{"id":"https://openalex.org/W7163385976","doi":"https://doi.org/10.48550/arxiv.2606.02962","title":"Hand Trajectory Fusion for Egocentric Natural Language Query Grounding","display_name":"Hand Trajectory Fusion for Egocentric Natural Language Query Grounding","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7163385976","doi":"https://doi.org/10.48550/arxiv.2606.02962"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2606.02962","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.02962","pdf_url":"https://arxiv.org/pdf/2606.02962","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2606.02962","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092625555","display_name":"Enmin Zhong","orcid":"https://orcid.org/0000-0002-4638-7947","observed_orcids":["https://orcid.org/0000-0002-4638-7947"]},"institutions":[{"id":"https://openalex.org/I4405253306","display_name":"Information Processing and Telecommunications Center","ror":"https://ror.org/00hcf7151","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4405253306","https://openalex.org/I88060688"]},{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Zhong, Enmin","raw_affiliation_strings":["ETSI Telecomunicaci\u00f3n , Universidad Polit\u00e9cnica de Madrid , Spain","Grupo de Tratamiento de Im\u00e1genes (GTI) , Information Processing and Telecommunications Center ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETSI Telecomunicaci\u00f3n , Universidad Polit\u00e9cnica de Madrid , Spain","institution_ids":["https://openalex.org/I88060688"]},{"raw_affiliation_string":"Grupo de Tratamiento de Im\u00e1genes (GTI) , Information Processing and Telecommunications Center ,","institution_ids":["https://openalex.org/I4405253306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137796694","display_name":"Carlos R. del-Blanco","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405253306","display_name":"Information Processing and Telecommunications Center","ror":"https://ror.org/00hcf7151","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4405253306","https://openalex.org/I88060688"]},{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"del-Blanco, Carlos R.","raw_affiliation_strings":["ETSI Telecomunicaci\u00f3n , Universidad Polit\u00e9cnica de Madrid , Spain","Grupo de Tratamiento de Im\u00e1genes (GTI) , Information Processing and Telecommunications Center ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETSI Telecomunicaci\u00f3n , Universidad Polit\u00e9cnica de Madrid , Spain","institution_ids":["https://openalex.org/I88060688"]},{"raw_affiliation_string":"Grupo de Tratamiento de Im\u00e1genes (GTI) , Information Processing and Telecommunications Center ,","institution_ids":["https://openalex.org/I4405253306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032522626","display_name":"Fernando Jaureguizar","orcid":"https://orcid.org/0000-0001-6449-5151","observed_orcids":["https://orcid.org/0000-0001-6449-5151"]},"institutions":[{"id":"https://openalex.org/I4405253306","display_name":"Information Processing and Telecommunications Center","ror":"https://ror.org/00hcf7151","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4405253306","https://openalex.org/I88060688"]},{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jaureguizar, Fernando","raw_affiliation_strings":["ETSI Telecomunicaci\u00f3n , Universidad Polit\u00e9cnica de Madrid , Spain","Grupo de Tratamiento de Im\u00e1genes (GTI) , Information Processing and Telecommunications Center ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETSI Telecomunicaci\u00f3n , Universidad Polit\u00e9cnica de Madrid , Spain","institution_ids":["https://openalex.org/I88060688"]},{"raw_affiliation_string":"Grupo de Tratamiento de Im\u00e1genes (GTI) , Information Processing and Telecommunications Center ,","institution_ids":["https://openalex.org/I4405253306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125590468","display_name":"Narciso Garc\u00eda","orcid":"https://orcid.org/0000-0002-0397-894X","observed_orcids":["https://orcid.org/0000-0002-0397-894X"]},"institutions":[{"id":"https://openalex.org/I4405253306","display_name":"Information Processing and Telecommunications Center","ror":"https://ror.org/00hcf7151","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4405253306","https://openalex.org/I88060688"]},{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Garc\u00eda, Narciso","raw_affiliation_strings":["ETSI Telecomunicaci\u00f3n , Universidad Polit\u00e9cnica de Madrid , Spain","Grupo de Tratamiento de Im\u00e1genes (GTI) , Information Processing and Telecommunications Center ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETSI Telecomunicaci\u00f3n , Universidad Polit\u00e9cnica de Madrid , Spain","institution_ids":["https://openalex.org/I88060688"]},{"raw_affiliation_string":"Grupo de Tratamiento de Im\u00e1genes (GTI) , Information Processing and Telecommunications Center ,","institution_ids":["https://openalex.org/I4405253306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9765999913215637,"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":0.9765999913215637,"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":0.010999999940395355,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.003000000026077032,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/hand-trajectory","display_name":"hand trajectory","score":0.7670000195503235},{"id":"https://openalex.org/keywords/hand-object-interaction","display_name":"hand-object interaction","score":0.8149999976158142},{"id":"https://openalex.org/keywords/cross-attention-fusion","display_name":"cross-attention fusion","score":0.8220000267028809},{"id":"https://openalex.org/keywords/adaptive-gating","display_name":"adaptive gating","score":0.9829999804496765},{"id":"https://openalex.org/keywords/ego4d","display_name":"Ego4D","score":0.7509999871253967},{"id":"https://openalex.org/keywords/egocentric-video","display_name":"egocentric video","score":0.7210000157356262},{"id":"https://openalex.org/keywords/temporal-localization","display_name":"temporal localization","score":0.4519999921321869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440000176429749},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6140999794006348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5853999853134155},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.572700023651123},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.47839999198913574},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4661000072956085},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4246000051498413},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4212999939918518},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41530001163482666},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37439998984336853},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C96956885","wikidata":"https://www.wikidata.org/wiki/Q6138701","display_name":"RDF query language","level":5,"score":0.2678000032901764},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.25429999828338623}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2606.02962","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.02962","pdf_url":"https://arxiv.org/pdf/2606.02962","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2606.02962","doi":"https://doi.org/10.48550/arxiv.2606.02962","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.02962","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2606.02962","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.02962","pdf_url":"https://arxiv.org/pdf/2606.02962","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7163385976.pdf","grobid_xml":"https://content.openalex.org/works/W7163385976.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W3036954260","https://openalex.org/W4310921506","https://openalex.org/W4400022837","https://openalex.org/W4415084011"],"related_works":["https://openalex.org/W7220904939","https://openalex.org/W4382491300","https://openalex.org/W7160871960","https://openalex.org/W4417531501","https://openalex.org/W7137204416","https://openalex.org/W7220953451","https://openalex.org/W3153098222","https://openalex.org/W4399151480","https://openalex.org/W3200786863","https://openalex.org/W7076953748"],"abstract_inverted_index":{"Egocentric":[0],"Natural":[1],"Language":[2],"Query":[3],"(NLQ)":[4],"grounding":[5,120],"asks":[6],"a":[7,12,21,50,60,65,86],"model":[8],"to":[9],"localize,":[10],"in":[11],"long":[13],"first-person":[14],"video,":[15],"the":[16,31,38,94,100],"temporal":[17],"interval":[18],"that":[19,40,116],"answers":[20],"free-form":[22],"text":[23],"query.":[24],"Existing":[25],"methods":[26],"fuse":[27],"video":[28],"appearance":[29,123],"with":[30,81,90],"query":[32],"but":[33],"ignore":[34],"hand":[35,68,72,117],"motion,":[36],"despite":[37],"fact":[39],"roughly":[41],"41%":[42],"of":[43,52,67],"Ego4D":[44,95],"NLQ":[45,96],"queries":[46,107,112],"are":[47,76],"answered":[48],"at":[49],"moment":[51],"hand--object":[53],"manipulation":[54],"or":[55],"their":[56],"immediate":[57],"outcomes.We":[58],"propose":[59],"hand-trajectory":[61],"encoder":[62],"for":[63,104],"converting":[64],"sequence":[66],"skeletons":[69],"into":[70],"highly-semantic":[71],"kinematic":[73],"features,":[74],"which":[75],"then":[77],"aligned":[78],"and":[79,110],"combined":[80],"pretrained":[82],"video--text":[83],"features":[84],"through":[85],"cross-attention":[87],"fusion":[88],"strategy":[89],"adaptive":[91],"gating.":[92],"On":[93],"v2":[97],"validation":[98],"split,":[99],"clearest":[101],"gains":[102],"appear":[103],"Hand-Object":[105],"Interaction":[106],"(+2.54":[108],"R1@IoU=0.3)":[109],"Quantity/State":[111],"(+4.32":[113],"R1@IoU=0.3),":[114],"indicating":[115],"trajectory":[118],"provides":[119],"cues":[121],"beyond":[122],"alone.":[124]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-06-04T00:00:00"}