{"id":"https://openalex.org/W4379806264","doi":"https://doi.org/10.1145/3591106.3592258","title":"A Unified Model for Video Understanding and Knowledge Embedding with Heterogeneous Knowledge Graph Dataset","display_name":"A Unified Model for Video Understanding and Knowledge Embedding with Heterogeneous Knowledge Graph Dataset","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4379806264","doi":"https://doi.org/10.1145/3591106.3592258"},"language":"en","primary_location":{"id":"doi:10.1145/3591106.3592258","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3591106.3592258","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3591106.3592258","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3591106.3592258","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103071284","display_name":"Jiaxin Deng","orcid":"https://orcid.org/0009-0003-1274-4154"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaxin Deng","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences & School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":"https://orcid.org/0009-0003-1274-4154","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences & School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026403327","display_name":"Dong Shen","orcid":"https://orcid.org/0000-0001-5592-8453"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Shen","raw_affiliation_strings":["MMU KuaiShou Inc., China"],"raw_orcid":"https://orcid.org/0000-0001-5592-8453","affiliations":[{"raw_affiliation_string":"MMU KuaiShou Inc., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haojie Pan","orcid":"https://orcid.org/0000-0002-6441-892X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haojie Pan","raw_affiliation_strings":["MMU KuaiShou Inc., China"],"raw_orcid":"https://orcid.org/0000-0002-6441-892X","affiliations":[{"raw_affiliation_string":"MMU KuaiShou Inc., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103045521","display_name":"Xiangyu Wu","orcid":"https://orcid.org/0009-0009-4802-2712"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangyu Wu","raw_affiliation_strings":["MMU KuaiShou Inc., China"],"raw_orcid":"https://orcid.org/0009-0009-4802-2712","affiliations":[{"raw_affiliation_string":"MMU KuaiShou Inc., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ximan Liu","orcid":"https://orcid.org/0009-0007-1685-101X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ximan Liu","raw_affiliation_strings":["MMU KuaiShou Inc., China"],"raw_orcid":"https://orcid.org/0009-0007-1685-101X","affiliations":[{"raw_affiliation_string":"MMU KuaiShou Inc., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675867","display_name":"Gaofeng Meng","orcid":"https://orcid.org/0000-0002-7103-6321"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaofeng Meng","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences; School of Artificial Intelligence, University of Chinese Academy of Sciences; & CAIR, HK Institute of Science and Innovation, Chinese Academy of Sciences"],"raw_orcid":"https://orcid.org/0000-0002-7103-6321","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences; School of Artificial Intelligence, University of Chinese Academy of Sciences; & CAIR, HK Institute of Science and Innovation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101591804","display_name":"Fan Yang","orcid":"https://orcid.org/0009-0005-4570-5885"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["MMU KuaiShou Inc., China"],"raw_orcid":"https://orcid.org/0009-0005-4570-5885","affiliations":[{"raw_affiliation_string":"MMU KuaiShou Inc., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102898179","display_name":"Tingting Gao","orcid":"https://orcid.org/0009-0003-0310-7751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tingting Gao","raw_affiliation_strings":["MMU KuaiShou Inc., China"],"raw_orcid":"https://orcid.org/0009-0003-0310-7751","affiliations":[{"raw_affiliation_string":"MMU KuaiShou Inc., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102819479","display_name":"Ruiji Fu","orcid":"https://orcid.org/0000-0002-9453-9060"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiji Fu","raw_affiliation_strings":["MMU KuaiShou Inc., China"],"raw_orcid":"https://orcid.org/0000-0002-9453-9060","affiliations":[{"raw_affiliation_string":"MMU KuaiShou Inc., China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090258312","display_name":"Zhongyuan Wang","orcid":"https://orcid.org/0000-0003-2987-9672"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongyuan Wang","raw_affiliation_strings":["MMU KuaiShou Inc., China"],"raw_orcid":"https://orcid.org/0000-0003-2987-9672","affiliations":[{"raw_affiliation_string":"MMU KuaiShou Inc., China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5103071284"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.1177,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.38028243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10812","display_name":"Human Pose and Action