{"id":"https://openalex.org/W2896897397","doi":"https://doi.org/10.1109/bigmm.2018.8499257","title":"Saliency-Based Spatiotemporal Attention for Video Captioning","display_name":"Saliency-Based Spatiotemporal Attention for Video Captioning","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2896897397","doi":"https://doi.org/10.1109/bigmm.2018.8499257","mag":"2896897397"},"language":"en","primary_location":{"id":"doi:10.1109/bigmm.2018.8499257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigmm.2018.8499257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM)","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/A5048381575","display_name":"Yangyu Chen","orcid":"https://orcid.org/0009-0006-5976-9772"},"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":"Yangyu Chen","raw_affiliation_strings":["University of Chinese Academy of Science, Beijing"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Science, Beijing","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014774434","display_name":"Weigang Zhang","orcid":"https://orcid.org/0000-0003-0042-7074"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weigang Zhang","raw_affiliation_strings":["Harbin Institute of Technology, Weihai"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Weihai","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669242","display_name":"Shuhui Wang","orcid":"https://orcid.org/0000-0002-5931-0527"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhui Wang","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Computing Technology, Beijing"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Computing Technology, Beijing","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420654","display_name":"Liang Li","orcid":"https://orcid.org/0000-0002-1943-8219"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Computing Technology, Beijing"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Computing Technology, Beijing","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Computing Technology, Beijing"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Computing Technology, Beijing","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048381575"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.7312,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.77009899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T11605","display_name":"Visual Attention and Saliency Detection","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987999796867371,"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":0.9749898314476013},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8489772081375122},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6014527678489685},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5869580507278442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5855737924575806},{"id":"https://openalex.org/keywords/saliency-map","display_name":"Saliency map","score":0.5691603422164917},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.5027420520782471},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.49797511100769043},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.49608978629112244},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49604520201683044},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.49339237809181213},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35273420810699463},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.31226861476898193}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9749898314476013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8489772081375122},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6014527678489685},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5869580507278442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5855737924575806},{"id":"https://openalex.org/C2779679900","wikidata":"https://www.wikidata.org/wiki/Q25304431","display_name":"Saliency map","level":3,"score":0.5691603422164917},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.5027420520782471},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.49797511100769043},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.49608978629112244},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49604520201683044},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.49339237809181213},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35273420810699463},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31226861476898193},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigmm.2018.8499257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigmm.2018.8499257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1514535095","https://openalex.org/W1521626219","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1686810756","https://openalex.org/W1956340063","https://openalex.org/W2041719651","https://openalex.org/W2047670868","https://openalex.org/W2089597841","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2110933980","https://openalex.org/W2123301721","https://openalex.org/W2128272608","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2164084182","https://openalex.org/W2194775991","https://openalex.org/W2472272718","https://openalex.org/W2507365558","https://openalex.org/W2508245937","https://openalex.org/W2523937091","https://openalex.org/W2962762462","https://openalex.org/W2962835968","https://openalex.org/W2962965405","https://openalex.org/W2963498278","https://openalex.org/W2963576560","https://openalex.org/W2963843052","https://openalex.org/W2964121744","https://openalex.org/W2964241990","https://openalex.org/W3098389804","https://openalex.org/W6621543089","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6678262379","https://openalex.org/W6727338826","https://openalex.org/W6784647857","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2949362007","https://openalex.org/W2895420168","https://openalex.org/W2896897397","https://openalex.org/W2155482448","https://openalex.org/W2363309472","https://openalex.org/W1513816165","https://openalex.org/W2358975700","https://openalex.org/W2252568761","https://openalex.org/W2899529391","https://openalex.org/W2357291621"],"abstract_inverted_index":{"Most":[0],"existing":[1],"video":[2,25,45,67,91],"captioning":[3,46],"methods":[4],"ignore":[5],"the":[6,39,43,57,63,77,82,88,97,109,122,132],"visual":[7,64,83],"saliency":[8,16,58,84],"information":[9,17,59,85],"in":[10],"videos.":[11],"We":[12,69],"suppose":[13],"that":[14,80],"using":[15,121],"can":[18,55,86,107,129],"be":[19],"helpful":[20],"to":[21,60],"generate":[22],"more":[23],"accurate":[24],"captions.":[26],"Therefore,":[27],"we":[28,49,128],"propose":[29],"a":[30,51],"saliency-based":[31,103,124],"spatiotemporal":[32,125],"attention":[33,100,105,126],"mechanism,":[34,127],"and":[35,76,111,116,134,138],"integrate":[36],"it":[37],"with":[38,96],"encoder-decoder":[40],"framework":[41],"of":[42,66,90],"classical":[44],"model.":[47],"Especially,":[48],"design":[50],"residual":[52],"block":[53],"which":[54],"use":[56],"properly":[61],"extract":[62],"feature":[65],"frames.":[68],"evaluate":[70],"our":[71,102],"method":[72],"on":[73],"MSVD":[74],"dataset":[75],"results":[78],"show":[79],"exploiting":[81],"improve":[87,108,131],"performance":[89],"captioning.":[92],"Specifically,":[93],"when":[94],"compared":[95],"traditional":[98],"temporal":[99,104],"method,":[101],"model":[106],"METEOR":[110,133],"CIDEr":[112,135],"metrics":[113],"by":[114,120,136],"3.4%":[115],"22.5%":[117],"respectively.":[118,141],"While":[119],"full":[123],"further":[130],"4.5%":[137],"23.1":[139],"%":[140]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}