{"id":"https://openalex.org/W4416385983","doi":"https://doi.org/10.1145/3777473","title":"Discriminative Representation Learning for Remote Sensing Visual Question Answering","display_name":"Discriminative Representation Learning for Remote Sensing Visual Question Answering","publication_year":2025,"publication_date":"2025-11-19","ids":{"openalex":"https://openalex.org/W4416385983","doi":"https://doi.org/10.1145/3777473"},"language":"en","primary_location":{"id":"doi:10.1145/3777473","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3777473","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5089018452","display_name":"Yingda Lyu","orcid":"https://orcid.org/0000-0002-2037-6692"},"institutions":[{"id":"https://openalex.org/I106645853","display_name":"Changchun University of Science and Technology","ror":"https://ror.org/007mntk44","country_code":"CN","type":"education","lineage":["https://openalex.org/I106645853"]},{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]},{"id":"https://openalex.org/I4210163951","display_name":"Department of Education of Jilin Province","ror":"https://ror.org/05782e512","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163951"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingda Lyu","raw_affiliation_strings":["College of Computer Science and Technology, Center for Public Education Research, Jilin University, Changchun, China","Center for Public Education Research, Jilin University, China"],"raw_orcid":"https://orcid.org/0000-0002-2037-6692","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Center for Public Education Research, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I106645853"]},{"raw_affiliation_string":"Center for Public Education Research, Jilin University, China","institution_ids":["https://openalex.org/I4210163951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102231030","display_name":"Yan Han","orcid":"https://orcid.org/0009-0002-3797-6763"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Yan","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, Changchun, China","Jilin University, College of Computer Science and Technology, China"],"raw_orcid":"https://orcid.org/0009-0002-3797-6763","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]},{"raw_affiliation_string":"Jilin University, College of Computer Science and Technology, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102030960","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0003-3023-3027"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, Changchun, China","Jilin University, College of Computer Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0003-3023-3027","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]},{"raw_affiliation_string":"Jilin University, College of Computer Science and Technology, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100627248","display_name":"Haipeng Chen","orcid":"https://orcid.org/0000-0002-9410-4120"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haipeng Chen","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, Changchun, China","Jilin University, College of Computer Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-9410-4120","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]},{"raw_affiliation_string":"Jilin University, College of Computer Science and Technology, China","institution_ids":["https://openalex.org/I194450716"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.77359181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"22","issue":"7","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9933000206947327,"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":0.9933000206947327,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.003000000026077032,"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":0.0006000000284984708,"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/discriminative-model","display_name":"Discriminative model","score":0.9144999980926514},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7009000182151794},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6657999753952026},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.656000018119812},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5073999762535095},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.43630000948905945},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4359999895095825},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43140000104904175},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.4138000011444092}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9144999980926514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8486999869346619},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7009000182151794},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6657999753952026},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.656000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5181000232696533},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5073999762535095},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4359999895095825},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4138000011444092},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4066999852657318},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3707999885082245},{"id":"https://openalex.org/C183365957","wikidata":"https://www.wikidata.org/wiki/Q17140402","display_name":"Remote