{"id":"https://openalex.org/W4226180366","doi":"https://doi.org/10.1145/3512576.3512606","title":"Human Action Captioning based on a GRU+LSTM+Attention Model","display_name":"Human Action Captioning based on a GRU+LSTM+Attention Model","publication_year":2021,"publication_date":"2021-12-22","ids":{"openalex":"https://openalex.org/W4226180366","doi":"https://doi.org/10.1145/3512576.3512606"},"language":"en","primary_location":{"id":"doi:10.1145/3512576.3512606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512576.3512606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 The 9th International Conference on Information Technology: IoT and Smart City","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/A5058467326","display_name":"Lijuan Zhou","orcid":"https://orcid.org/0000-0002-6418-6284"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lijuan Zhou","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, China and Zhengzhou Zoneyet Technology Co., Ltd., China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, China and Zhengzhou Zoneyet Technology Co., Ltd., China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043191784","display_name":"Weicong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weicong Zhang","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, China and Zhengzhou Zoneyet Technology Co., Ltd., China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, China and Zhengzhou Zoneyet Technology Co., Ltd., China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101827794","display_name":"Xiaojie Qian","orcid":"https://orcid.org/0009-0004-8545-7815"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Qian","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, China","institution_ids":["https://openalex.org/I38877650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5058467326"],"corresponding_institution_ids":["https://openalex.org/I38877650"],"apc_list":null,"apc_paid":null,"fwci":0.2882,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.57900327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"168","last_page":"173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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":0.992900013923645,"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/closed-captioning","display_name":"Closed captioning","score":0.9561573266983032},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8339422941207886},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.7054010629653931},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6379504799842834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.624671459197998},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6023316383361816},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5819556713104248},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42051011323928833},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09153872728347778}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9561573266983032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8339422941207886},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7054010629653931},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6379504799842834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.624671459197998},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6023316383361816},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5819556713104248},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42051011323928833},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09153872728347778},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3512576.3512606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512576.3512606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 The 9th International Conference on Information Technology: IoT and Smart City","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8399999737739563,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6241720096","display_name":null,"funder_award_id":"62006211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6573402828","display_name":null,"funder_award_id":"2019TQ0286,2020M682349","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1502957213","https://openalex.org/W1586939924","https://openalex.org/W1593271688","https://openalex.org/W1601567445","https://openalex.org/W1614298861","https://openalex.org/W1847618513","https://openalex.org/W2101105183","https://openalex.org/W2110933980","https://openalex.org/W2133512280","https://openalex.org/W2133564696","https://openalex.org/W2142900973","https://openalex.org/W2526468814","https://openalex.org/W2595813107","https://openalex.org/W2596567068","https://openalex.org/W2727718475","https://openalex.org/W2914587137","https://openalex.org/W2963351113","https://openalex.org/W2968124245","https://openalex.org/W2981750519","https://openalex.org/W3035265375","https://openalex.org/W3035365026","https://openalex.org/W3123172502","https://openalex.org/W3174257385","https://openalex.org/W3176689360","https://openalex.org/W3201519611","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"To":[0,74],"quickly":[1],"understand":[2],"human":[3,14,27,72],"actions":[4,82,88],"in":[5,96],"the":[6,13,49,53,63,67,77,85,97,102,106,109],"videos,":[7],"this":[8,42],"paper":[9],"proposes":[10],"to":[11,20,40,51,65],"solve":[12,41],"action":[15,28],"captioning":[16],"problem":[17],"which":[18],"aims":[19],"automatically":[21],"generate":[22,66],"text":[23],"descriptions":[24,70],"based":[25,33],"on":[26,34,76,101],"videos.":[29],"A":[30],"sequence-to-sequence":[31],"method":[32],"GRU+LSTM+Attention":[35],"(GLA)":[36],"model":[37],"is":[38,46,60,94],"proposed":[39,98,110],"problem.":[43],"Specifically,":[44],"GRU":[45],"applied":[47,61,95],"as":[48,62],"encoder":[50],"capture":[52,84],"temporal":[54],"information":[55],"of":[56,81,108],"actions.":[57,73],"The":[58],"LSTM":[59],"decoder":[64],"fluent":[68],"fine-grained":[69],"for":[71],"focus":[75],"most":[78],"relevant":[79],"part":[80],"and":[83,89],"correlation":[86],"between":[87],"descriptions,":[90],"an":[91],"attention":[92],"mechanism":[93],"method.":[99,111],"Experiments":[100],"WorkoutUOW-18":[103],"dataset":[104],"demonstrate":[105],"effectiveness":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}