{"id":"https://openalex.org/W3003411605","doi":"https://doi.org/10.1109/iros40897.2019.8968118","title":"Analyzing Liquid Pouring Sequences via Audio-Visual Neural Networks","display_name":"Analyzing Liquid Pouring Sequences via Audio-Visual Neural Networks","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3003411605","doi":"https://doi.org/10.1109/iros40897.2019.8968118","mag":"3003411605"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8968118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102778571","display_name":"Justin Wilson","orcid":"https://orcid.org/0000-0003-2768-3799"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Wilson","raw_affiliation_strings":["UNC Chapel Hill,Department of Computer Science,Chapel Hill,NC,USA,27599","Department of Computer Science, UNC Chapel Hill, Chapel Hill, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill,Department of Computer Science,Chapel Hill,NC,USA,27599","institution_ids":["https://openalex.org/I114027177"]},{"raw_affiliation_string":"Department of Computer Science, UNC Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005996231","display_name":"Auston Sterling","orcid":"https://orcid.org/0000-0001-7897-7610"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Auston Sterling","raw_affiliation_strings":["UNC Chapel Hill,Department of Computer Science,Chapel Hill,NC,USA,27599","Department of Computer Science, UNC Chapel Hill, Chapel Hill, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill,Department of Computer Science,Chapel Hill,NC,USA,27599","institution_ids":["https://openalex.org/I114027177"]},{"raw_affiliation_string":"Department of Computer Science, UNC Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102878981","display_name":"Ming C. Lin","orcid":"https://orcid.org/0000-0003-3736-6949"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming C. Lin","raw_affiliation_strings":["UNC Chapel Hill,Department of Computer Science,Chapel Hill,NC,USA,27599","Department of Computer Science, UNC Chapel Hill, Chapel Hill, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill,Department of Computer Science,Chapel Hill,NC,USA,27599","institution_ids":["https://openalex.org/I114027177"]},{"raw_affiliation_string":"Department of Computer Science, UNC Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114027177"],"apc_list":null,"apc_paid":null,"fwci":2.6324,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91020831,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7702","last_page":"7709"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9936000108718872,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9793999791145325,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7642899751663208},{"id":"https://openalex.org/keywords/container","display_name":"Container (type theory)","score":0.6964629888534546},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6292448043823242},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6257315874099731},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.571580708026886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5354881882667542},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5289801359176636},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47677189111709595},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.45697885751724243},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4501035213470459},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37681931257247925},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3421770930290222},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12334403395652771},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.113107830286026}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7642899751663208},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.6964629888534546},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6292448043823242},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6257315874099731},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.571580708026886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5354881882667542},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5289801359176636},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47677189111709595},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.45697885751724243},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4501035213470459},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37681931257247925},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3421770930290222},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12334403395652771},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.113107830286026},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros40897.2019.8968118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W1522301498","https://openalex.org/W1559305623","https://openalex.org/W1592843886","https://openalex.org/W1844329104","https://openalex.org/W1854573962","https://openalex.org/W1974521191","https://openalex.org/W1982431017","https://openalex.org/W2003612239","https://openalex.org/W2024978593","https://openalex.org/W2043506339","https://openalex.org/W2044541909","https://openalex.org/W2044606382","https://openalex.org/W2064675550","https://openalex.org/W2076169683","https://openalex.org/W2081857580","https://openalex.org/W2099621636","https://openalex.org/W2104657103","https://openalex.org/W2122111042","https://openalex.org/W2125838338","https://openalex.org/W2132914434","https://openalex.org/W2140005305","https://openalex.org/W2143545157","https://openalex.org/W2147880316","https://openalex.org/W2149706766","https://openalex.org/W2163605009","https://openalex.org/W2170653751","https://openalex.org/W2296360731","https://openalex.org/W2464867595","https://openalex.org/W2481916066","https://openalex.org/W2519091744","https://openalex.org/W2529170537","https://openalex.org/W2550143307","https://openalex.org/W2564989727","https://openalex.org/W2579689856","https://openalex.org/W2641889749","https://openalex.org/W2742299865","https://openalex.org/W2775795276","https://openalex.org/W2792764867","https://openalex.org/W2886982406","https://openalex.org/W2895085622","https://openalex.org/W2899466959","https://openalex.org/W2949382160","https://openalex.org/W2952505264","https://openalex.org/W2962756039","https://openalex.org/W2963150162","https://openalex.org/W2964237810","https://openalex.org/W3016001898","https://openalex.org/W4235232193","https://openalex.org/W4236137412","https://openalex.org/W4243555565","https://openalex.org/W4251076369","https://openalex.org/W4285719527","https://openalex.org/W4293665662","https://openalex.org/W6633668799","https://openalex.org/W6682082992","https://openalex.org/W6684191040","https://openalex.org/W6729280921","https://openalex.org/W6729831399","https://openalex.org/W6740195615","https://openalex.org/W6747218270","https://openalex.org/W6749825310","https://openalex.org/W6755151086","https://openalex.org/W6816408058"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2942893872"],"abstract_inverted_index":{"Existing":[0],"work":[1],"to":[2,38,160],"estimate":[3,39],"the":[4,30,56,124,139,146,153],"weight":[5],"of":[6,32,72,123,148,156],"a":[7,11,59,66,95],"liquid":[8,47,62,162],"poured":[9,40,64],"into":[10,65,76],"target":[12,49,67],"container":[13],"often":[14],"require":[15],"predefined":[16],"source":[17],"weights":[18],"or":[19,109],"visual":[20,88],"data.":[21],"We":[22],"present":[23],"novel":[24],"audio-based":[25,52],"and":[26,45,48,97,121,136,170],"audio-augmented":[27,80],"techniques,":[28],"in":[29,105],"form":[31],"multimodal":[33],"convolutional":[34],"neural":[35,53,158],"networks":[36,159],"(CNNs),":[37],"weight,":[41,168],"perform":[42],"overflow":[43],"detection,":[44],"classify":[46],"container.":[50,68,172],"Our":[51,79,112,128],"network":[54,81],"uses":[55],"sound":[57],"from":[58],"pouring":[60,126,163],"sequence-a":[61],"being":[63],"Audio":[69],"inputs":[70],"consist":[71],"converting":[73],"raw":[74],"audio":[75,84],"mel-scaled":[77],"spectrograms.":[78],"fuses":[82],"this":[83,151],"with":[85],"its":[86],"corresponding":[87],"data":[89],"based":[90],"on":[91],"video":[92],"images.":[93],"Only":[94],"microphone":[96],"camera":[98],"are":[99,134],"required,":[100],"which":[101],"can":[102],"be":[103],"found":[104],"any":[106],"modern":[107],"smartphone":[108],"Microsoft":[110],"Kinect.":[111],"approach":[113],"improves":[114],"classification":[115],"accuracy":[116],"for":[117],"different":[118],"environments,":[119],"containers,":[120],"contents":[122],"robot":[125],"task.":[127],"Pouring":[129],"Sequence":[130],"Neural":[131],"Networks":[132],"(PSNN)":[133],"trained":[135],"tested":[137],"using":[138],"Rethink":[140],"Robotics":[141],"Baxter":[142],"Research":[143],"Robot.":[144],"To":[145],"best":[147],"our":[149],"knowledge,":[150],"is":[152],"first":[154],"use":[155],"audio-visual":[157],"analyze":[161],"sequences":[164],"by":[165],"classifying":[166],"their":[167],"liquid,":[169],"receiving":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}