{"id":"https://openalex.org/W4416551429","doi":"https://doi.org/10.1109/iccv51701.2025.00876","title":"Fine-Grained Spatiotemporal Grounding on Egocentric Videos","display_name":"Fine-Grained Spatiotemporal Grounding on Egocentric Videos","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416551429","doi":"https://doi.org/10.1109/iccv51701.2025.00876"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.00518","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086747098","display_name":"Shuo Liang","orcid":"https://orcid.org/0000-0001-7842-7782"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Shuo Liang","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040199499","display_name":"Yiwu Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yiwu Zhong","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007459088","display_name":"Zi-Yuan Hu","orcid":"https://orcid.org/0000-0002-4471-0499"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zi-Yuan Hu","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yeyao Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yeyao Tao","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035789490","display_name":"Liwei Wang","orcid":"https://orcid.org/0000-0001-5329-6835"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Liwei Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5086747098"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33693253,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9385","last_page":"9395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9089000225067139,"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":0.9089000225067139,"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":0.037700001150369644,"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/T11439","display_name":"Video Analysis and Summarization","score":0.012299999594688416,"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/endocentric-and-exocentric","display_name":"Endocentric and exocentric","score":0.8877000212669373},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7366999983787537},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6610999703407288},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.510699987411499},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4867999851703644},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.3652999997138977},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.34700000286102295},{"id":"https://openalex.org/keywords/activity-recognition","display_name":"Activity recognition","score":0.33500000834465027}],"concepts":[{"id":"https://openalex.org/C131042201","wikidata":"https://www.wikidata.org/wiki/Q493198","display_name":"Endocentric and exocentric","level":4,"score":0.8877000212669373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7620999813079834},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7366999983787537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6953999996185303},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6610999703407288},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.510699987411499},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49219998717308044},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.34700000286102295},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.33329999446868896},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.30799999833106995},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.30489999055862427},{"id":"https://openalex.org/C22304111","wikidata":"https://www.wikidata.org/wiki/Q1417978","display_name":"Object permanence","level":4,"score":0.2915000021457672},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2818000018596649},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.00518","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.00518","pdf_url":"https://arxiv.org/pdf/2508.00518","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"doi:10.48550/arxiv.2508.00518","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.00518","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.00518","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.00518","pdf_url":"https://arxiv.org/pdf/2508.00518","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[{"id":"https://openalex.org/G3760517555","display_name":null,"funder_award_id":"24200223","funder_id":"https://openalex.org/F4320321590","funder_display_name":"Gentofte Hospital"},{"id":"https://openalex.org/G8284215404","display_name":null,"funder_award_id":"2022ZD0161200,2022ZD0161201","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321590","display_name":"Gentofte Hospital","ror":"https://ror.org/051dzw862"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Spatiotemporal":[0],"video":[1,165],"grounding":[2,89,133],"aims":[3],"to":[4,123],"localize":[5],"target":[6],"entities":[7],"in":[8,21,34,90],"videos":[9],"based":[10],"on":[11,137,143,151],"textual":[12],"queries.":[13],"While":[14],"existing":[15],"research":[16],"has":[17],"made":[18],"significant":[19,146],"progress":[20],"exocentric":[22,56,152],"videos,":[23,57],"the":[24,51,82,130],"egocentric":[25,54,91,164],"setting":[26],"remains":[27],"relatively":[28],"underexplored,":[29],"despite":[30],"its":[31],"growing":[32],"importance":[33],"applications":[35],"such":[36,61],"as":[37,62],"augmented":[38],"reality":[39],"and":[40,55,71,106,112,160],"robotics.":[41],"In":[42],"this":[43],"work,":[44],"we":[45,79,116],"conduct":[46],"a":[47,119],"systematic":[48],"analysis":[49],"of":[50],"discrepancies":[52],"between":[53],"revealing":[58],"key":[59],"challenges":[60],"shorter":[63],"object":[64,69,107],"durations,":[65],"sparser":[66],"trajectories,":[67],"smaller":[68],"sizes,":[70],"larger":[72],"positional":[73],"shifts.":[74],"To":[75],"address":[76],"these":[77],"challenges,":[78],"introduce":[80],"EgoMask,":[81,140],"first":[83],"pixel-level":[84],"benchmark":[85,139],"for":[86,162],"fine-grained":[87],"spatiotemporal":[88,132],"videos.":[92,114],"It":[93],"is":[94,169],"constructed":[95],"by":[96],"our":[97,138],"proposed":[98],"automatic":[99],"annotation":[100],"pipeline,":[101],"which":[102],"annotates":[103],"referring":[104],"expressions":[105],"masks":[108],"across":[109],"short-,":[110],"medium-,":[111],"long-term":[113],"Additionally,":[115],"create":[117],"EgoMask-Train,":[118],"large-scale":[120],"training":[121],"dataset":[122],"facilitate":[124],"model":[125],"development.":[126],"Experiments":[127],"demonstrate":[128],"that":[129],"state-of-the-art":[131],"models":[134],"perform":[135],"poorly":[136],"but":[141],"fine-tuning":[142],"EgoMask-Train":[144],"yields":[145],"improvements,":[147],"while":[148],"preserving":[149],"performance":[150],"datasets.":[153],"Our":[154,167],"work":[155],"thus":[156],"provides":[157],"essential":[158],"resources":[159],"insights":[161],"advancing":[163],"understanding.":[166],"code":[168],"available":[170],"at":[171],"https://github.com/LaVi-Lab/EgoMask":[172],".":[173]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}