{"id":"https://openalex.org/W4417308247","doi":"https://doi.org/10.1109/iccv51701.2025.02190","title":"TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision","display_name":"TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417308247","doi":"https://doi.org/10.1109/iccv51701.2025.02190"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02190","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02190","pdf_url":null,"source":null,"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"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.09445","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022676725","display_name":"Ayush Gupta","orcid":"https://orcid.org/0000-0003-0935-9207"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ayush Gupta","raw_affiliation_strings":["SRI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101893463","display_name":"Anirban Roy","orcid":"https://orcid.org/0009-0003-2769-3388"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anirban Roy","raw_affiliation_strings":["SRI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102762707","display_name":"Rama Chellappa","orcid":"https://orcid.org/0000-0002-7638-1650"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rama Chellappa","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032194186","display_name":"Nathaniel D. Bastian","orcid":"https://orcid.org/0000-0001-9957-2778"},"institutions":[{"id":"https://openalex.org/I192545095","display_name":"United States Military Academy","ror":"https://ror.org/01jepya76","country_code":"US","type":"education","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I192545095","https://openalex.org/I4210088792"]},{"id":"https://openalex.org/I4210137659","display_name":"American Military Academy","ror":"https://ror.org/02xs6gm19","country_code":"PR","type":"education","lineage":["https://openalex.org/I4210137659"]}],"countries":["PR","US"],"is_corresponding":false,"raw_author_name":"Nathaniel D. Bastian","raw_affiliation_strings":["United States Military Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"United States Military Academy","institution_ids":["https://openalex.org/I4210137659","https://openalex.org/I192545095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067109059","display_name":"Alvaro Velasquez","orcid":"https://orcid.org/0000-0001-6757-105X"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]},{"id":"https://openalex.org/I2802236040","display_name":"University of Colorado System","ror":"https://ror.org/00jc20583","country_code":"US","type":"education","lineage":["https://openalex.org/I2802236040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alvaro Velasquez","raw_affiliation_strings":["University of Colorado Boulder"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado Boulder","institution_ids":["https://openalex.org/I2802236040","https://openalex.org/I188538660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035902535","display_name":"Susmit Jha","orcid":"https://orcid.org/0000-0001-5983-9095"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Susmit Jha","raw_affiliation_strings":["SRI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5022676725"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38159438,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23593","last_page":"23603"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9746000170707703,"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":0.9746000170707703,"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":0.010300000198185444,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0017000000225380063,"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/grounded-theory","display_name":"Grounded theory","score":0.5996999740600586},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5860000252723694},{"id":"https://openalex.org/keywords/notice","display_name":"Notice","score":0.5570999979972839},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48910000920295715},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.4880000054836273},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.38519999384880066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6991000175476074},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.5996999740600586},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5860000252723694},{"id":"https://openalex.org/C2779913896","wikidata":"https://www.wikidata.org/wiki/Q7063001","display_name":"Notice","level":2,"score":0.5570999979972839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5365999937057495},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48910000920295715},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.4880000054836273},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.357699990272522},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34940001368522644},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.2565999925136566}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02190","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02190","pdf_url":null,"source":null,"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:2506.09445","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.09445","pdf_url":"https://arxiv.org/pdf/2506.09445","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2506.09445","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.09445","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.09445","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.09445","pdf_url":"https://arxiv.org/pdf/2506.09445","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,58,70,85,124,143,181],"address":[1],"the":[2,35,64,67,78,94,105,112,120,129,132,158,176],"problem":[3],"of":[4,96,107],"video":[5,24],"question":[6,106,117,137,169],"answering":[7,138],"(video":[8],"QA)":[9],"with":[10,34,55,131],"temporal":[11,20,68,79,90,122],"grounding":[12,80,91,109,133],"in":[13,72],"a":[14,23,26,46,73,101,108,116],"weakly":[15,74,166],"supervised":[16,75,167],"setup,":[17],"without":[18],"any":[19],"annotations.":[21],"Given":[22],"and":[25,37,66,92,111,149,178],"question,":[27],"we":[28,43,156,174],"generate":[29,63,86],"an":[30],"open-ended":[31,150,172],"answer":[32,65],"grounded":[33,147,154,168],"start":[36],"end":[38],"time.":[39],"For":[40,153,171],"this":[41],"task,":[42],"propose":[44],"TOGA:":[45],"vision-language":[47],"model":[48],"for":[49,89,185],"Temporally":[50],"Grounded":[51],"Open-Ended":[52],"Video":[53],"QA":[54,148,151],"Weak":[56],"Supervision.":[57],"instruct-tune":[59],"TOGA":[60,145],"to":[61,119,164],"jointly":[62,127],"grounding.":[69,142],"operate":[71],"setup":[76],"where":[77],"annotations":[81],"are":[82],"not":[83],"available.":[84],"pseudo":[87],"labels":[88,98],"ensure":[93],"validity":[95],"these":[97,189],"by":[99,115],"imposing":[100],"consistency":[102],"constraint":[103],"between":[104],"response":[110,113],"generated":[114],"referring":[118],"same":[121],"segment.":[123],"notice":[125],"that":[126],"generating":[128],"answers":[130],"improves":[134],"performance":[135,184],"on":[136,146,188],"as":[139,141],"well":[140],"evaluate":[144,165],"tasks.":[152],"QA,":[155,173],"consider":[157,175],"NExT-GQA":[159],"benchmark":[160],"which":[161],"is":[162],"designed":[163],"answering.":[170],"MSVD-QA":[177],"ActivityNet-QA":[179],"benchmarks.":[180,190],"achieve":[182],"state-of-the-art":[183],"both":[186],"tasks":[187]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}