{"id":"https://openalex.org/W2949190893","doi":"https://doi.org/10.48550/arxiv.1612.07360","title":"Top-down Visual Saliency Guided by Captions","display_name":"Top-down Visual Saliency Guided by Captions","publication_year":2016,"publication_date":"2016-12-21","ids":{"openalex":"https://openalex.org/W2949190893","doi":"https://doi.org/10.48550/arxiv.1612.07360","mag":"2949190893"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1612.07360","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.07360","pdf_url":"https://arxiv.org/pdf/1612.07360","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1612.07360","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001707003","display_name":"Vasili Ramanishka","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramanishka, Vasili","raw_affiliation_strings":["Boston University","Boston Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Boston Univ","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101751934","display_name":"Abir Das","orcid":"https://orcid.org/0000-0002-2327-1618","observed_orcids":["https://orcid.org/0000-0002-2327-1618"]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Das, Abir","raw_affiliation_strings":["Boston University","Boston Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Boston Univ","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036510129","display_name":"Jianming Zhang","orcid":"https://orcid.org/0000-0002-9954-6294","observed_orcids":["https://orcid.org/0000-0002-9954-6294"]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Jianming","raw_affiliation_strings":["Adobe Research","Adobe Research#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"Adobe Research#TAB#","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075906727","display_name":"Kate Saenko","orcid":"https://orcid.org/0000-0002-7564-7218","observed_orcids":["https://orcid.org/0000-0002-7564-7218","https://orcid.org/0000-0002-5704-7614"]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saenko, Kate","raw_affiliation_strings":["Boston University","Boston Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Boston Univ","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9940999746322632,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9940999746322632,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.00570000009611249,"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/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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/image-captioning","display_name":"image captioning","score":0.7699999809265137},{"id":"https://openalex.org/keywords/video-captioning","display_name":"video captioning","score":0.7360000014305115},{"id":"https://openalex.org/keywords/encoder-decoder-architecture","display_name":"encoder-decoder architecture","score":0.7279999852180481},{"id":"https://openalex.org/keywords/model-interpretability","display_name":"model interpretability","score":0.6420000195503235}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9361481070518494},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8841439485549927},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6534783840179443},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6349799633026123},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5806558132171631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5385004878044128},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5318581461906433},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5240780711174011},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5117533206939697},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5065258741378784},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5002412796020508},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48637154698371887},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41124364733695984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3274173140525818},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1612.07360","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.07360","pdf_url":"https://arxiv.org/pdf/1612.07360","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":"mag:2949190893","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1612.07360","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1612.07360","doi":"https://doi.org/10.48550/arxiv.1612.07360","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1612.07360","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":"pmh:oai:arXiv.org:1612.07360","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.07360","pdf_url":"https://arxiv.org/pdf/1612.07360","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G636252579","display_name":"RI: Large: Collaborative Research: Reconstructive recognition: Uniting statistical scene understanding and physics-based visual reasoning","funder_award_id":"1212928","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2949190893.pdf","grobid_xml":"https://content.openalex.org/works/W2949190893.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1849277567","https://openalex.org/W1895989618","https://openalex.org/W1951216520","https://openalex.org/W2108598243","https://openalex.org/W2123301721","https://openalex.org/W2130942839","https://openalex.org/W2133459682","https://openalex.org/W2133564696","https://openalex.org/W2136036867","https://openalex.org/W2164290393","https://openalex.org/W2169393322","https://openalex.org/W2185175083","https://openalex.org/W2221625691","https://openalex.org/W2295107390","https://openalex.org/W2425121537","https://openalex.org/W2528777330","https://openalex.org/W2949605076","https://openalex.org/W2949844032","https://openalex.org/W2949987032","https://openalex.org/W2950019618","https://openalex.org/W2950179405","https://openalex.org/W2950307714","https://openalex.org/W2950635152","https://openalex.org/W2951805548","https://openalex.org/W2951912364","https://openalex.org/W2963109634","https://openalex.org/W2963630207","https://openalex.org/W2963735856","https://openalex.org/W2963758027","https://openalex.org/W3098232790"],"related_works":["https://openalex.org/W2891752192","https://openalex.org/W2751076261","https://openalex.org/W2607818926","https://openalex.org/W2962982762","https://openalex.org/W2734241621","https://openalex.org/W2962938439","https://openalex.org/W4293518823","https://openalex.org/W2896897397","https://openalex.org/W4409367151","https://openalex.org/W2753232960"],"abstract_inverted_index":{"Neural":[0],"image/video":[1],"captioning":[2,146],"models":[3],"can":[4,30,91,118],"generate":[5],"accurate":[6,154],"descriptions,":[7],"but":[8,43],"their":[9,131],"internal":[10],"process":[11],"of":[12,112,125],"mapping":[13,69],"regions":[14,33],"to":[15,24,65,121],"words":[16],"is":[17,78,159],"a":[18,35,46,123],"black":[19],"box":[20],"and":[21,74,101,117,129,137],"therefore":[22],"difficult":[23],"explain.":[25],"Top-down":[26],"neural":[27],"saliency":[28,108,155],"methods":[29,150],"find":[31],"important":[32],"given":[34],"high-level":[36],"semantic":[37],"task":[38],"such":[39],"as":[40,50],"object":[41],"classification,":[42],"cannot":[44],"use":[45],"natural":[47],"language":[48],"sentence":[49],"the":[51,55,67,110],"top-down":[52],"input":[53],"for":[54,97,102],"task.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60],"propose":[61],"Caption-Guided":[62],"Visual":[63],"Saliency":[64],"expose":[66],"region-to-word":[68],"in":[70],"modern":[71],"encoder-decoder":[72],"networks":[73],"demonstrate":[75],"that":[76,141],"it":[77],"learned":[79],"implicitly":[80],"from":[81],"caption":[82],"training":[83],"data,":[84],"without":[85,109],"any":[86],"pixel-level":[87],"annotations.":[88],"Our":[89,157],"approach":[90,143],"produce":[92],"spatial":[93],"or":[94],"spatiotemporal":[95],"heatmaps":[96],"both":[98],"predicted":[99],"captions,":[100],"arbitrary":[103],"query":[104],"sentences.":[105],"It":[106],"recovers":[107],"overhead":[111],"introducing":[113],"explicit":[114],"attention":[115],"layers,":[116],"be":[119],"used":[120],"analyze":[122],"variety":[124],"existing":[126,149],"model":[127],"architectures":[128],"improve":[130],"design.":[132],"Evaluation":[133],"on":[134],"large-scale":[135],"video":[136],"image":[138],"datasets":[139],"demonstrates":[140],"our":[142],"achieves":[144],"comparable":[145],"performance":[147],"with":[148],"while":[151],"providing":[152],"more":[153],"heatmaps.":[156],"code":[158],"available":[160],"at":[161],"visionlearninggroup.github.io/caption-guided-saliency/.":[162]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2019-06-27T00:00:00"}