{"id":"https://openalex.org/W7140129050","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.32","title":"Towards Robust Evaluation of Visual Activity Recognition: Resolving Verb Ambiguity with Sense Clustering","display_name":"Towards Robust Evaluation of Visual Activity Recognition: Resolving Verb Ambiguity with Sense Clustering","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140129050","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.32"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.32","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.32","pdf_url":"https://aclanthology.org/2026.findings-eacl.32.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.32.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089765171","display_name":"Louie Hong Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Louie Hong Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130411060","display_name":"Nicholas Jarvis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicholas Jarvis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124051966","display_name":"Tianyu Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyu Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"656","last_page":"672"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.38659998774528503,"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":0.38659998774528503,"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":0.2831999957561493,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.03200000151991844,"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/ambiguity","display_name":"Ambiguity","score":0.5379999876022339},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5072000026702881},{"id":"https://openalex.org/keywords/verb","display_name":"Verb","score":0.4277999997138977},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.320499986410141},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.30889999866485596}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6089000105857849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5907999873161316},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5379999876022339},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5072000026702881},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47040000557899475},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2863999903202057}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.32","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.32","pdf_url":"https://aclanthology.org/2026.findings-eacl.32.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.32","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.32","pdf_url":"https://aclanthology.org/2026.findings-eacl.32.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4360968768596649,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140129050.pdf","grobid_xml":"https://content.openalex.org/works/W7140129050.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Evaluating":[0],"visual":[1],"activity":[2,116],"recognition":[3,117],"systems":[4],"is":[5],"challenging":[6],"due":[7],"to":[8,25,38,59,99],"inherent":[9],"ambiguities":[10],"in":[11,19,64],"verb":[12,43,81],"semantics":[13],"and":[14,119],"image":[15,97],"interpretation.When":[16],"describing":[17],"actions":[18],"images,":[20],"synonymous":[21],"verbs":[22],"can":[23,36],"refer":[24],"the":[26,91,112,134],"same":[27],"event":[28],"(e.g.,":[29,45],"brushing":[30],"vs.":[31,47],"grooming),":[32],"while":[33],"different":[34],"perspectives":[35],"lead":[37],"equally":[39],"valid":[40],"but":[41],"distinct":[42,109],"choices":[44],"piloting":[46],"operating).Standard":[48],"exact-match":[49],"evaluation,":[50],"which":[51],"relies":[52],"on":[53],"a":[54,75,85,108,143],"single":[55],"gold":[56],"answer,":[57],"fails":[58],"capture":[60],"these":[61],"ambiguities,":[62],"resulting":[63],"an":[65],"incomplete":[66],"assessment":[67,146],"of":[68,90,111,147],"model":[69,148],"performance.To":[70],"address":[71],"this,":[72],"we":[73],"propose":[74],"vision-language":[76],"clustering":[77],"framework":[78],"that":[79,95,133],"constructs":[80],"sense":[82,102],"clusters,":[83,103],"providing":[84],"more":[86,144],"robust":[87],"evaluation.Our":[88],"analysis":[89,131],"imSitu":[92],"dataset":[93],"shows":[94],"each":[96,105],"maps":[98],"around":[100],"four":[101],"with":[104,124,139],"cluster":[106],"representing":[107],"perspective":[110],"image.We":[113],"evaluate":[114],"multiple":[115],"models":[118],"compare":[120],"our":[121,128],"cluster-based":[122,135],"evaluation":[123,126,136],"standard":[125],"methods.Additionally,":[127],"human":[129,140],"alignment":[130],"suggests":[132],"better":[137],"aligns":[138],"judgments,":[141],"offering":[142],"nuanced":[145],"performance.":[149]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-03-24T00:00:00"}