{"id":"https://openalex.org/W4417131421","doi":"https://doi.org/10.1109/tmm.2025.3639956","title":"Scene-Text Grounding for Text-Based Video Question Answering","display_name":"Scene-Text Grounding for Text-Based Video Question Answering","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4417131421","doi":"https://doi.org/10.1109/tmm.2025.3639956"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2025.3639956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3639956","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/A5100782531","display_name":"Sheng Zhou","orcid":"https://orcid.org/0009-0007-4215-5464"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Zhou","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0007-4215-5464","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024669782","display_name":"Junbin Xiao","orcid":"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":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5573-6195","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034737032","display_name":"Xun Yang","orcid":"https://orcid.org/0000-0003-0201-1638"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Yang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-0201-1638","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015177224","display_name":"Peipei Song","orcid":"https://orcid.org/0000-0001-6764-3375"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peipei Song","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6764-3375","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059530979","display_name":"Dan Guo","orcid":"https://orcid.org/0000-0003-2594-254X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Guo","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2594-254X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006278133","display_name":"Angela Yao","orcid":"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":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7418-6141","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377147","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-3094-7735"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3094-7735","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"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":"Tat-Seng Chua","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6097-7807","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78133549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"28","issue":null,"first_page":"1417","last_page":"1430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9886000156402588,"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":0.9886000156402588,"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":0.003800000064074993,"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":0.00139999995008111,"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/oracle","display_name":"Oracle","score":0.6786999702453613},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6632000207901001},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.550599992275238},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5249000191688538},{"id":"https://openalex.org/keywords/grounded-theory","display_name":"Grounded theory","score":0.5210999846458435},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4675999879837036},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.390500009059906},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.38089999556541443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8528000116348267},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6786999702453613},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6632000207901001},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.550599992275238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5321000218391418},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5249000191688538},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.5210999846458435},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4675999879837036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42829999327659607},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.424699991941452},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.390500009059906},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38260000944137573},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.334199994802475},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3149999976158142},{"id":"https://openalex.org/C2779117054","wikidata":"https://www.wikidata.org/wiki/Q1406345","display_name":"Straddle","level":2,"score":0.3125},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2791999876499176},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3639956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3639956","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/G1040185051","display_name":null,"funder_award_id":"62272435","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G24005822","display_name":null,"funder_award_id":"JZ2024AHST0337","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2556245913","display_name":null,"funder_award_id":"JZ2023YQTD0072","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G405190135","display_name":null,"funder_award_id":"U22A2094","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4862433228","display_name":null,"funder_award_id":"62272144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6151690139","display_name":null,"funder_award