{"id":"https://openalex.org/W2605528234","doi":"https://doi.org/10.18653/v1/w17-2003","title":"Learning to Recognize Animals by Watching Documentaries: Using Subtitles as Weak Supervision","display_name":"Learning to Recognize Animals by Watching Documentaries: Using Subtitles as Weak Supervision","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2605528234","doi":"https://doi.org/10.18653/v1/w17-2003","mag":"2605528234"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-2003","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2003","pdf_url":"https://www.aclweb.org/anthology/W17-2003.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 Sixth Workshop on Vision and Language","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-2003.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078222309","display_name":"Aparna Nurani Venkitasubramanian","orcid":"https://orcid.org/0000-0002-2063-6773"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Aparna Nurani Venkitasubramanian","raw_affiliation_strings":["KU Leuven, Computer Science Department, Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven, Computer Science Department, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074816094","display_name":"Tinne Tuytelaars","orcid":"https://orcid.org/0000-0003-3307-9723"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]},{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Tinne Tuytelaars","raw_affiliation_strings":["KU Leuven, ESAT-PSI, IMEC, Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven, ESAT-PSI, IMEC, Belgium","institution_ids":["https://openalex.org/I4210114974","https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075796989","display_name":"Marie\u2010Francine Moens","orcid":"https://orcid.org/0000-0002-3732-9323"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Marie-Francine Moens","raw_affiliation_strings":["KU Leuven, Computer Science Department, Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven, Computer Science Department, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078222309"],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":0.091,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42910773,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976999759674072,"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":0.9976999759674072,"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":0.993399977684021,"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":0.9818999767303467,"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/computer-science","display_name":"Computer science","score":0.79668128490448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6657658815383911},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6405774354934692},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6157893538475037},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5245402455329895},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.49265366792678833},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.45829543471336365},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4412723183631897},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4283781945705414},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4233441948890686},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3597526550292969},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35926732420921326}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79668128490448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6657658815383911},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6405774354934692},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6157893538475037},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5245402455329895},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.49265366792678833},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.45829543471336365},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4412723183631897},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4283781945705414},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4233441948890686},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3597526550292969},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35926732420921326},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w17-2003","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2003","pdf_url":"https://www.aclweb.org/anthology/W17-2003.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 Sixth Workshop on Vision and Language","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/573537","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/573537","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"6th Workshop on Vision and Language (VL'17) at EACL 2016, Valencia, 4 April 2017","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-2003","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2003","pdf_url":"https://www.aclweb.org/anthology/W17-2003.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 Sixth Workshop on Vision and Language","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Life in Land","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2605528234.pdf","grobid_xml":"https://content.openalex.org/works/W2605528234.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1678889691","https://openalex.org/W1797268635","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1976543808","https://openalex.org/W2062118960","https://openalex.org/W2064477131","https://openalex.org/W2081580037","https://openalex.org/W2083209880","https://openalex.org/W2099444282","https://openalex.org/W2100500227","https://openalex.org/W2102605133","https://openalex.org/W2105148880","https://openalex.org/W2108598243","https://openalex.org/W2108881949","https://openalex.org/W2118585731","https://openalex.org/W2123053055","https://openalex.org/W2128862157","https://openalex.org/W2142900973","https://openalex.org/W2152942156","https://openalex.org/W2167090521","https://openalex.org/W2168996682","https://openalex.org/W2251512949","https://openalex.org/W2256642932","https://openalex.org/W2413342122","https://openalex.org/W2413367505","https://openalex.org/W2613718673","https://openalex.org/W2915312087","https://openalex.org/W2915431448","https://openalex.org/W2949769367","https://openalex.org/W2963173190","https://openalex.org/W2964298670","https://openalex.org/W3100609465","https://openalex.org/W4229979643","https://openalex.org/W4239072543","https://openalex.org/W4386506836"],"related_works":["https://openalex.org/W2130674020","https://openalex.org/W2093748878","https://openalex.org/W3183901164","https://openalex.org/W2951211570","https://openalex.org/W3176438653","https://openalex.org/W3135818718","https://openalex.org/W4290188444","https://openalex.org/W3003905048","https://openalex.org/W2253429366","https://openalex.org/W3127975138"],"abstract_inverted_index":{"We":[0,94],"investigate":[1,95],"animal":[2],"recognition":[3],"models":[4],"learned":[5],"from":[6],"wildlife":[7],"video":[8],"documentaries":[9],"by":[10],"using":[11],"the":[12,16,26,48,70,79,90,133,144],"weak":[13,54],"supervision":[14],"of":[15,109,111,132,151],"textual":[17,73],"subtitles.":[18],"This":[19,57,138],"is":[20,58,135],"a":[21,43,52,86,103,112,120,125,193],"challenging":[22],"setting,":[23],"since":[24],"i)":[25],"animals":[27],"occur":[28],"in":[29,59,69,85,101,143,149],"their":[30],"natural":[31],"habitat":[32],"and":[33,38,67,82,99,155,189],"are":[34,41,75,168],"often":[35,83],"largely":[36],"occluded":[37],"ii)":[39],"subtitles":[40],"to":[42,47,61,78,146,176],"great":[44],"degree":[45],"complementary":[46],"visual":[49],"content,":[50,81],"providing":[51],"very":[53],"supervisory":[55],"signal.":[56],"contrast":[60],"most":[62],"work":[63],"on":[64,107,124,171],"integrated":[65],"vision":[66],"language":[68],"literature,":[71],"where":[72,129],"descriptions":[74],"tightly":[76],"linked":[77],"image":[80,97,127,145,156,163],"generated":[84],"curated":[87],"fashion":[88],"for":[89],"task":[91],"at":[92],"hand.":[93],"different":[96,186],"representations":[98],"models,":[100],"particular":[102],"support":[104],"vector":[105],"machine":[106],"top":[108],"activations":[110],"pretrained":[113],"convolutional":[114],"neural":[115],"network,":[116],"as":[117,119],"well":[118,173],"Naive":[121],"Bayes":[122],"framework":[123],"'bag-of-activations'":[126],"representation,":[128],"each":[130],"element":[131],"bag":[134],"considered":[136],"separately.":[137],"representation":[139],"allows":[140],"key":[141],"components":[142],"be":[147],"isolated,":[148],"spite":[150],"vastly":[152],"varying":[153],"backgrounds":[154],"clutter,":[157],"without":[158],"an":[159],"object":[160],"detection":[161],"or":[162],"segmentation":[164],"step.":[165],"The":[166],"methods":[167],"evaluated":[169],"based":[170],"how":[172],"they":[174],"transfer":[175],"unseen":[177],"camera-trap":[178],"images":[179],"captured":[180],"across":[181],"diverse":[182],"topographical":[183],"regions":[184],"under":[185],"environmental":[187],"conditions":[188],"illumination":[190],"settings,":[191],"involving":[192],"large":[194],"domain":[195],"shift.":[196]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}