{"id":"https://openalex.org/W2963389277","doi":"https://doi.org/10.1609/aaai.v32i1.12289","title":"Self-View Grounding Given a Narrated 360\u00b0 Video","display_name":"Self-View Grounding Given a Narrated 360\u00b0 Video","publication_year":2018,"publication_date":"2018-04-27","ids":{"openalex":"https://openalex.org/W2963389277","doi":"https://doi.org/10.1609/aaai.v32i1.12289","mag":"2963389277"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v32i1.12289","doi":"https://doi.org/10.1609/aaai.v32i1.12289","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v32i1.12289","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v32i1.12289","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054796285","display_name":"Shih-Han Chou","orcid":"https://orcid.org/0000-0003-1163-5063","observed_orcids":["https://orcid.org/0000-0003-1163-5063"]},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shih-Han Chou","raw_affiliation_strings":["National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459613","display_name":"Yi\u2010Chun Chen","orcid":"https://orcid.org/0000-0002-5205-4006","observed_orcids":["https://orcid.org/0000-0002-5205-4006"]},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Chun Chen","raw_affiliation_strings":["National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017651065","display_name":"Kuo-Hao Zeng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuo-Hao Zeng","raw_affiliation_strings":["National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101453875","display_name":"Hou-Ning Hu","orcid":"https://orcid.org/0000-0002-7564-1473","observed_orcids":["https://orcid.org/0000-0002-7564-1473"]},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hou-Ning Hu","raw_affiliation_strings":["National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072029041","display_name":"Jianlong Fu","orcid":"https://orcid.org/0000-0002-1025-2012","observed_orcids":["https://orcid.org/0000-0002-1025-2012"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianlong Fu","raw_affiliation_strings":["Microsoft Research, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102008600","display_name":"Min Sun","orcid":"https://orcid.org/0000-0001-9598-8178","observed_orcids":["https://orcid.org/0000-0001-9598-8178","https://orcid.org/0000-0001-8766-1140","https://orcid.org/0000-0002-0336-4446"]},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Min Sun","raw_affiliation_strings":["National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8074,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.837887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"32","issue":"1","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":0.9639000296592712,"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":0.9639000296592712,"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":0.017500000074505806,"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":0.00279999990016222,"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/360-degree-video","display_name":"360-degree video","score":0.8669999837875366},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.7200000286102295},{"id":"https://openalex.org/keywords/visual-guidance","display_name":"visual guidance","score":0.3790000081062317},{"id":"https://openalex.org/keywords/soft-attention","display_name":"soft attention","score":0.7710000276565552},{"id":"https://openalex.org/keywords/sentence-generation","display_name":"sentence generation","score":0.3630000054836273}],"concepts":[{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.8284152150154114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7967567443847656},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6685538291931152},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6139774918556213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5428095459938049},{"id":"https://openalex.org/C2780580889","wikidata":"https://www.wikidata.org/wiki/Q41363","display_name":"Panorama","level":2,"score":0.5280460119247437},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5015037059783936},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.49902844429016113},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4579147398471832},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.4493579566478729},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4166862964630127},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4135389029979706},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.363442599773407},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0849086344242096},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v32i1.12289","doi":"https://doi.org/10.1609/aaai.v32i1.12289","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v32i1.12289","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1711.08664","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.08664","pdf_url":"https://arxiv.org/pdf/1711.08664","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ojs.aaai.org:article/12289","doi":null,"is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/12289","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/12289/12148","source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.1711.08664","doi":"https://doi.org/10.48550/arxiv.1711.08664","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1711.08664","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1609/aaai.v32i1.12289","doi":"https://doi.org/10.1609/aaai.v32i1.12289","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v32i1.12289","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6010651588","display_name":"Smartpano: