{"id":"https://openalex.org/W7160245317","doi":"https://doi.org/10.1109/wacv61042.2026.00342","title":"SPOC: Spatially-Progressing Object State Change Segmentation in Video","display_name":"SPOC: Spatially-Progressing Object State Change Segmentation in Video","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160245317","doi":"https://doi.org/10.1109/wacv61042.2026.00342"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5090437590","display_name":"Priyanka Mandikal","orcid":"https://orcid.org/0000-0002-6257-7417"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Priyanka Mandikal","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035608624","display_name":"Tushar Nagarajan","orcid":"https://orcid.org/0000-0002-1627-3842"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tushar Nagarajan","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135285845","display_name":"Alex Stoken","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Stoken","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059038346","display_name":"Zihui Xue","orcid":"https://orcid.org/0000-0001-7394-5169"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zihui Xue","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135418710","display_name":"Kristen Grauman","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristen Grauman","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":21.6816,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98938304,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3504","last_page":"3513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.4099000096321106,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.4099000096321106,"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":0.2206999957561493,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.0551999993622303,"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/object","display_name":"Object (grammar)","score":0.427700012922287},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.412200003862381},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3758000135421753},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.34450000524520874},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3147999942302704},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3124000132083893}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6640999913215637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6603999733924866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5983999967575073},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.427700012922287},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3758000135421753},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.28110000491142273},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.27219998836517334},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2630999982357025}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1948251820","https://openalex.org/W2412782625","https://openalex.org/W2470139095","https://openalex.org/W2594270457","https://openalex.org/W2736809457","https://openalex.org/W2777926144","https://openalex.org/W2889167066","https://openalex.org/W2889986507","https://openalex.org/W2963863119","https://openalex.org/W2984008963","https://openalex.org/W2986385672","https://openalex.org/W3158711590","https://openalex.org/W3162332195","https://openalex.org/W3172112830","https://openalex.org/W3205786327","https://openalex.org/W4214926101","https://openalex.org/W4312396403","https://openalex.org/W4312563428","https://openalex.org/W4312578829","https://openalex.org/W4312960937","https://openalex.org/W4313174527","https://openalex.org/W4386065555","https://openalex.org/W4386071798","https://openalex.org/W4386075561","https://openalex.org/W4386075819","https://openalex.org/W4390874167","https://openalex.org/W4390874575","https://openalex.org/W4390874670","https://openalex.org/W4402703020","https://openalex.org/W4402716047","https://openalex.org/W4402733566","https://openalex.org/W4402753682","https://openalex.org/W4402753868","https://openalex.org/W4404612908","https://openalex.org/W7133224883"],"related_works":[],"abstract_inverted_index":{"Object":[0],"state":[1,29,39,64],"changes":[2],"in":[3,26,160],"video":[4,95,188],"reveal":[5],"critical":[6],"cues":[7],"about":[8],"human":[9],"and":[10,84,94,105,120,154,196],"agent":[11],"activity.":[12],"However,":[13],"existing":[14],"methods":[15,97,195],"are":[16,82,87,158],"limited":[17],"to":[18,55,71,171,200],"temporal":[19],"localization":[20],"of":[21,78,138,147],"when":[22,34],"the":[23,49,57,61,74,136,139,145,198],"object":[24,63,80],"is":[25,51,70],"its":[27,103],"initial":[28,109],"(e.g.,":[30,41],"cheese":[31],"block)":[32],"versus":[33],"it":[35],"has":[36],"completed":[37],"a":[38,113,121,183],"change":[40,50,65],"grated":[42],"cheese),":[43],"offering":[44],"no":[45],"insight":[46],"into":[47],"where":[48,153],"unfolding.":[52],"We":[53,89,162],"propose":[54],"deepen":[56],"problem":[58],"by":[59],"introducing":[60],"spatially-progressing":[62],"segmentation":[66,96,181],"task.":[67],"The":[68],"goal":[69],"segment":[72],"at":[73,99],"pixel-level":[75],"those":[76,85],"regions":[77],"an":[79,108],"that":[81,86,91,191],"actionable":[83],"transformed.":[88],"show":[90],"state-of-the-art":[92],"VLMs":[93],"struggle":[98],"this":[100],"task,":[101],"underscoring":[102],"difficulty":[104],"novelty.":[106],"As":[107],"baseline,":[110],"we":[111],"design":[112],"VLM-based":[114],"pseudo-labeling":[115],"approach,":[116],"state-change":[117],"dynamics":[118],"constraints,":[119],"novel":[122],"WhereToChange":[123],"benchmark":[124],"built":[125],"on":[126,131],"in-the-wild":[127],"Internet":[128],"videos.":[129],"Experiments":[130],"two":[132],"datasets":[133],"validate":[134],"both":[135],"challenge":[137],"new":[140,184],"task":[141,186],"as":[142,144,182],"well":[143],"promise":[146],"our":[148,176],"model":[149],"for":[150,167,187],"localizing":[151],"exactly":[152],"how":[155],"fast":[156],"objects":[157],"changing":[159],"video.":[161],"further":[163],"demonstrate":[164],"useful":[165],"implications":[166],"tracking":[168],"activity":[169],"progress":[170],"benefit":[172],"robotic":[173],"agents.":[174],"Overall,":[175],"work":[177],"positions":[178],"spatial":[179],"OSC":[180],"frontier":[185],"understanding:":[189],"one":[190],"challenges":[192],"current":[193],"SOTA":[194],"invites":[197],"community":[199],"build":[201],"more":[202],"robust,":[203],"state-change-sensitive":[204],"representations.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}