{"id":"https://openalex.org/W3009398916","doi":"https://doi.org/10.1109/wacv45572.2020.9093410","title":"Representing Objects in Video as Space-Time Volumes by Combining Top-Down and Bottom-Up Processes","display_name":"Representing Objects in Video as Space-Time Volumes by Combining Top-Down and Bottom-Up Processes","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3009398916","doi":"https://doi.org/10.1109/wacv45572.2020.9093410","mag":"3009398916"},"language":"en","primary_location":{"id":"doi:10.1109/wacv45572.2020.9093410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085362771","display_name":"Filip Ilic","orcid":null},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Filip Ilic","raw_affiliation_strings":["Graz University of Technology"],"affiliations":[{"raw_affiliation_string":"Graz University of Technology","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034013413","display_name":"Axel Pinz","orcid":"https://orcid.org/0000-0001-7914-619X"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Axel Pinz","raw_affiliation_strings":["Graz University of Technology"],"affiliations":[{"raw_affiliation_string":"Graz University of Technology","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085362771"],"corresponding_institution_ids":["https://openalex.org/I4092182"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01740942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1903","last_page":"1911"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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":0.9998000264167786,"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/T10331","display_name":"Video Surveillance and Tracking Methods","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7263115048408508},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6529367566108704},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5910516977310181},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5880475044250488},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5689851641654968},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5635426044464111},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.48999062180519104},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4619567394256592},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4315785765647888},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4306311011314392},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.42827683687210083},{"id":"https://openalex.org/keywords/scale-space","display_name":"Scale space","score":0.4115699529647827},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36495834589004517},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14922964572906494},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11951708793640137},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.11254844069480896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7263115048408508},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6529367566108704},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5910516977310181},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5880475044250488},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5689851641654968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5635426044464111},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.48999062180519104},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4619567394256592},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4315785765647888},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4306311011314392},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.42827683687210083},{"id":"https://openalex.org/C99102927","wikidata":"https://www.wikidata.org/wiki/Q3058184","display_name":"Scale space","level":4,"score":0.4115699529647827},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36495834589004517},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14922964572906494},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11951708793640137},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.11254844069480896},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv45572.2020.9093410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1907877624","https://openalex.org/W1955404912","https://openalex.org/W2020163092","https://openalex.org/W2031489346","https://openalex.org/W2081432165","https://openalex.org/W2096979710","https://openalex.org/W2104125540","https://openalex.org/W2112328181","https://openalex.org/W2118246710","https://openalex.org/W2119799051","https://openalex.org/W2119823327","https://openalex.org/W2128715362","https://openalex.org/W2138682569","https://openalex.org/W2146634731","https://openalex.org/W2342662179","https://openalex.org/W2466029529","https://openalex.org/W2470139095","https://openalex.org/W2470394683","https://openalex.org/W2560474170","https://openalex.org/W2613718673","https://openalex.org/W2799058067","https://openalex.org/W2889986507","https://openalex.org/W2892083345","https://openalex.org/W2914242123","https://openalex.org/W2962855257","https://openalex.org/W2963150697","https://openalex.org/W2963227409","https://openalex.org/W2965101223","https://openalex.org/W3023013923","https://openalex.org/W3098012555","https://openalex.org/W6620707391","https://openalex.org/W6639102338","https://openalex.org/W6670927870","https://openalex.org/W6720898849","https://openalex.org/W6758503643","https://openalex.org/W6766093832"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W1978572805","https://openalex.org/W2383807498","https://openalex.org/W2130974462","https://openalex.org/W1997992934","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W100433498"],"abstract_inverted_index":{"As":[0],"top-down":[1],"based":[2],"approaches":[3],"of":[4,79,105],"object":[5,53,107,114,130,141,165],"recognition":[6],"from":[7],"video":[8,129],"are":[9],"getting":[10],"more":[11],"powerful,":[12],"a":[13,47,51,63,127,154],"structured":[14],"way":[15],"to":[16,33,55,68,99],"combine":[17],"them":[18],"with":[19,138],"bottom-up":[20,91],"grouping":[21],"processes":[22],"becomes":[23],"feasible.":[24],"When":[25],"done":[26],"right,":[27],"the":[28,103,179],"resulting":[29,94],"representation":[30,96,169],"is":[31,119],"able":[32],"describe":[34],"objects":[35],"and":[36,62,101],"their":[37],"decomposition":[38,104],"into":[39,108],"parts":[40,110,180],"at":[41,178],"appropriate":[42],"spatio-temporal":[43,85],"scales.":[44],"We":[45],"propose":[46],"method":[48,161],"that":[49,89,159,173],"uses":[50],"modern":[52],"detector":[54],"focus":[56],"on":[57,126,150],"salient":[58],"structures":[59,74],"in":[60,84],"video,":[61],"dense":[64],"optical":[65],"flow":[66],"estimator":[67],"supplement":[69],"feature":[70],"extraction.":[71],"From":[72],"these":[73],"we":[75,122,134,152],"extract":[76],"space-time":[77,176],"volumes":[78],"interest":[80],"(STVIs)":[81],"by":[82,157],"smoothing":[83],"Gaussian":[86],"Scale":[87],"Space":[88],"guides":[90],"grouping.":[92],"The":[93],"novel":[95],"enables":[97],"us":[98],"analyze":[100],"visualize":[102],"an":[106],"meaningful":[109,164],"while":[111],"preserving":[112],"temporal":[113],"continuity.":[115],"Our":[116,167],"experimental":[117],"validation":[118],"twofold.":[120],"First,":[121],"achieve":[123],"competitive":[124],"results":[125],"common":[128],"segmentation":[131],"benchmark.":[132],"Second,":[133],"extend":[135],"this":[136],"benchmark":[137],"high":[139],"quality":[140],"part":[142],"annotations,":[143],"DAVIS":[144],"Parts":[145],"<sup":[146],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[147],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[148],",":[149],"which":[151],"establish":[153],"strong":[155],"baseline":[156],"showing":[158],"our":[160],"yields":[162],"spatio-temporally":[163],"parts.":[166],"new":[168],"will":[170],"support":[171],"applications":[172],"require":[174],"high-level":[175],"reasoning":[177],"level.":[181]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}