{"id":"https://openalex.org/W2970679379","doi":"https://doi.org/10.1109/icip.2019.8803153","title":"Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions","display_name":"Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions","publication_year":2019,"publication_date":"2019-08-26","ids":{"openalex":"https://openalex.org/W2970679379","doi":"https://doi.org/10.1109/icip.2019.8803153","mag":"2970679379"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2019.8803153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2019.8803153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1902.01078","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Alexandros Stergiou","orcid":null},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Alexandros Stergiou","raw_affiliation_strings":["Utrecht University, Utrecht, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Utrecht University, Utrecht, Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Georgios Kapidis","orcid":null},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Georgios Kapidis","raw_affiliation_strings":["Utrecht University, Utrecht, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Utrecht University, Utrecht, Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Grigorios Kalliatakis","orcid":null},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Grigorios Kalliatakis","raw_affiliation_strings":["University of Essex, Colchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Essex, Colchester, UK","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Christos Chrysoulas","orcid":null},"institutions":[{"id":"https://openalex.org/I28257850","display_name":"London South Bank University","ror":"https://ror.org/02vwnat91","country_code":"GB","type":"education","lineage":["https://openalex.org/I28257850"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christos Chrysoulas","raw_affiliation_strings":["London South Bank University, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"London South Bank University, London, UK","institution_ids":["https://openalex.org/I28257850"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Remco Veltkamp","orcid":null},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Remco Veltkamp","raw_affiliation_strings":["Utrecht University, Utrecht, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Utrecht University, Utrecht, Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ronald Poppe","orcid":null},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ronald Poppe","raw_affiliation_strings":["Utrecht University, Utrecht, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Utrecht University, Utrecht, Netherlands","institution_ids":["https://openalex.org/I193662353"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6861,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.87851182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1830","last_page":"1834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9983000159263611,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9983000159263611,"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":0.9976999759674072,"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/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.960099995136261,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6559000015258789},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6474999785423279},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6111000180244446},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.60589998960495},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5827999711036682},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4957999885082245},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4675999879837036},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4327000081539154},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4253000020980835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6923999786376953},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6559000015258789},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6474999785423279},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6111000180244446},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.60589998960495},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5827999711036682},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4957999885082245},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4675999879837036},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41990000009536743},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3747999966144562},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3601999878883362},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3425000011920929},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.27079999446868896},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25519999861717224}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icip.2019.8803153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2019.8803153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1902.01078","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.01078","pdf_url":"https://arxiv.org/pdf/1902.01078","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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:napier-surface.worktribe.com:2548328","is_oa":false,"landing_page_url":"http://researchrepository.napier.ac.uk/Output/2548328","pdf_url":null,"source":{"id":"https://openalex.org/S4306400544","display_name":"Research Output (Edinburgh Napier University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I251738","host_organization_name":"Edinburgh Napier University","host_organization_lineage":["https://openalex.org/I251738"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:166028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ICIP.2019.8803153","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"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":"article"},{"id":"pmh:uu:oai:dspace.library.uu.nl:1874/427778","is_oa":true,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/427778","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the IEEE International Conference on Image Processing (ICIP), 1830. IEEE","raw_type":"info:eu-repo/semantics/bookpart"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1902.01078","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.01078","pdf_url":"https://arxiv.org/pdf/1902.01078","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1915485278","https://openalex.org/W1923332106","https://openalex.org/W2102605133","https://openalex.org/W2194775991","https://openalex.org/W2282821441","https://openalex.org/W2295107390","https://openalex.org/W2657631929","https://openalex.org/W2765793020","https://openalex.org/W2776207810","https://openalex.org/W2962858109","https://openalex.org/W2963371637","https://openalex.org/W2963524571","https://openalex.org/W2963749936","https://openalex.org/W2963989815","https://openalex.org/W6600983433","https://openalex.org/W6638389677","https://openalex.org/W6639204139","https://openalex.org/W6639432524","https://openalex.org/W6639927594","https://openalex.org/W6640820311","https://openalex.org/W6682864246","https://openalex.org/W6684191040","https://openalex.org/W6724944384","https://openalex.org/W6735944810","https://openalex.org/W6742162214","https://openalex.org/W6749916090","https://openalex.org/W6753049748","https://openalex.org/W6753057791"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"learning":[1],"approaches":[2],"have":[3,18],"been":[4,19],"established":[5],"as":[6,40,58,70],"the":[7,32,41,64,67,81,88,92,95,109,126,131,149],"main":[8,127],"methodology":[9],"for":[10,63,141],"video":[11,28,93,171],"classification":[12,146],"and":[13,112,118,143,147,153,168],"recognition.":[14],"Recently,":[15],"3-dimensional":[16],"convolutions":[17],"used":[20,139],"to":[21,47,53,86,124],"achieve":[22],"state-of-the-art":[23],"performance":[24],"in":[25,51,114],"many":[26],"challenging":[27,74],"datasets.":[29],"Because":[30],"of":[31,35,37,79,130,151],"high":[33],"level":[34,117],"complexity":[36],"these":[38],"methods,":[39],"convolution":[42],"operations":[43],"are":[44,122,175],"also":[45,176],"extended":[46],"an":[48],"additional":[49],"dimension":[50],"order":[52],"extract":[54],"features":[55],"from":[56],"it":[57],"well,":[59],"providing":[60],"a":[61,73,102,169],"visualization":[62],"signals":[65],"that":[66,94,121,155],"network":[68,96],"interpret":[69],"informative,":[71],"is":[72],"task.":[75],"An":[76],"effective":[77],"notion":[78],"understanding":[80],"network's":[82],"innerworkings":[83],"would":[84],"be":[85,125],"isolate":[87],"spatio-temporal":[89],"regions":[90,113],"on":[91,137],"finds":[97],"most":[98],"informative.":[99],"We":[100,133],"propose":[101],"method":[103],"called":[104],"Saliency":[105],"Tubes":[106],"which":[107],"demonstrate":[108,134],"foremost":[110],"points":[111,129],"both":[115],"frame":[116],"over":[119],"time":[120],"found":[123],"focus":[128],"network.":[132],"our":[135],"findings":[136],"widely":[138],"datasets":[140],"thirdperson":[142],"egocentric":[144],"action":[145],"enhance":[148],"set":[150],"methods":[152],"visualizations":[154],"improve":[156],"3D":[157],"Convolutional":[158],"Neural":[159],"Networks":[160],"(CNNs)":[161],"intelligibility.":[162],"Our":[163],"code":[164],"<sup":[165,172],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[166,173],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[167],"demo":[170],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[174],"available.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2019-09-05T00:00:00"}