{"id":"https://openalex.org/W7160142452","doi":"https://doi.org/10.1109/iccv51701.2025.00242","title":"Visual Intention Grounding for Egocentric Assistants","display_name":"Visual Intention Grounding for Egocentric Assistants","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7160142452","doi":"https://doi.org/10.1109/iccv51701.2025.00242"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00242","doi":"https://doi.org/10.1109/iccv51701.2025.00242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00242","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.13621","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102605009","display_name":"Pengzhan Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Pengzhan Sun","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024669782","display_name":"Junbin Xiao","orcid":"https://orcid.org/0000-0001-5573-6195","observed_orcids":["https://orcid.org/0000-0001-5573-6195"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Junbin Xiao","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017172598","display_name":"Tze Ho Elden Tse","orcid":"https://orcid.org/0009-0000-5910-1509","observed_orcids":["https://orcid.org/0009-0000-5910-1509"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tze Ho Elden Tse","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101762862","display_name":"Yicong Li","orcid":"https://orcid.org/0000-0003-3844-9332","observed_orcids":["https://orcid.org/0000-0003-3844-9332"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yicong Li","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020005244","display_name":"Arjun Akula","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arjun Akula","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006278133","display_name":"Angela Yao","orcid":"https://orcid.org/0000-0001-7418-6141","observed_orcids":["https://orcid.org/0000-0001-7418-6141"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Angela Yao","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4318,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.88423361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2512","last_page":"2522"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0,"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/egocentric-vision","display_name":"egocentric vision","score":0.6909999847412109},{"id":"https://openalex.org/keywords/instruction-tuning","display_name":"instruction tuning","score":0.6639999747276306},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.7440000176429749},{"id":"https://openalex.org/keywords/object-grounding","display_name":"object grounding","score":0.5669999718666077}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5737000107765198},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3743000030517578},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3409000039100647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.32199999690055847},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.31769999861717224},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25189998745918274},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00242","doi":"https://doi.org/10.1109/iccv51701.2025.00242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00242","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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:2504.13621","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2504.13621","pdf_url":"https://arxiv.org/pdf/2504.13621","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.13621","doi":"https://doi.org/10.48550/arxiv.2504.13621","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.13621","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.13621","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2504.13621","pdf_url":"https://arxiv.org/pdf/2504.13621","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320698","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160142452.pdf","grobid_xml":"https://content.openalex.org/works/W7160142452.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2040145958","https://openalex.org/W2128248292","https://openalex.org/W2159149613","https://openalex.org/W2251512949","https://openalex.org/W2489434015","https://openalex.org/W2505639562","https://openalex.org/W2933801649","https://openalex.org/W2963109634","https://openalex.org/W2963635127","https://openalex.org/W2986755220","https://openalex.org/W3034772468","https://openalex.org/W3035097537","https://openalex.org/W3159619744","https://openalex.org/W3187651588","https://openalex.org/W3205691536","https://openalex.org/W3205786327","https://openalex.org/W4309181071","https://openalex.org/W4312974690","https://openalex.org/W4386065350","https://openalex.org/W4386071509","https://openalex.org/W4386075493","https://openalex.org/W4402670811","https://openalex.org/W4402671847","https://openalex.org/W4402702986","https://openalex.org/W4402728164","https://openalex.org/W4402753519","https://openalex.org/W4403081598","https://openalex.org/W4404612908","https://openalex.org/W4404781880","https://openalex.org/W4411631838","https://openalex.org/W4413146322"],"related_works":["https://openalex.org/W7220858320","https://openalex.org/W7160137123","https://openalex.org/W7220843653","https://openalex.org/W7160098082","https://openalex.org/W7212020375","https://openalex.org/W2921787403","https://openalex.org/W7220932931","https://openalex.org/W3128721591","https://openalex.org/W7166821174","https://openalex.org/W7160059780"],"abstract_inverted_index":{"Visual":[0],"grounding":[1,118,143],"associates":[2],"textual":[3],"descriptions":[4,107],"with":[5,105,111],"objects":[6,34,70,86],"in":[7,91],"an":[8],"image.":[9],"Conventional":[10],"methods":[11],"target":[12],"third-person":[13],"image":[14],"inputs":[15,30,149],"and":[16,33,42,66,71,87,108,116,125,146,155],"named":[17],"object":[18,76,117,153],"queries.":[19],"In":[20],"applications":[21],"such":[22],"as":[23],"AI":[24],"assistants,":[25],"the":[26,51],"perspective":[27],"shifts":[28],"--":[29],"are":[31],"egocentric,":[32],"may":[35],"be":[36],"referred":[37],"to":[38,63],"implicitly":[39],"through":[40],"needs":[41],"intentions.":[43,158],"To":[44],"bridge":[45],"this":[46],"gap,":[47],"we":[48],"introduce":[49],"EgoIntention,":[50,129],"first":[52],"dataset":[53],"for":[54,144],"egocentric":[55,92,109,145],"visual":[56,142,148],"intention":[57,114],"grounding.":[58,137],"EgoIntention":[59],"challenges":[60],"multimodal":[61],"LLMs":[62],"1)":[64],"understand":[65],"ignore":[67],"unintended":[68],"contextual":[69],"2)":[72],"reason":[73],"about":[74],"uncommon":[75],"functionalities.":[77],"Benchmark":[78],"results":[79],"show":[80],"that":[81],"current":[82],"models":[83],"misidentify":[84],"context":[85],"lack":[88],"affordance":[89],"understanding":[90],"views.":[93],"We":[94],"also":[95],"propose":[96],"Reason-to-Ground":[97],"(RoG)":[98],"instruction":[99],"tuning;":[100],"it":[101],"enables":[102,140],"hybrid":[103,126],"training":[104,127],"normal":[106],"intentions":[110],"a":[112],"chained":[113],"reasoning":[115],"mechanism.":[119],"RoG":[120],"significantly":[121],"outperforms":[122],"naive":[123,135],"finetuning":[124],"on":[128],"while":[130,150],"maintaining":[131],"or":[132],"slightly":[133],"improving":[134],"description":[136],"This":[138],"advancement":[139],"unified":[141],"exocentric":[147],"handling":[151],"explicit":[152],"queries":[154],"implicit":[156],"human":[157]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-05-05T00:00:00"}