Recognition","score":0.9991000294685364,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8249471187591553},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6446521282196045},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5344191193580627},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.513613224029541},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49780917167663574},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.4761790633201599},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4408724009990692},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43343526124954224},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.42934268712997437},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3806038200855255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3725034296512604},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.3708544373512268},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.15986856818199158}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8249471187591553},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6446521282196045},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5344191193580627},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.513613224029541},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49780917167663574},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.4761790633201599},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4408724009990692},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43343526124954224},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.42934268712997437},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3806038200855255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3725034296512604},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3708544373512268},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.15986856818199158},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3591106.3592258","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3591106.3592258","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3591106.3592258","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3591106.3592258","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3591106.3592258","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3591106.3592258","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4379806264.pdf","grobid_xml":"https://content.openalex.org/works/W4379806264.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1964189668","https://openalex.org/W2133510502","https://openalex.org/W2250184916","https://openalex.org/W2283196293","https://openalex.org/W2620787630","https://openalex.org/W2808284704","https://openalex.org/W2889583850","https://openalex.org/W2962898354","https://openalex.org/W2963466847","https://openalex.org/W2969985801","https://openalex.org/W2990503944","https://openalex.org/W2998385486","https://openalex.org/W3035047011","https://openalex.org/W3078516413","https://openalex.org/W3135367836","https://openalex.org/W3173407577","https://openalex.org/W3205420591","https://openalex.org/W4304142382"],"related_works":["https://openalex.org/W2604454537","https://openalex.org/W2808284704","https://openalex.org/W2897702399","https://openalex.org/W4206028705","https://openalex.org/W2757431232","https://openalex.org/W2954554213","https://openalex.org/W4206547516","https://openalex.org/W4293236197","https://openalex.org/W4389850132","https://openalex.org/W4292070284"],"abstract_inverted_index":{"Video":[0],"understanding":[1,27,63,90,146,162,178],"is":[2,59,70,93],"an":[3,138],"important":[4],"task":[5],"in":[6,17,217],"short":[7],"video":[8,18,26,38,42,62,81,89,107,120,145,161,177,186],"business":[9],"platforms":[10],"and":[11,20,45,91,109,127,207,214],"it":[12,190],"has":[13],"a":[14,100],"wide":[15],"application":[16],"recommendation":[19],"classification.":[21],"Most":[22],"of":[23,80],"the":[24,32,37,41,53,67,74,78,85,105,124,144,184,193],"existing":[25],"works":[28],"only":[29,155],"focus":[30],"on":[31,133,205],"information":[33],"that":[34,103,141,175],"appeared":[35],"within":[36],"content,":[39],"including":[40],"frames,":[43],"audio":[44],"text.":[46],"However,":[47],"introducing":[48],"common":[49,111],"sense":[50,112],"knowledge":[51,82,149,159,182,197],"from":[52],"external":[54],"Knowledge":[55],"Graph":[56],"(KG)":[57],"dataset":[58,102,115],"essential":[60],"for":[61,170],"when":[64],"referring":[65],"to":[66,73,77],"content":[68],"which":[69,87,152,200],"less":[71],"relevant":[72],"video.":[75],"Owing":[76],"lack":[79],"graph":[83,150,198],"dataset,":[84,135],"work":[86],"integrates":[88],"KG":[92],"rare.":[94],"In":[95],"this":[96,134],"paper,":[97],"we":[98,136],"propose":[99,137],"heterogeneous":[101],"contains":[104],"multi-modal":[106,167],"entity":[108,168],"fruitful":[110],"relations.":[113],"This":[114],"also":[116,164,191],"provides":[117],"multiple":[118],"novel":[119],"inference":[121],"tasks":[122,209],"like":[123],"Video-Relation-Tag":[125],"(VRT)":[126],"Video-Relation-Video":[128],"(VRV)":[129],"tasks.":[130],"Furthermore,":[131],"based":[132],"end-to-end":[139],"model":[140,194],"jointly":[142],"optimizes":[143],"objective":[147],"with":[148,180,210],"embedding,":[151],"can":[153],"not":[154],"better":[156,196],"inject":[157],"factual":[158,181],"into":[160],"but":[163],"generate":[165,195],"effective":[166],"embedding":[169,179,199],"KG.":[171],"Comprehensive":[172],"experiments":[173],"indicate":[174],"combining":[176],"benefits":[183],"content-based":[185],"retrieval":[187],"performance.":[188],"Moreover,":[189],"helps":[192],"outperforms":[201],"traditional":[202],"KGE-based":[203],"methods":[204],"VRT":[206],"VRV":[208],"at":[211],"least":[212],"42.36%":[213],"17.73%":[215],"improvement":[216],"[email":[218],"protected].":[219]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}