{"id":"https://openalex.org/W4304755979","doi":"https://doi.org/10.1145/3562007.3562052","title":"Differentiate Visual Features with Guidance Signals for Video Captioning","display_name":"Differentiate Visual Features with Guidance Signals for Video Captioning","publication_year":2022,"publication_date":"2022-08-26","ids":{"openalex":"https://openalex.org/W4304755979","doi":"https://doi.org/10.1145/3562007.3562052"},"language":"en","primary_location":{"id":"doi:10.1145/3562007.3562052","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3562007.3562052","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3562007.3562052","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 3rd International Conference on Control, Robotics and Intelligent System","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/10.1145/3562007.3562052","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114910951","display_name":"Yifan Yang","orcid":"https://orcid.org/0000-0003-1455-2001"},"institutions":[{"id":"https://openalex.org/I4210144662","display_name":"Xi'an Institute of Optics and Precision Mechanics","ror":"https://ror.org/0444j5556","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210144662"]},{"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":"Yifan Yang","raw_affiliation_strings":["Key Laboratory of Spectral Imaging Technology CAS, Xi\u2019an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, China and University of Chinese Academy of Sciences, China","Key Laboratory of Spectral Imaging Technology CAS, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, China and University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Spectral Imaging Technology CAS, Xi\u2019an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, China and University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210144662","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Key Laboratory of Spectral Imaging Technology CAS, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, China and University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210144662","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018824735","display_name":"Xiaoqiang Lu","orcid":"https://orcid.org/0000-0002-7037-5188"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210144662","display_name":"Xi'an Institute of Optics and Precision Mechanics","ror":"https://ror.org/0444j5556","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210144662"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqiang Lu","raw_affiliation_strings":["Key Laboratory of Spectral Imaging Technology CAS, Xi\u2019an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, China","Key Laboratory of Spectral Imaging Technology CAS, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Spectral Imaging Technology CAS, Xi\u2019an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210144662","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Key Laboratory of Spectral Imaging Technology CAS, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210144662","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5114910951"],"corresponding_institution_ids":["https://openalex.org/I4210144662","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09494968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"235","last_page":"240"},"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":0.9993000030517578,"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":0.9962999820709229,"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":0.989646315574646},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.9173569679260254},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8143719434738159},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6314249634742737},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5865591764450073},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5668748021125793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5149460434913635},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5004186630249023},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4611945152282715},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4303007125854492},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.396502822637558},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.21086689829826355}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.989646315574646},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9173569679260254},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143719434738159},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6314249634742737},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5865591764450073},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5668748021125793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5149460434913635},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5004186630249023},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4611945152282715},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4303007125854492},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.396502822637558},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.21086689829826355},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3562007.3562052","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3562007.3562052","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3562007.3562052","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 3rd International Conference on Control, Robotics and Intelligent System","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3562007.3562052","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3562007.3562052","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3562007.3562052","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 3rd International Conference on Control, Robotics and Intelligent System","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4304755979.pdf","grobid_xml":"https://content.openalex.org/works/W4304755979.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1586939924","https://openalex.org/W1593271688","https://openalex.org/W1601567445","https://openalex.org/W1956340063","https://openalex.org/W2139501017","https://openalex.org/W2425121537","https://openalex.org/W2565656701","https://openalex.org/W2600463316","https://openalex.org/W2938603906","https://openalex.org/W2946086442","https://openalex.org/W2962681491","https://openalex.org/W2963224792","https://openalex.org/W2963524571","https://openalex.org/W2964118342","https://openalex.org/W2964896648","https://openalex.org/W2975813532","https://openalex.org/W2981750519","https://openalex.org/W3093309253","https://openalex.org/W3132101720"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2905433371","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W4323929292"],"abstract_inverted_index":{"The":[0],"task":[1],"of":[2,19,34,40,72,112],"video":[3,52,116],"captioning":[4,53,117],"is":[5,65,83],"to":[6,45,56,85],"generate":[7],"comprehensible":[8],"and":[9,92,104],"grammatically":[10],"correct":[11],"sentences":[12],"which":[13,67],"describe":[14],"the":[15,27,38,69,73,86,97,110],"main":[16],"visual":[17],"content":[18],"videos.":[20],"Existing":[21],"neural":[22,74,113],"modules":[23,42,75,114],"based":[24,76,115],"methods":[25,118],"improve":[26],"model":[28],"interpretability":[29],"by":[30],"separately":[31],"predicting":[32],"words":[33],"different":[35,41,94],"part-of-speech.":[36],"However,":[37],"separation":[39],"may":[43],"lead":[44],"confusing":[46],"semantics.":[47],"In":[48],"this":[49],"work,":[50],"a":[51],"method":[54,77],"referred":[55],"as":[57],"Differentiate":[58],"Visual":[59],"Features":[60],"with":[61],"Guidance":[62],"Signals":[63],"(DVFGS)":[64],"proposed,":[66],"enhances":[68],"semantic":[70],"consistency":[71],"through":[78],"guidance":[79],"signals.":[80],"This":[81],"process":[82],"similar":[84],"cell":[87],"differentiation":[88],"process,":[89],"producing":[90],"differences":[91],"having":[93],"effects":[95],"on":[96,102],"whole.":[98],"Extensive":[99],"experiments":[100],"performed":[101],"MSVD":[103],"MSR-VTT":[105],"show":[106],"that":[107],"DVFGS":[108],"pushes":[109],"limit":[111],"forward.":[119]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