_id":"62020106007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6973123188","display_name":null,"funder_award_id":"JZ2024HGTG0309","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8480155402","display_name":null,"funder_award_id":"72188101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2053317383","https://openalex.org/W2493916176","https://openalex.org/W2560730294","https://openalex.org/W2896457183","https://openalex.org/W2963541336","https://openalex.org/W2963705779","https://openalex.org/W2979382951","https://openalex.org/W2988326850","https://openalex.org/W3004413500","https://openalex.org/W3034336960","https://openalex.org/W3034636873","https://openalex.org/W3094071022","https://openalex.org/W3109142545","https://openalex.org/W3110575265","https://openalex.org/W3168597991","https://openalex.org/W3175961224","https://openalex.org/W3177934633","https://openalex.org/W3181186176","https://openalex.org/W3181758331","https://openalex.org/W4221155360","https://openalex.org/W4226094317","https://openalex.org/W4304098887","https://openalex.org/W4307778795","https://openalex.org/W4312331087","https://openalex.org/W4312974690","https://openalex.org/W4319300063","https://openalex.org/W4382203033","https://openalex.org/W4383112678","https://openalex.org/W4385245566","https://openalex.org/W4385695880","https://openalex.org/W4385990855","https://openalex.org/W4386071468","https://openalex.org/W4386453561","https://openalex.org/W4387542259","https://openalex.org/W4387546363","https://openalex.org/W4387968089","https://openalex.org/W4388189239","https://openalex.org/W4388189392","https://openalex.org/W4389140516","https://openalex.org/W4389988129","https://openalex.org/W4390872733","https://openalex.org/W4390872994","https://openalex.org/W4390873438","https://openalex.org/W4391216149","https://openalex.org/W4391454521","https://openalex.org/W4394896927","https://openalex.org/W4402727520","https://openalex.org/W4402874874","https://openalex.org/W4413146322","https://openalex.org/W4415399230"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"efforts":[1],"in":[2,99,198],"text-based":[3],"video":[4],"question":[5],"answering":[6],"(TextVideoQA)":[7],"are":[8,243],"criticized":[9],"for":[10,69,112,143,215],"their":[11],"opaque":[12],"decision-making":[13],"and":[14,37,50,101,147,181,190,241],"heavy":[15],"reliance":[16],"on":[17],"scene-text":[18,42,48,64,76,102,124,145,166,222,230],"recognition.":[19,103,231],"In":[20],"this":[21],"paper,":[22],"we":[23,130,153,186],"propose":[24,131],"to":[25,34,176],"study":[26],"<italic":[27,115,158],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[28,116,118,159,164,171,178,246],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Grounded":[29],"TextVideoQA</i>":[30],"by":[31,89],"forcing":[32],"models":[33],"answer":[35,70,87],"questions":[36,180],"spatio-temporally":[38],"localize":[39],"the":[40,83,96,106,109,132,192,206,226,234],"relevant":[41],"regions,":[43],"thus":[44,81],"decoupling":[45],"QA":[46,121],"from":[47],"recognition":[49],"promoting":[51],"research":[52,235],"towards":[53],"interpretable":[54],"QA.":[55],"The":[56],"task":[57],"has":[58],"three-fold":[59],"significance.":[60],"First,":[61],"it":[62,73,94],"encourages":[63],"evidence":[65],"versus":[66],"other":[67],"short-cuts":[68],"predictions.":[71],"Second,":[72],"directly":[74],"accepts":[75],"regions":[77],"as":[78],"visual":[79],"answers,":[80],"circumventing":[82],"problem":[84],"of":[85,108,195,220,236],"ineffective":[86],"evaluation":[88],"stringent":[90],"string":[91],"matching.":[92],"Third,":[93],"isolates":[95],"challenges":[97],"inherited":[98],"VideoQA":[100],"This":[104],"enables":[105],"diagnosis":[107],"root":[110],"causes":[111],"failure":[113],"predictions,":[114],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">e</i>.<italic":[117],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">g</i>.,":[119],"wrong":[120,123],"or":[122],"recognition?":[125],"To":[126,150,232],"achieve":[127],"Grounded":[128,199,237],"TextVideoQA,":[129,238],"T2S-QA":[133,202],"model":[134],"that":[135,225],"highlights":[136],"a":[137,155],"disentangled":[138],"temporal-to-spatial":[139],"contrastive":[140],"learning":[141],"strategy":[142],"weakly-supervised":[144],"grounding":[146],"grounded":[148],"TextVideoQA.":[149,200],"facilitate":[151],"evaluation,":[152],"construct":[154],"new":[156],"dataset":[157,240],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">ViTXT-GQA</i>":[160],"which":[161],"features":[162],"52<bold":[163],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">K</b>":[165,172,179],"bounding":[167],"boxes":[168],"within":[169],"2.2<bold":[170],"temporal":[173],"segments":[174],"related":[175],"2<bold":[177],"729":[182],"videos.":[183],"With":[184],"ViTXT-GQA,":[185],"perform":[187],"extensive":[188],"experiments":[189],"demonstrate":[191],"severe":[193],"limitations":[194],"existing":[196],"techniques":[197],"While":[201],"achieves":[203],"superior":[204],"results,":[205],"large":[207],"performance":[208],"gap":[209],"with":[210],"human":[211],"leaves":[212],"ample":[213],"space":[214],"improvement.":[216],"Our":[217],"further":[218],"analysis":[219],"oracle":[221],"inputs":[223],"posits":[224],"major":[227],"challenge":[228],"is":[229],"advance":[233],"our":[239],"code":[242],"at":[244],"<uri":[245],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/zhousheng97/ViTXT-GQA.git</uri>":[247]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-08T00:00:00"}
