{"id":"https://openalex.org/W2963521717","doi":"https://doi.org/10.18653/v1/p19-1183","title":"Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video","display_name":"Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2963521717","doi":"https://doi.org/10.18653/v1/p19-1183","mag":"2963521717"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1183","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1183","pdf_url":"https://www.aclweb.org/anthology/P19-1183.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1183.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064272059","display_name":"Zhenfang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Zhenfang Chen","raw_affiliation_strings":["The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017116858","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0002-7331-6132"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004450394","display_name":"Wenhan Luo","orcid":"https://orcid.org/0000-0002-5697-4168"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhan Luo","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109582975","display_name":"Kenneth K. Wong","orcid":"https://orcid.org/0000-0001-8560-9007"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kwan-Yee Kenneth Wong","raw_affiliation_strings":["The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064272059"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":5.8207,"has_fulltext":true,"cited_by_count":104,"citation_normalized_percentile":{"value":0.96914996,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1884","last_page":"1894"},"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":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/sentence","display_name":"Sentence","score":0.8086603879928589},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7644373178482056},{"id":"https://openalex.org/keywords/interactor","display_name":"Interactor","score":0.7064563035964966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.633995771408081},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5773878693580627},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5470075607299805},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5385236740112305},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5168807506561279},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5162355899810791},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4671000838279724},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44188937544822693},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43835148215293884},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3913334906101227},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3866526484489441},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07036235928535461}],"concepts":[{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.8086603879928589},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7644373178482056},{"id":"https://openalex.org/C166998942","wikidata":"https://www.wikidata.org/wiki/Q16969238","display_name":"Interactor","level":2,"score":0.7064563035964966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.633995771408081},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5773878693580627},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5470075607299805},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5385236740112305},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5168807506561279},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5162355899810791},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4671000838279724},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44188937544822693},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43835148215293884},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3913334906101227},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3866526484489441},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07036235928535461},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1183","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1183","pdf_url":"https://www.aclweb.org/anthology/P19-1183.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1183","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1183","pdf_url":"https://www.aclweb.org/anthology/P19-1183.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963521717.pdf","grobid_xml":"https://content.openalex.org/works/W2963521717.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1916445035","https://openalex.org/W1923162067","https://openalex.org/W1923332106","https://openalex.org/W1995820507","https://openalex.org/W2048343491","https://openalex.org/W2049705550","https://openalex.org/W2064675550","https://openalex.org/W2111078031","https://openalex.org/W2117539524","https://openalex.org/W2153579005","https://openalex.org/W2222764656","https://openalex.org/W2520141964","https://openalex.org/W2571175805","https://openalex.org/W2604260814","https://openalex.org/W2605585413","https://openalex.org/W2606594151","https://openalex.org/W2606746036","https://openalex.org/W2613718673","https://openalex.org/W2620629206","https://openalex.org/W2767014100","https://openalex.org/W2788810331","https://openalex.org/W2798708692","https://openalex.org/W2798990097","https://openalex.org/W2803088946","https://openalex.org/W2813911573","https://openalex.org/W2890502146","https://openalex.org/W2903901502","https://openalex.org/W2904164128","https://openalex.org/W2949559657","https://openalex.org/W2950438040","https://openalex.org/W2962681491","https://openalex.org/W2962700105","https://openalex.org/W2962703144","https://openalex.org/W2962764817","https://openalex.org/W2962799512","https://openalex.org/W2962870068","https://openalex.org/W2962949233","https://openalex.org/W2963042258","https://openalex.org/W2963389687","https://openalex.org/W2963445828","https://openalex.org/W2963524571","https://openalex.org/W2963672682","https://openalex.org/W2963735856","https://openalex.org/W2963843782","https://openalex.org/W2964345792","https://openalex.org/W3098232790","https://openalex.org/W4289126595","https://openalex.org/W4294170691","https://openalex.org/W4297500590","https://openalex.org/W4300614726","https://openalex.org/W4300917784"],"related_works":["https://openalex.org/W2331011004","https://openalex.org/W2327979883","https://openalex.org/W2325169325","https://openalex.org/W183699606","https://openalex.org/W2126505405","https://openalex.org/W2746007138","https://openalex.org/W2370286462","https://openalex.org/W2150948843","https://openalex.org/W1555983178","https://openalex.org/W2184228381"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,24,118],"address":[4],"a":[5,18,22,26,49,88,91,121,136],"novel":[6,92],"task,":[7],"namely":[8],"weakly-supervised":[9],"spatio-temporally":[10],"grounding":[11],"natural":[12,19],"sentence":[13,20,70],"in":[14,29],"video.":[15,62],"Specifically,":[16],"given":[17,37],"and":[21,68,112,156],"video,":[23],"localize":[25],"spatio-temporal":[27,44],"tube":[28],"the":[30,36,61,69,99,105,114,127,145,151,157],"video":[31,129],"that":[32],"semantically":[33],"corresponds":[34],"to":[35,55,82,97,103,133],"sentence,":[38],"with":[39],"no":[40],"reliance":[41],"on":[42,126],"any":[43],"annotations":[45],"during":[46],"training.":[47],"First,":[48],"set":[50],"of":[51,108,147],"spatiotemporal":[52],"tubes,":[53],"referred":[54],"as":[56,135],"instances,":[57],"are":[58,161],"extracted":[59],"from":[60],"We":[63],"then":[64],"encode":[65],"these":[66],"instances":[67],"using":[71],"our":[72,139,148],"proposed":[73,100],"attentive":[74,101],"interactor":[75,102],"which":[76],"can":[77],"exploit":[78],"their":[79,84],"fine-grained":[80],"relationships":[81],"characterize":[83],"matching":[85,106],"behaviors.":[86],"Besides":[87],"ranking":[89],"loss,":[90],"diversity":[93],"loss":[94],"is":[95],"introduced":[96],"train":[98],"strengthen":[104],"behaviors":[107],"reliable":[109],"instance-sentence":[110],"pairs":[111],"penalize":[113],"unreliable":[115],"ones.":[116],"Moreover,":[117],"also":[119],"contribute":[120],"dataset,":[122,132],"called":[123],"VID-sentence,":[124],"based":[125],"Im-ageNet":[128],"object":[130],"detection":[131],"serve":[134],"benchmark":[137],"for":[138],"task.":[140],"Extensive":[141],"experimental":[142],"results":[143],"demonstrate":[144],"superiority":[146],"model":[149],"over":[150],"baseline":[152],"approaches.":[153],"Our":[154],"code":[155],"constructed":[158],"VID-sentence":[159],"dataset":[160],"available":[162],"at:":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}