{"id":"https://openalex.org/W3035763695","doi":"https://doi.org/10.24963/ijcai.2020/131","title":"Hierarchical Attention Based Spatial-Temporal Graph-to-Sequence Learning for Grounded Video Description","display_name":"Hierarchical Attention Based Spatial-Temporal Graph-to-Sequence Learning for Grounded Video Description","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3035763695","doi":"https://doi.org/10.24963/ijcai.2020/131","mag":"3035763695"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/131","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/131","pdf_url":"https://www.ijcai.org/proceedings/2020/0131.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0131.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114858716","display_name":"Kai Shen","orcid":"https://orcid.org/0000-0002-3564-0281"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Shen","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011825081","display_name":"Lingfei Wu","orcid":"https://orcid.org/0000-0002-3660-651X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingfei Wu","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046151303","display_name":"Fangli Xu","orcid":"https://orcid.org/0000-0003-1519-2909"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fangli Xu","raw_affiliation_strings":["Squirrel AI Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Squirrel AI Learning","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063062444","display_name":"Siliang Tang","orcid":"https://orcid.org/0000-0002-7356-9711"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siliang Tang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101485989","display_name":"Jun Xiao","orcid":"https://orcid.org/0000-0002-6142-9914"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xiao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008666077","display_name":"Yueting Zhuang","orcid":"https://orcid.org/0000-0001-9017-2508"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueting Zhuang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"941","last_page":"947"},"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":0.9980999827384949,"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":0.9919999837875366,"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/exploit","display_name":"Exploit","score":0.8084209561347961},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.753235936164856},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5682260394096375},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5030845999717712},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5014533996582031},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.48271867632865906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46654725074768066}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.8084209561347961},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753235936164856},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5682260394096375},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5030845999717712},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5014533996582031},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.48271867632865906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46654725074768066},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/131","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/131","pdf_url":"https://www.ijcai.org/proceedings/2020/0131.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/131","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/131","pdf_url":"https://www.ijcai.org/proceedings/2020/0131.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G297858759","display_name":null,"funder_award_id":"U19B2043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3025651444","display_name":null,"funder_award_id":"LZ17F020001","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G3466144234","display_name":null,"funder_award_id":"61976185","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4138342883","display_name":"\u590d\u6742\u89c6\u89c9\u573a\u666f\u667a\u80fd\u611f\u77e5\u4e0e\u5185\u5bb9\u751f\u6210\u7814\u7a76","funder_award_id":"LR19F020002","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G5526867466","display_name":null,"funder_award_id":"U1611461","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6605900608","display_name":null,"funder_award_id":"61751209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7385131631","display_name":null,"funder_award_id":"LR19F020002, LZ17F020001","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322927","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884"},{"id":"https://openalex.org/F4320327609","display_name":"China Knowledge Centre for Engineering Sciences and Technology","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3035763695.pdf","grobid_xml":"https://content.openalex.org/works/W3035763695.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522734439","https://openalex.org/W2139501017","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2322020277","https://openalex.org/W2745461083","https://openalex.org/W2796167946","https://openalex.org/W2806331055","https://openalex.org/W2807718466","https://openalex.org/W2889418103","https://openalex.org/W2890531016","https://openalex.org/W2948358897","https://openalex.org/W2963101956","https://openalex.org/W2963351113","https://openalex.org/W2963403868","https://openalex.org/W2967827612","https://openalex.org/W2968101724","https://openalex.org/W2994821362","https://openalex.org/W2994900646","https://openalex.org/W2995796742","https://openalex.org/W3003307214","https://openalex.org/W3004349648","https://openalex.org/W3034549794","https://openalex.org/W4289542422","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"The":[0],"task":[1,55],"of":[2,142],"Grounded":[3],"Video":[4],"Description~(GVD)":[5],"is":[6],"to":[7,27,73,85,109,123,147],"generate":[8],"sentences":[9],"whose":[10],"objects":[11,96],"can":[12],"be":[13],"grounded":[14],"with":[15],"the":[16,20,34,37,53,134,140],"bounding":[17],"boxes":[18],"in":[19,32,41,71,97,127],"video":[21,65],"frames.":[22],"Existing":[23],"works":[24],"often":[25],"fail":[26],"exploit":[28,82],"structural":[29,77],"information":[30],"both":[31],"modeling":[33],"relationships":[35],"among":[36,94],"region":[38],"proposals":[39],"and":[40,100],"attending":[42],"them":[43],"for":[44,131],"text":[45],"generation.":[46],"To":[47],"address":[48],"these":[49],"issues,":[50],"we":[51,63,81,117],"cast":[52],"GVD":[54],"as":[56,67],"a":[57,87,103],"spatial-temporal":[58,68,92],"Graph-to-Sequence":[59],"learning":[60],"problem,":[61],"where":[62],"model":[64],"frames":[66],"sequence":[69,88,125],"graph":[70,89,105,113,126],"order":[72],"better":[74,132],"capture":[75],"implicit":[76],"relationships.":[78],"In":[79,115],"particular,":[80],"two":[83],"ways":[84],"construct":[86],"that":[90],"captures":[91],"correlations":[93],"different":[95,128],"each":[98],"frame":[99],"further":[101],"present":[102,119],"novel":[104],"topology":[106],"refinement":[107],"technique":[108],"discover":[110],"optimal":[111],"underlying":[112],"structure.":[114],"addition,":[116],"also":[118],"hierarchical":[120],"attention":[121],"mechanism":[122],"attend":[124],"resolution":[129],"levels":[130],"generating":[133],"sentences.":[135],"Our":[136],"extensive":[137],"experiments":[138],"demonstrate":[139],"effectiveness":[141],"our":[143],"proposed":[144],"method":[145],"compared":[146],"state-of-the-art":[148],"methods.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}