{"id":"https://openalex.org/W3091672532","doi":"https://doi.org/10.1109/icip40778.2020.9190820","title":"Retrieving and Highlighting Action with Spatiotemporal Reference","display_name":"Retrieving and Highlighting Action with Spatiotemporal Reference","publication_year":2020,"publication_date":"2020-09-30","ids":{"openalex":"https://openalex.org/W3091672532","doi":"https://doi.org/10.1109/icip40778.2020.9190820","mag":"3091672532"},"language":"en","primary_location":{"id":"doi:10.1109/icip40778.2020.9190820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9190820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Image Processing (ICIP)","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/A5066258514","display_name":"Seito Kasai","orcid":"https://orcid.org/0000-0003-2225-7053"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Seito Kasai","raw_affiliation_strings":["Keio University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110664866","display_name":"Yuchi Ishikawa","orcid":"https://orcid.org/0000-0002-9485-6840"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuchi Ishikawa","raw_affiliation_strings":["Keio University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064065544","display_name":"Masaki Hayashi","orcid":"https://orcid.org/0000-0003-4890-3113"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaki Hayashi","raw_affiliation_strings":["Keio University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070908826","display_name":"Yoshimitsu Aoki","orcid":"https://orcid.org/0000-0001-7361-0027"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshimitsu Aoki","raw_affiliation_strings":["Keio University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061654293","display_name":"Kensho Hara","orcid":"https://orcid.org/0000-0001-6463-7738"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kensho Hara","raw_affiliation_strings":["AIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIST","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011507481","display_name":"Hirokatsu Kataoka","orcid":"https://orcid.org/0000-0001-8844-165X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hirokatsu Kataoka","raw_affiliation_strings":["AIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIST","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"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":0.10883667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1401","last_page":"1405"},"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":0.9998999834060669,"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":0.996399998664856,"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/computer-science","display_name":"Computer science","score":0.8415219187736511},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7212119698524475},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6681843400001526},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6546109914779663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6471007466316223},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6248387098312378},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.573756992816925},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5651654005050659},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.531963586807251},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4834485948085785},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4728703200817108},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.42549240589141846},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3850090205669403},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3753175735473633},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.328123539686203}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8415219187736511},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7212119698524475},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6681843400001526},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6546109914779663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6471007466316223},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6248387098312378},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.573756992816925},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5651654005050659},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.531963586807251},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4834485948085785},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4728703200817108},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.42549240589141846},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3850090205669403},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3753175735473633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.328123539686203},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip40778.2020.9190820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9190820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1527575280","https://openalex.org/W2096733369","https://openalex.org/W2425121537","https://openalex.org/W2774267535","https://openalex.org/W2796207103","https://openalex.org/W2808399042","https://openalex.org/W2810689564","https://openalex.org/W2936420065","https://openalex.org/W2951174316","https://openalex.org/W2961193895","https://openalex.org/W2962858109","https://openalex.org/W2962934715","https://openalex.org/W2963467339","https://openalex.org/W2963499204","https://openalex.org/W2964187781","https://openalex.org/W2964276596","https://openalex.org/W2965458216","https://openalex.org/W2972073579","https://openalex.org/W2975813532","https://openalex.org/W2990503944","https://openalex.org/W3023441976","https://openalex.org/W3099206234","https://openalex.org/W6631516269","https://openalex.org/W6717767745","https://openalex.org/W6747225742","https://openalex.org/W6750041603","https://openalex.org/W6752948076","https://openalex.org/W6761692906","https://openalex.org/W6765307894","https://openalex.org/W6766263406","https://openalex.org/W6766582784"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2358294942","https://openalex.org/W4367460280"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,91],"present":[4],"a":[5,48,116],"framework":[6,71],"that":[7,93],"jointly":[8],"retrieves":[9],"and":[10,36,76,85],"spatiotemporally":[11],"highlights":[12],"actions":[13,38],"in":[14,40,87,103],"videos":[15],"by":[16,132],"enhancing":[17],"current":[18],"deep":[19],"cross-modal":[20],"retrieval":[21,125],"methods.":[22],"Our":[23],"work":[24],"takes":[25],"on":[26,59,100,134],"the":[27,83,135],"novel":[28],"task":[29],"of":[30],"action":[31,54],"highlighting,":[32],"which":[33,57,80,104],"visualizes":[34],"where":[35],"when":[37],"occur":[39],"an":[41],"untrimmed":[42],"video":[43],"setting.":[44],"Action":[45],"highlighting":[46],"is":[47],"fine-grained":[49],"task,":[50],"compared":[51],"to":[52,82,114],"conventional":[53,105],"recognition":[55],"tasks":[56],"focus":[58],"classification":[60],"or":[61],"window-based":[62],"localization.":[63],"Leveraging":[64],"weak":[65],"supervision":[66],"from":[67],"annotated":[68],"captions,":[69],"our":[70,94,122,128],"acquires":[72],"spatiotemporal":[73],"relevance":[74],"maps":[75,98],"generates":[77,96],"local":[78],"embeddings":[79],"relate":[81],"nouns":[84],"verbs":[86],"captions.":[88],"Through":[89],"experiments,":[90],"show":[92,115],"model":[95,123],"various":[97],"conditioned":[99],"different":[101],"actions,":[102],"visual":[106],"reasoning":[107],"methods":[108],"only":[109],"go":[110],"as":[111,113],"far":[112],"single":[117],"deterministic":[118],"saliency":[119],"map.":[120],"Also,":[121],"improves":[124],"recall":[126],"over":[127],"baseline":[129],"without":[130],"alignment":[131],"2-3%":[133],"MSR-VTT":[136],"dataset.":[137]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}