{"id":"https://openalex.org/W4402777385","doi":"https://doi.org/10.1109/cvpr52733.2024.01229","title":"Grounded Question-Answering in Long Egocentric Videos","display_name":"Grounded Question-Answering in Long Egocentric Videos","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402777385","doi":"https://doi.org/10.1109/cvpr52733.2024.01229"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.01229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5007532959","display_name":"Shangzhe Di","orcid":"https://orcid.org/0009-0005-6977-4332"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shangzhe Di","raw_affiliation_strings":["CMIC, Shanghai Jiao Tong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CMIC, Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053549250","display_name":"Weidi Xie","orcid":"https://orcid.org/0009-0002-8609-6826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidi Xie","raw_affiliation_strings":["CMIC, Shanghai Jiao Tong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CMIC, Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007532959"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":3.9187,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.94350517,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12934","last_page":"12943"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9269999861717224,"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/T12031","display_name":"Speech and dialogue systems","score":0.9269999861717224,"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":0.920799970626831,"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/T10028","display_name":"Topic Modeling","score":0.9093999862670898,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7282054424285889},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6642898321151733},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45346298813819885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4117041230201721},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3761966824531555}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7282054424285889},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6642898321151733},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45346298813819885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4117041230201721},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3761966824531555}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.01229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Existing":[0],"approaches":[1],"to":[2,43,84,105,129],"video":[3,65],"understanding,":[4],"mainly":[5],"designed":[6],"for":[7,71,114,127],"short":[8],"videos":[9],"from":[10],"a":[11,102,123],"third-person":[12],"perspective,":[13],"are":[14,156],"limited":[15],"in":[16,19,34],"their":[17,46,85],"applicability":[18],"certain":[20],"fields,":[21],"such":[22],"as":[23],"robotics.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28],"delve":[29],"into":[30],"open-ended":[31,81],"question-answering":[32],"(QA)":[33],"long,":[35],"egocentric":[36],"videos,":[37],"which":[38,141],"allows":[39],"individuals":[40],"or":[41],"robots":[42],"inquire":[44],"about":[45],"own":[47],"past":[48],"visual":[49],"ex-periences.":[50],"This":[51],"task":[52,126],"presents":[53],"unique":[54],"challenges,":[55],"including":[56],"the":[57,67,76,136,147],"complexity":[58],"of":[59,79,138],"temporally":[60],"grounding":[61,98],"queries":[62],"within":[63,101],"extensive":[64],"content,":[66],"high":[68],"resource":[69],"demands":[70],"precise":[72],"data":[73,118],"annotation,":[74],"and":[75,99,116,120,149,154],"inherent":[77],"difficulty":[78],"evaluating":[80],"answers":[82],"due":[83],"ambiguous":[86],"nature.":[87],"Our":[88],"proposed":[89],"approach":[90],"tackles":[91],"these":[92],"challenges":[93],"by":[94],"(i)":[95],"integrating":[96],"query":[97],"answering":[100],"unified":[103],"model":[104],"reduce":[106],"error":[107],"propagation;":[108],"(ii)":[109],"employing":[110],"large":[111],"language":[112],"models":[113,155],"efficient":[115],"scalable":[117],"synthesis;":[119],"(iii)":[121],"introducing":[122],"close-ended":[124],"QA":[125],"evaluation,":[128],"man-age":[130],"answer":[131],"ambiguity.":[132],"Extensive":[133],"experiments":[134],"demonstrate":[135],"effectiveness":[137],"our":[139],"method,":[140],"also":[142],"achieves":[143],"state-of-the-art":[144],"performance":[145],"on":[146],"QAEgo4D":[148],"Ego4D-NLQ":[150],"benchmarks.":[151],"Code,":[152],"data,":[153],"open-sourced":[157],"<sup":[158],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[159],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}