sensing application","level":3,"score":0.3206999897956848},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2946000099182129},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26269999146461487},{"id":"https://openalex.org/C2778102629","wikidata":"https://www.wikidata.org/wiki/Q725252","display_name":"Satellite imagery","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3777473","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3777473","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8209437284","display_name":null,"funder_award_id":"62276112","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2560730294","https://openalex.org/W2597425697","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2963150162","https://openalex.org/W2963383024","https://openalex.org/W2963954913","https://openalex.org/W2964023275","https://openalex.org/W2964138017","https://openalex.org/W2966683369","https://openalex.org/W3012111773","https://openalex.org/W3087338569","https://openalex.org/W3168972675","https://openalex.org/W3175205795","https://openalex.org/W3204588463","https://openalex.org/W3206799531","https://openalex.org/W3209229003","https://openalex.org/W4206437316","https://openalex.org/W4225991573","https://openalex.org/W4229439310","https://openalex.org/W4285818301","https://openalex.org/W4295036294","https://openalex.org/W4309417506","https://openalex.org/W4315880881","https://openalex.org/W4316661266","https://openalex.org/W4360930321","https://openalex.org/W4386472879","https://openalex.org/W4389519587","https://openalex.org/W4393148220","https://openalex.org/W4393149666","https://openalex.org/W4393197781","https://openalex.org/W4394938913","https://openalex.org/W4395041667","https://openalex.org/W4399572612","https://openalex.org/W4399665663","https://openalex.org/W4402473945","https://openalex.org/W4403396149","https://openalex.org/W4404782764","https://openalex.org/W4404809303","https://openalex.org/W4407152340","https://openalex.org/W4409367667","https://openalex.org/W4414360243"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"Remote":[1,155],"Sensing":[2,156],"Visual":[3],"Question":[4],"Answering":[5],"(RSVQA)":[6],"has":[7],"attracted":[8],"increasing":[9],"attention":[10],"from":[11,86,175],"both":[12],"academia":[13],"and":[14,29,42,61,63,77,117,133,180,187,260],"industry,":[15],"which":[16,197],"is":[17,59,80,230],"the":[18,22,54,64,124,129,135,147,154,234,237,252],"basis":[19],"for":[20,45,201],"understanding":[21],"underlying":[23],"correspondence":[24],"between":[25],"remote":[26,55,87,167,215],"sensing":[27,56,88,168,216],"imagery":[28],"text":[30],"descriptions.":[31],"However,":[32],"current":[33],"methods":[34,210],"are":[35,198],"still":[36],"insufficient":[37],"in":[38,166,242],"learning":[39],"discriminative":[40,74,93,139,195],"visual":[41,75,114,131,140,190],"textual":[43],"representations":[44,141,191],"answer":[46,202],"reasoning,":[47],"mainly":[48],"due":[49],"to":[50,72,91,127,137,162,192,232],"two":[51,111],"reasons:":[52],"(1)":[53],"image":[57],"environment":[58,132],"complex":[60],"changeable,":[62],"target":[65],"scales":[66],"vary":[67],"significantly,":[68],"making":[69],"it":[70],"difficult":[71],"extract":[73],"features;":[76],"(2)":[78],"there":[79],"a":[81,100,221],"lack":[82],"of":[83,236,254],"effective":[84],"guidance":[85],"domain":[89],"knowledge":[90,119,178],"learn":[92],"features.":[94,149],"To":[95],"this":[96],"end,":[97],"we":[98,122,152,218],"propose":[99],"D":[101],"iscriminative":[102],"R":[103],"epresentation":[104],"L":[105],"earning":[106],"(DRL)":[107],"method":[108],"that":[109,206],"includes":[110],"key":[112],"strategies:":[113],"feature":[115],"enhancement":[116],"prior":[118,170],"guidance.":[120],"Specifically,":[121],"employ":[123],"Fourier":[125],"transform":[126],"simulate":[128],"diverse":[130],"force":[134],"model":[136],"mine":[138],"by":[142],"imposing":[143],"consistency":[144],"constraints":[145],"with":[146,189],"original":[148],"In":[150],"addition,":[151],"leverage":[153],"Multimodal":[157],"Large":[158],"Language":[159],"Model":[160],"(RSMLLM)":[161],"generate":[163,193],"captions":[164],"rich":[165,238],"domain-specific":[169],"knowledge.":[171],"These":[172],"captions,":[173],"derived":[174],"RSMLLM\u2019s":[176],"powerful":[177],"integration":[179],"summarization":[181],"capabilities,":[182],"can":[183],"then":[184],"be":[185,263],"compared":[186],"fused":[188],"more":[194],"representations,":[196],"ultimately":[199],"used":[200],"reasoning.":[203],"Finally,":[204],"recognizing":[205],"most":[207],"existing":[208],"RSVQA":[209],"rely":[211],"solely":[212],"on":[213],"static":[214],"images,":[217],"introduce":[219],"RSVideoQA,":[220],"novel":[222],"satellite":[223],"video":[224,243],"question":[225],"answering":[226],"dataset.":[227],"This":[228],"dataset":[229,259],"designed":[231],"facilitate":[233],"exploration":[235],"spatio-temporal":[239],"dynamics":[240],"inherent":[241],"sequences.":[244],"Experimental":[245],"results":[246],"across":[247],"three":[248],"distinct":[249],"datasets":[250],"validate":[251],"effectiveness":[253],"our":[255],"proposed":[256],"method.":[257],"Our":[258],"code":[261],"will":[262],"released":[264],"at":[265],"https://github.com/chill-han/DRL":[266],".":[267]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-25T06:16:34.145877","created_date":"2025-11-19T00:00:00"}