151","https://openalex.org/W4287633646","https://openalex.org/W4378501473"],"abstract_inverted_index":{"In":[0,26,82],"this":[1],"paper,":[2],"we":[3,37,67,84,114],"propose":[4,68],"CLIP4VideoCap":[5],"for":[6],"video":[7,35,106],"captioning":[8],"based":[9],"on":[10,33,118],"large-scale":[11],"pre-trained":[12],"CLIP":[13],"image":[14,58],"and":[15,23],"text":[16],"encoders":[17],"together":[18],"with":[19],"multi-scale":[20,70],"temporal":[21,62,71,76,80],"reasoning":[22,63],"commonsense":[24,87,102],"knowledge.":[25],"addition":[27],"to":[28,46,51],"the":[29,48,57,65,90,96,101,105,108,119],"CLIP-image":[30],"encoder":[31,50],"operating":[32],"successive":[34],"frames,":[36],"introduce":[38],"a":[39,69],"knowledge":[40,55],"distillation-based":[41],"learning":[42],"scheme":[43,73],"that":[44,74,124],"aims":[45],"exploit":[47],"CLIP-text":[49],"generate":[52],"rich":[53],"textual":[54],"from":[56,78,104],"features.":[59],"For":[60],"improved":[61],"over":[64],"video,":[66],"fusion":[72],"accumulates":[75],"features":[77,103],"different":[79],"windows.":[81],"addition,":[83],"integrate":[85],"various":[86],"aspects":[88],"in":[89,107],"caption":[91,97],"generation":[92],"which":[93],"greatly":[94],"enhances":[95],"quality":[98],"by":[99],"extracting":[100],"intermediate":[109],"phase.":[110],"Combining":[111],"these":[112],"strategies,":[113],"achieve":[115],"state-of-the-art":[116],"performance":[117],"benchmark":[120],"MSR-VTT":[121],"dataset":[122],"confirming":[123],"our":[125],"framework":[126],"significantly":[127],"outperforms":[128],"existing":[129],"approaches.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}