{"id":"https://openalex.org/W4416402721","doi":"https://doi.org/10.1109/ismar-adjunct68609.2025.00177","title":"Sequential Context Engineering for Zero-Shot Recognition of Procedural Tasks in Egocentric AR","display_name":"Sequential Context Engineering for Zero-Shot Recognition of Procedural Tasks in Egocentric AR","publication_year":2025,"publication_date":"2025-10-08","ids":{"openalex":"https://openalex.org/W4416402721","doi":"https://doi.org/10.1109/ismar-adjunct68609.2025.00177"},"language":null,"primary_location":{"id":"doi:10.1109/ismar-adjunct68609.2025.00177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ismar-adjunct68609.2025.00177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)","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/A5089530552","display_name":"Junhyeok Park","orcid":"https://orcid.org/0000-0002-7942-4580"},"institutions":[{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]},{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["CA","KR"],"is_corresponding":true,"raw_author_name":"Junhyeok Park","raw_affiliation_strings":["KAIST"],"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023177829","display_name":"Woontack Woo","orcid":"https://orcid.org/0000-0002-5501-4421"},"institutions":[{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]},{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Woontack Woo","raw_affiliation_strings":["KAIST"],"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5089530552"],"corresponding_institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19887426,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"761","last_page":"762"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.44190001487731934,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.44190001487731934,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1656000018119812,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.14569999277591705,"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/context","display_name":"Context (archaeology)","score":0.6200000047683716},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6061999797821045},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4271000027656555},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.35429999232292175},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.3091000020503998},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.28790000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7864999771118164},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6200000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6186000108718872},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6061999797821045},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4271000027656555},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36250001192092896},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.35429999232292175},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31929999589920044},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3034999966621399},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2639000117778778},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ismar-adjunct68609.2025.00177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ismar-adjunct68609.2025.00177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)","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":5,"referenced_works":["https://openalex.org/W2895299763","https://openalex.org/W3126721948","https://openalex.org/W3207758636","https://openalex.org/W4386071547","https://openalex.org/W4388854793"],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,93],"sequential":[3],"context":[4,61],"engineering":[5],"framework":[6],"for":[7,30,55,99],"zero-shot":[8,22,107],"recognition":[9],"of":[10],"procedural":[11,31],"tasks":[12],"in":[13,101],"egocentric":[14],"AR.":[15],"While":[16],"large":[17],"vision-language":[18],"models":[19],"excel":[20],"at":[21],"image":[23],"classification,":[24],"they":[25],"lack":[26],"temporal":[27,56,97],"reasoning":[28,98],"required":[29],"understanding,":[32],"and":[33,58],"fully":[34],"fine-tuning":[35],"them":[36],"degrades":[37],"generalization":[38],"capabilities.":[39],"The":[40],"proposed":[41],"method":[42],"preserves":[43],"frozen":[44],"CLIP":[45],"encoders":[46],"while":[47,86],"introducing":[48],"lightweight":[49],"modules:":[50],"an":[51,59],"intra-action":[52],"attention":[53],"module":[54,62],"aggregation":[57],"inter-action":[60],"that":[63],"leverages":[64],"previous":[65],"predictions":[66],"to":[67],"generate":[68],"context-aware":[69],"prompts.":[70],"Evaluated":[71],"on":[72],"EGTEA":[73],"Gaze+":[74],"dataset,":[75],"our":[76],"approach":[77],"shows":[78],"promising":[79],"results":[80],"with":[81],"notable":[82],"improvements":[83],"over":[84],"baselines":[85],"maintaining":[87],"parameter":[88],"efficiency.":[89],"This":[90],"work":[91],"presents":[92],"step":[94],"toward":[95],"enabling":[96],"VLMs":[100],"resource-constrained":[102],"AR":[103],"systems":[104],"without":[105],"sacrificing":[106],"generalization.":[108]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-18T00:00:00"}