{"id":"https://openalex.org/W4221049797","doi":"https://doi.org/10.1145/3512388.3512427","title":"SHTVS: Shot-level based Hierarchical Transformer for Video Summarization","display_name":"SHTVS: Shot-level based Hierarchical Transformer for Video Summarization","publication_year":2022,"publication_date":"2022-01-07","ids":{"openalex":"https://openalex.org/W4221049797","doi":"https://doi.org/10.1145/3512388.3512427"},"language":"en","primary_location":{"id":"doi:10.1145/3512388.3512427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512388.3512427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 the 5th International Conference on Image and Graphics Processing (ICIGP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5055172259","display_name":"Yubo An","orcid":"https://orcid.org/0000-0001-6111-697X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yubo An","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077965872","display_name":"Shenghui Zhao","orcid":"https://orcid.org/0000-0002-0844-2319"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenghui Zhao","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"268","last_page":"274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","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"}},"topics":[{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","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/T11309","display_name":"Music and Audio Processing","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9555000066757202,"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/automatic-summarization","display_name":"Automatic summarization","score":0.937758207321167},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7886636257171631},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.765498697757721},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6991661787033081},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6670063734054565},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5398257970809937},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47458648681640625},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44704723358154297},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4363187551498413},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10093855857849121}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.937758207321167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7886636257171631},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.765498697757721},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6991661787033081},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6670063734054565},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5398257970809937},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47458648681640625},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44704723358154297},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4363187551498413},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10093855857849121},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic 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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3512388.3512427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512388.3512427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 the 5th International Conference on Image and Graphics Processing (ICIGP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1924343884","https://openalex.org/W1987366351","https://openalex.org/W2097117768","https://openalex.org/W2529272619","https://openalex.org/W2558333741","https://openalex.org/W2607326921","https://openalex.org/W2737677090","https://openalex.org/W2883872876","https://openalex.org/W2906430987","https://openalex.org/W2963351448","https://openalex.org/W2964167369","https://openalex.org/W3087792975","https://openalex.org/W3115386295","https://openalex.org/W3136873339","https://openalex.org/W3138217142","https://openalex.org/W3201625964","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W4317547544","https://openalex.org/W4313395829"],"abstract_inverted_index":{"In":[0,64],"this":[1],"paper,":[2],"a":[3,47,75],"Shot-level":[4],"based":[5],"Hierarchical":[6],"Transformer":[7,49,97,116],"for":[8,14,113],"Video":[9],"Summarization":[10],"(SHTVS)":[11],"is":[12,81],"proposed":[13],"supervised":[15],"video":[16,51,62,78,108],"summarization.":[17,63],"Different":[18],"from":[19],"most":[20],"existing":[21],"methods":[22,44],"that":[23,46],"employ":[24],"bidirectional":[25],"long":[26],"short-term":[27],"memory":[28],"or":[29],"use":[30,69],"self-attention":[31],"to":[32,66,99,118],"replace":[33],"certain":[34],"components":[35],"while":[36],"keeping":[37],"their":[38],"overall":[39],"structure":[40],"in":[41,61,74],"place,":[42],"our":[43,137],"show":[45],"pure":[48],"with":[50,88],"feature":[52,79,86,109],"sequences":[53,87],"as":[54],"its":[55],"input":[56],"can":[57],"achieve":[58],"competitive":[59],"performance":[60],"addition,":[65],"make":[67],"better":[68],"of":[70,136],"the":[71,114,134],"multi-shot":[72],"characteristic":[73],"video,":[76],"each":[77],"sequence":[80,110],"firstly":[82],"split":[83],"into":[84,95],"shot-level":[85,96,101,104],"kernel":[89],"temporal":[90],"segmentation,":[91],"and":[92,106,131],"then":[93],"fed":[94],"encoder":[98,117],"learn":[100],"representations.":[102],"Finally,":[103],"representations":[105],"original":[107],"are":[111],"integrated":[112],"frame-level":[115,120],"predict":[119],"importance":[121],"scores.":[122],"Extensive":[123],"experimental":[124],"results":[125],"on":[126],"two":[127],"benchmark":[128],"datasets":[129],"(SumMe":[130],"TVSum)":[132],"prove":[133],"effectiveness":[135],"methods.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}