{"id":"https://openalex.org/W4403061203","doi":"https://doi.org/10.1109/iotaai62601.2024.10692707","title":"Video Summarization using Multi-Scale Dilated Hybrid Attention Mechanisms","display_name":"Video Summarization using Multi-Scale Dilated Hybrid Attention Mechanisms","publication_year":2024,"publication_date":"2024-07-26","ids":{"openalex":"https://openalex.org/W4403061203","doi":"https://doi.org/10.1109/iotaai62601.2024.10692707"},"language":"en","primary_location":{"id":"doi:10.1109/iotaai62601.2024.10692707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iotaai62601.2024.10692707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 6th International Conference on Internet of Things, Automation and Artificial Intelligence (IoTAAI)","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/A5068720671","display_name":"Jingyun Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingyun Yan","raw_affiliation_strings":["China Aerospace Academy of Systems Science and Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Aerospace Academy of Systems Science and Engineering,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114238734","display_name":"Xiuyun Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiuyun Cao","raw_affiliation_strings":["China Aerospace Academy of Systems Science and Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Aerospace Academy of Systems Science and Engineering,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101678888","display_name":"Jun Jiang","orcid":"https://orcid.org/0000-0002-4373-9185"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Jiang","raw_affiliation_strings":["China Aerospace Academy of Systems Science and Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Aerospace Academy of Systems Science and Engineering,Beijing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033841572","display_name":"Xingxing Fang","orcid":"https://orcid.org/0000-0002-6390-4678"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingxing Fang","raw_affiliation_strings":["China Aerospace Academy of Systems Science and Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Aerospace Academy of Systems Science and Engineering,Beijing,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5259,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69974277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"698","last_page":"702"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9914000034332275,"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":0.9914000034332275,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9896000027656555,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9883999824523926,"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":0.9261391758918762},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7134957313537598},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.49814748764038086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3408069312572479},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3322860598564148}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9261391758918762},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7134957313537598},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.49814748764038086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3408069312572479},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3322860598564148},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iotaai62601.2024.10692707","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iotaai62601.2024.10692707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 6th International Conference on Internet of Things, Automation and Artificial Intelligence (IoTAAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2098159512","https://openalex.org/W2737677090","https://openalex.org/W2781922022","https://openalex.org/W2782139640","https://openalex.org/W2902616437","https://openalex.org/W2904820498","https://openalex.org/W2963919999","https://openalex.org/W2964158702","https://openalex.org/W2964167369","https://openalex.org/W2971202647","https://openalex.org/W3010145455","https://openalex.org/W3090254005","https://openalex.org/W3210314917","https://openalex.org/W4205776365","https://openalex.org/W4206423448","https://openalex.org/W4319663728","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2351187795","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747"],"abstract_inverted_index":{"Video":[0],"summarization":[1,29],"is":[2],"an":[3],"essential":[4],"technique":[5],"for":[6,66],"efficiently":[7],"managing":[8],"and":[9,38,51,80,92,107,119,128,137,159],"browsing":[10],"large":[11],"volumes":[12],"of":[13],"video":[14,25,28,67,161],"data":[15],"by":[16],"extracting":[17],"key":[18],"frames":[19],"or":[20],"segments":[21],"to":[22,45,88,104,148],"generate":[23],"concise":[24],"summaries.":[26,162],"Traditional":[27],"methods":[30],"often":[31],"struggle":[32],"with":[33,47,101],"capturing":[34],"multi-scale":[35],"temporal":[36,94],"features":[37,109,115],"integrating":[39],"information":[40,49],"across":[41],"different":[42],"scales,":[43],"leading":[44],"summaries":[46],"poor":[48],"density":[50],"completeness.":[52],"To":[53],"address":[54],"these":[55,114],"challenges,":[56],"we":[57],"propose":[58],"a":[59,72,81],"novel":[60],"Multi-Scale":[61,73],"Dilated":[62,74],"Hybrid":[63,75,83],"Attention":[64,76,85],"Mechanism":[65],"summarization.":[68],"Our":[69],"approach":[70],"leverages":[71],"Transformer":[77],"Encoder":[78],"(MSDHAT-Encoder)":[79],"Segmented":[82],"Residual":[84],"Network":[86],"(SHRAN)":[87],"capture":[89],"both":[90],"fine-grained":[91],"long-range":[93],"dependencies.":[95],"The":[96],"MSDHAT-Encoder":[97],"combines":[98],"dilated":[99],"convolutions":[100],"self-attention":[102],"mechanisms":[103],"model":[105],"local":[106],"global":[108],"effectively,":[110],"while":[111],"SHRAN":[112],"refines":[113],"using":[116],"segment-level":[117],"attention":[118],"residual":[120],"connections.":[121],"Experimental":[122],"results":[123],"on":[124],"benchmark":[125],"datasets":[126,135],"SumMe":[127],"TVSum,":[129],"as":[130,132],"well":[131],"the":[133],"enhanced":[134,154],"YouTube":[136],"OVP,":[138],"demonstrate":[139],"that":[140],"our":[141],"proposed":[142],"framework":[143],"achieves":[144],"improved":[145],"performance":[146],"compared":[147],"other":[149],"existing":[150],"methods.":[151],"It":[152],"shows":[153],"effectiveness":[155],"in":[156],"generating":[157],"accurate":[158],"representative":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}