{"id":"https://openalex.org/W3128220517","doi":"https://doi.org/10.1145/3443279.3443285","title":"Using Spatial Temporal Graph Convolutional Network Dynamic Scene Graph for Video Captioning of Pedestrians Intention","display_name":"Using Spatial Temporal Graph Convolutional Network Dynamic Scene Graph for Video Captioning of Pedestrians Intention","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3128220517","doi":"https://doi.org/10.1145/3443279.3443285","mag":"3128220517"},"language":"en","primary_location":{"id":"doi:10.1145/3443279.3443285","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3443279.3443285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Natural Language Processing and Information Retrieval","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/A5101920378","display_name":"Dong Cao","orcid":"https://orcid.org/0000-0001-8270-6960"},"institutions":[{"id":"https://openalex.org/I4401726871","display_name":"Deepblue Technology (China)","ror":"https://ror.org/01n015v70","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726871"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dong Cao","raw_affiliation_strings":["DeepBlue Technology (Shanghai) Co., Ltd. Shanghai, China"],"affiliations":[{"raw_affiliation_string":"DeepBlue Technology (Shanghai) Co., Ltd. Shanghai, China","institution_ids":["https://openalex.org/I4401726871"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091724742","display_name":"Qunhe Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726871","display_name":"Deepblue Technology (China)","ror":"https://ror.org/01n015v70","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726871"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qunhe Zhao","raw_affiliation_strings":["DeepBlue Technology Co., Ltd. Shanghai, China"],"affiliations":[{"raw_affiliation_string":"DeepBlue Technology Co., Ltd. Shanghai, China","institution_ids":["https://openalex.org/I4401726871"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024947652","display_name":"Yunbin Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726871","display_name":"Deepblue Technology (China)","ror":"https://ror.org/01n015v70","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726871"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbin Fu","raw_affiliation_strings":["DeepBlue Technology (Shanghai)Co., Ltd. Shanghai, China"],"affiliations":[{"raw_affiliation_string":"DeepBlue Technology (Shanghai)Co., Ltd. Shanghai, China","institution_ids":["https://openalex.org/I4401726871"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101920378"],"corresponding_institution_ids":["https://openalex.org/I4401726871"],"apc_list":null,"apc_paid":null,"fwci":0.1954,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52455132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"179","last_page":"183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9940999746322632,"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/computer-science","display_name":"Computer science","score":0.8666192889213562},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8606631755828857},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6215579509735107},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5571442246437073},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5531559586524963},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5438551902770996},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.459307998418808},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.41366589069366455},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20022472739219666},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.16674402356147766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8666192889213562},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8606631755828857},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6215579509735107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5571442246437073},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5531559586524963},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5438551902770996},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.459307998418808},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.41366589069366455},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20022472739219666},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.16674402356147766},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3443279.3443285","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3443279.3443285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Natural Language Processing and Information Retrieval","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":25,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2016053056","https://openalex.org/W2116341502","https://openalex.org/W2117539524","https://openalex.org/W2424778531","https://openalex.org/W2425121537","https://openalex.org/W2570343428","https://openalex.org/W2607855566","https://openalex.org/W2613718673","https://openalex.org/W2769277182","https://openalex.org/W2948358897","https://openalex.org/W2954414836","https://openalex.org/W2962785943","https://openalex.org/W2963076818","https://openalex.org/W2963514444","https://openalex.org/W2964350391","https://openalex.org/W2968104955","https://openalex.org/W2972943773","https://openalex.org/W2979635428","https://openalex.org/W2985775525","https://openalex.org/W2987123286","https://openalex.org/W2991653934","https://openalex.org/W3003533476","https://openalex.org/W3003626968","https://openalex.org/W6690815549"],"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/W4287661223","https://openalex.org/W4392007279","https://openalex.org/W4387129494"],"abstract_inverted_index":{"Video":[0],"captioning":[1,81,177],"helps":[2],"to":[3,48,144],"understand":[4,146],"video":[5,31,80,124,171,176],"content":[6],"at":[7],"a":[8,79,88],"semantic":[9,110,160],"level.":[10],"The":[11,22,100],"scene":[12,23,91,102],"graph":[13,24,92,97,103],"method":[14,25,104,156,187],"can":[15,26,188],"realize":[16],"structured":[17,111],"representation":[18,112],"of":[19,36,82,108,113,122,133,150,193],"image":[20],"semantics.":[21],"provide":[27],"effective":[28],"support":[29],"for":[30,179],"captioning.":[32],"In":[33,74],"the":[34,58,66,106,109,114,123,141,147,170,175,191],"areas":[35],"autonomous":[37],"driving":[38],"and":[39,55,57,130,165],"Advanced":[40],"Driver":[41],"Assistance":[42],"Systems":[43],"(ADAS),":[44],"intelligent":[45],"systems":[46],"need":[47],"make":[49,68,119],"cognitive":[50],"inferences":[51],"about":[52],"pedestrian":[53,180],"intentions":[54],"behaviors,":[56],"relationships":[59],"between":[60,128],"surrounding":[61],"objects.":[62],"This":[63,85],"will":[64],"help":[65],"system":[67],"accurate":[69],"decisions":[70],"in":[71,136],"real":[72],"time.":[73],"this":[75],"paper,":[76],"we":[77],"propose":[78],"pedestrians":[83],"intention,":[84],"algorithm":[86],"constructs":[87],"novel":[89,186],"dynamic":[90,148],"based":[93],"on":[94],"spatial":[95,164],"temporal":[96],"convolution":[98],"network.":[99],"previous":[101],"solved":[105],"problem":[107],"image,":[115],"but":[116],"did":[117],"not":[118,145],"good":[120],"use":[121],"time":[125],"series":[126],"information":[127],"front":[129],"back":[131],"images":[132],"consecutive":[134],"frames":[135],"video.":[137],"Such":[138],"defects":[139],"cause":[140],"existing":[142],"algorithms":[143],"behavior":[149],"traffic":[151],"scenes":[152],"well.":[153],"Our":[154],"new":[155],"collaboratively":[157],"extracts":[158],"visual":[159],"features":[161],"from":[162],"both":[163],"temporal,":[166],"which":[167],"effectively":[168],"improves":[169],"reasoning":[172],"ability.":[173],"On":[174],"dataset":[178],"scenes,":[181],"Experimental":[182],"results":[183],"show":[184],"that":[185],"significantly":[189],"improve":[190],"performance":[192],"trajectory":[194],"prediction.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}