Intelligent Panormaic Vi Deo Editing, Synthesis, and Its Novel Applications( I )","funder_award_id":"MOST106-3114-E007-008","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"},{"id":"https://openalex.org/G927507832","display_name":"Assistive 360 Vi Deo and Assistive Vi Rtual Reality","funder_award_id":"MOST106-2221-E007-107","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320322410","display_name":"MediaTek","ror":"https://ror.org/05g9jck81"},{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"},{"id":"https://openalex.org/F4320333993","display_name":"Microsoft Research Asia","ror":"https://ror.org/0300m5276"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963389277.pdf","grobid_xml":"https://content.openalex.org/works/W2963389277.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1510835000","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1802459088","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1924770834","https://openalex.org/W2062400178","https://openalex.org/W2064675550","https://openalex.org/W2077069816","https://openalex.org/W2086842362","https://openalex.org/W2105081120","https://openalex.org/W2108598243","https://openalex.org/W2112912048","https://openalex.org/W2136668269","https://openalex.org/W2136985729","https://openalex.org/W2150417956","https://openalex.org/W2194775991","https://openalex.org/W2247513039","https://openalex.org/W2250539671","https://openalex.org/W2295415742","https://openalex.org/W2436270489","https://openalex.org/W2479344183","https://openalex.org/W2559818034","https://openalex.org/W2593745480","https://openalex.org/W2606746036","https://openalex.org/W2611836059","https://openalex.org/W2734518663","https://openalex.org/W2747053578","https://openalex.org/W2747107070","https://openalex.org/W2963042258","https://openalex.org/W2963109634","https://openalex.org/W2963339238","https://openalex.org/W2963389687","https://openalex.org/W2963735856","https://openalex.org/W2964121744","https://openalex.org/W2964335490","https://openalex.org/W3023993913","https://openalex.org/W6753449277"],"related_works":["https://openalex.org/W2949410299","https://openalex.org/W2957912435","https://openalex.org/W4281761498","https://openalex.org/W4226439695","https://openalex.org/W2885054293","https://openalex.org/W7160036654","https://openalex.org/W4390871893","https://openalex.org/W2565955132","https://openalex.org/W4214604251","https://openalex.org/W4366966801"],"abstract_inverted_index":{"Narrated":[0],"360\u00b0":[1,53,230],"videos":[2,231],"are":[3],"typically":[4],"provided":[5],"in":[6],"many":[7],"touring":[8],"scenarios":[9],"to":[10,30,39,61,72,109,129,134,188,202,209,214],"mimic":[11],"real-world":[12],"experience.":[13],"However,":[14],"previous":[15],"work":[16],"has":[17],"shown":[18],"that":[19,179],"smart":[20],"assistance":[21],"(i.e.,":[22],"providing":[23],"visual":[24],"guidance)":[25],"can":[26],"significantly":[27],"help":[28],"users":[29],"follow":[31],"the":[32,40,49,58,77,80,92,107,110,136,140,148,151,155,176,180,189,198,211,218,227],"Normal":[33],"Field":[34],"of":[35,51,57,97,197],"View":[36],"(NFoV)":[37],"corresponding":[38],"narrative.In":[41],"this":[42],"project,":[43],"we":[44,89,123,146,166,225],"aim":[45],"at":[46,86],"automatically":[47],"grounding":[48],"NFoVs":[50,78,99,128,185],"a":[52,66,101,169],"video":[54,81],"given":[55,79,143,190,219],"subtitles":[56,108],"narrative":[59],"(referred":[60,201],"as":[62,150,203],"''NFoV-grounding\").":[63],"We":[64],"propose":[65],"novel":[67],"Visual":[68],"Grounding":[69],"Model":[70],"(VGM)":[71],"implicitly":[73],"and":[74,83,106,142,233],"efficiently":[75,90],"predict":[76],"content":[82],"subtitles.":[84],"Specifically,":[85],"each":[87],"frame,":[88],"encode":[91],"panorama":[93],"into":[94],"feature":[95],"map":[96],"candidate":[98,127,152,184],"using":[100,114],"Convolutional":[102],"Neural":[103],"Network":[104],"(CNN)":[105],"same":[111],"hidden":[112],"space":[113],"an":[115],"RNN":[116],"with":[117,154],"Gated":[118],"Recurrent":[119],"Units":[120],"(GRU).":[121],"Then,":[122],"apply":[124],"soft-attention":[125,177],"on":[126,173,183],"trigger":[130],"sentence":[131,171,200,213],"decoder":[132],"aiming":[133],"minimize":[135],"reconstruct":[137],"loss":[138,196],"between":[139],"generated":[141],"sentence.":[144,191,220],"Finally,":[145],"obtain":[147],"NFoV":[149,153],"maximum":[156],"attention":[157,181],"without":[158],"any":[159],"human":[160],"supervision.To":[161],"train":[162],"VGM":[163],"more":[164],"robustly,":[165],"also":[167],"generate":[168],"reverse":[170,199,212],"conditioning":[172],"one":[174],"minus":[175],"such":[178],"focuses":[182],"less":[186],"relevant":[187],"The":[192],"negative":[193],"log":[194],"reconstruction":[195],"''irrelevant":[204],"loss\")":[205],"is":[206],"jointly":[207],"minimized":[208],"encourage":[210],"be":[215],"different":[216],"from":[217],"To":[221],"evaluate":[222],"our":[223],"method,":[224],"collect":[226],"first":[228],"narrated":[229],"dataset":[232],"achieve":[234],"state-of-the-art":[235],"NFoV-grounding":[236],"performance.":[237]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2019-07-30T00:00:00"}