{"id":"https://openalex.org/W4387546363","doi":"https://doi.org/10.1109/tmm.2023.3323878","title":"Locate Before Answering: Answer Guided Question Localization for Video Question Answering","display_name":"Locate Before Answering: Answer Guided Question Localization for Video Question Answering","publication_year":2023,"publication_date":"2023-10-11","ids":{"openalex":"https://openalex.org/W4387546363","doi":"https://doi.org/10.1109/tmm.2023.3323878"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3323878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3323878","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5071784615","display_name":"Tianwen Qian","orcid":"https://orcid.org/0000-0002-3881-4857"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianwen Qian","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3881-4857","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101421440","display_name":"Ran Cui","orcid":"https://orcid.org/0000-0001-8613-3346"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ran Cui","raw_affiliation_strings":["Australian National University, Canberra, ACT, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8613-3346","affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373492","display_name":"Jingjing Chen","orcid":"https://orcid.org/0000-0003-3148-264X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Chen","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3148-264X","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564498","display_name":"Pai Peng","orcid":"https://orcid.org/0000-0003-4755-9736"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pai Peng","raw_affiliation_strings":["Bilibili Company, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4755-9736","affiliations":[{"raw_affiliation_string":"Bilibili Company, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101813748","display_name":"Xiaowei Guo","orcid":"https://orcid.org/0009-0004-1171-1956"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaowei Guo","raw_affiliation_strings":["Bilibili Company, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-1171-1956","affiliations":[{"raw_affiliation_string":"Bilibili Company, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1907-8567","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4463,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.91201529,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"4554","last_page":"4563"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9955000281333923,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9902999997138977,"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/computer-science","display_name":"Computer science","score":0.884833812713623},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.8590172529220581},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6711530089378357},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6369116902351379},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.536310076713562},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5210175514221191},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40336281061172485},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39799028635025024},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3376190960407257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.884833812713623},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8590172529220581},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6711530089378357},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6369116902351379},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.536310076713562},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5210175514221191},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40336281061172485},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39799028635025024},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3376190960407257},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3323878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3323878","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6151995449","display_name":"\u6df1\u5ea6\u795e\u7ecf\u7f51\u7edc\u7684\u6570\u5b66\u7406\u8bba\u53ca\u5176\u5e94\u7528","funder_award_id":"21JC1400600","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1586939924","https://openalex.org/W1927052826","https://openalex.org/W1933349210","https://openalex.org/W2095705004","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2250384498","https://openalex.org/W2250539671","https://openalex.org/W2549139847","https://openalex.org/W2606982687","https://openalex.org/W2619947201","https://openalex.org/W2735159761","https://openalex.org/W2747623286","https://openalex.org/W2765716052","https://openalex.org/W2883429621","https://openalex.org/W2896457183","https://openalex.org/W2904291752","https://openalex.org/W2954199749","https://openalex.org/W2962949233","https://openalex.org/W2963017553","https://openalex.org/W2963541336","https://openalex.org/W2964072591","https://openalex.org/W2964089981","https://openalex.org/W2964220823","https://openalex.org/W2966683369","https://openalex.org/W2969897437","https://openalex.org/W2974161034","https://openalex.org/W2979933490","https://openalex.org/W2997805943","https://openalex.org/W2998166190","https://openalex.org/W3016658915","https://openalex.org/W3027790991","https://openalex.org/W3034730770","https://openalex.org/W3108328693","https://openalex.org/W3121304688","https://openalex.org/W3126942607","https://openalex.org/W3135751354","https://openalex.org/W3172523222","https://openalex.org/W3173367591","https://openalex.org/W3175961224","https://openalex.org/W3181758331","https://openalex.org/W3186567887","https://openalex.org/W3187433838","https://openalex.org/W3189890868","https://openalex.org/W3197457832","https://openalex.org/W4226094317","https://openalex.org/W4230025115","https://openalex.org/W4295046616","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638318767","https://openalex.org/W6674330103","https://openalex.org/W6682086655","https://openalex.org/W6780226713","https://openalex.org/W6955071965"],"related_works":["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/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359"],"abstract_inverted_index":{"Video":[0],"question":[1,71,86,118,161,204],"answering":[2],"(VideoQA)":[3],"is":[4,152],"an":[5,122,127],"essential":[6],"task":[7],"in":[8,63,75,90],"vision-language":[9],"understanding,":[10],"which":[11],"has":[12],"attracted":[13],"numerous":[14],"research":[15],"attention":[16],"recently.":[17],"Nevertheless,":[18],"existing":[19],"works":[20],"mostly":[21],"achieve":[22],"promising":[23],"performances":[24],"on":[25,35,185],"short":[26,77],"videos":[27],"of":[28,46,145,202],"duration":[29],"within":[30],"15":[31],"seconds.":[32],"For":[33],"VideoQA":[34,189],"minute-level":[36],"long-term":[37,188],"videos,":[38],"those":[39],"methods":[40],"are":[41],"likely":[42],"to":[43,50,82,87,154,172],"fail":[44],"because":[45],"lacking":[47],"the":[48,64,67,70,85,91,96,99,131,134,142,146,160,174,179,199,203],"ability":[49],"deal":[51],"with":[52],"noise":[53],"and":[54,60,93,121,193],"redundancy":[55],"caused":[56],"by":[57],"scene":[58],"changes":[59],"multiple":[61],"actions":[62],"video.":[65],"Considering":[66],"fact":[68],"that":[69,115],"often":[72],"remains":[73],"concentrated":[74],"a":[76,88,112,117,167],"temporal":[78,157],"range,":[79],"we":[80,106,165],"propose":[81,107],"first":[83],"locate":[84],"segment":[89,101],"video":[92],"then":[94],"infer":[95],"answer":[97,123,136,147],"using":[98],"located":[100],"only.":[102],"Under":[103],"this":[104],"scheme,":[105],"\u201cLocate":[108],"before":[109],"Answering\u201d":[110],"(LocAns),":[111],"novel":[113],"approach":[114],"integrates":[116],"localization":[119,162],"module":[120,125],"prediction":[124,148],"into":[126],"end-to-end":[128],"model.":[129],"During":[130],"training":[132,170],"phase,":[133],"available":[135],"label":[137],"not":[138],"only":[139],"serves":[140],"as":[141],"supervision":[143],"signal":[144],"module,":[149],"but":[150],"also":[151],"used":[153],"generate":[155],"pseudo":[156],"labels":[158],"for":[159],"module.":[163],"Moreover,":[164],"design":[166],"decoupled":[168],"alternative":[169],"strategy":[171],"update":[173],"two":[175],"modules":[176],"separately.":[177],"In":[178],"experiments,":[180],"LocAns":[181],"achieves":[182],"state-of-the-art":[183],"performance":[184,201],"three":[186],"modern":[187],"datasets,":[190],"NExT-QA,":[191],"ActivityNet-QA,":[192],"AGQA.":[194],"Its":[195],"qualitative":[196],"examples":[197],"show":[198],"reliable":[200],"localization.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2025-10-10T00:00:00"}
