{"id":"https://openalex.org/W4410492211","doi":"https://doi.org/10.1109/tim.2025.3571119","title":"Semantic Distance-Aware Cross-Modal Attention Mechanism for Video Question Answering","display_name":"Semantic Distance-Aware Cross-Modal Attention Mechanism for Video Question Answering","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4410492211","doi":"https://doi.org/10.1109/tim.2025.3571119"},"language":"en","primary_location":{"id":"doi:10.1109/tim.2025.3571119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tim.2025.3571119","pdf_url":null,"source":{"id":"https://openalex.org/S10892749","display_name":"IEEE Transactions on Instrumentation and Measurement","issn_l":"0018-9456","issn":["0018-9456","1557-9662"],"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 Instrumentation and Measurement","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/A5024853469","display_name":"Mingyang Liu","orcid":"https://orcid.org/0000-0002-3630-5821"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyang Liu","raw_affiliation_strings":["School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3630-5821","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090896025","display_name":"Fan Zhou","orcid":"https://orcid.org/0000-0002-0400-9366"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhou","raw_affiliation_strings":["School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0400-9366","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000079751","display_name":"Ruomei Wang","orcid":"https://orcid.org/0000-0002-2712-4412"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruomei Wang","raw_affiliation_strings":["School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2712-4412","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087397999","display_name":"Baoquan Zhao","orcid":"https://orcid.org/0000-0003-0031-7721"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoquan Zhao","raw_affiliation_strings":["School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, China"],"raw_orcid":"https://orcid.org/0000-0003-0031-7721","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045437445","display_name":"Fuwei Zhang","orcid":"https://orcid.org/0000-0003-0179-9988"},"institutions":[{"id":"https://openalex.org/I135714990","display_name":"North University of China","ror":"https://ror.org/047bp1713","country_code":"CN","type":"education","lineage":["https://openalex.org/I135714990"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuwei Zhang","raw_affiliation_strings":["School of Computer Science and Technology, North University of China, Taiyuan, China"],"raw_orcid":"https://orcid.org/0000-0003-0179-9988","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, North University of China, Taiyuan, China","institution_ids":["https://openalex.org/I135714990"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.69994615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"74","issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9988999962806702,"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":0.9909999966621399,"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/computer-science","display_name":"Computer science","score":0.7136370539665222},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5970674753189087},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5512095093727112},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5303614139556885},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5252078175544739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46753212809562683},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36982834339141846},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3538384437561035},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1238536536693573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7136370539665222},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5970674753189087},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5512095093727112},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5303614139556885},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5252078175544739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46753212809562683},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36982834339141846},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3538384437561035},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1238536536693573},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tim.2025.3571119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tim.2025.3571119","pdf_url":null,"source":{"id":"https://openalex.org/S10892749","display_name":"IEEE Transactions on Instrumentation and Measurement","issn_l":"0018-9456","issn":["0018-9456","1557-9662"],"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 Instrumentation and Measurement","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G6519393976","display_name":null,"funder_award_id":"2023A1515011639","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522734439","https://openalex.org/W2079636521","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2606982687","https://openalex.org/W2765716052","https://openalex.org/W2896457183","https://openalex.org/W2904452845","https://openalex.org/W2954199749","https://openalex.org/W2962858109","https://openalex.org/W2962949233","https://openalex.org/W2964051877","https://openalex.org/W2964057271","https://openalex.org/W2964220823","https://openalex.org/W2974161034","https://openalex.org/W2984008963","https://openalex.org/W2997805943","https://openalex.org/W2998166190","https://openalex.org/W3010593057","https://openalex.org/W3023993913","https://openalex.org/W3027790991","https://openalex.org/W3034730770","https://openalex.org/W3035419698","https://openalex.org/W3160817565","https://openalex.org/W3168640669","https://openalex.org/W3172523222","https://openalex.org/W3173367591","https://openalex.org/W3189890868","https://openalex.org/W3197364345","https://openalex.org/W3203995540","https://openalex.org/W3207409917","https://openalex.org/W3217304284","https://openalex.org/W4226289673","https://openalex.org/W4285600797","https://openalex.org/W4292263081","https://openalex.org/W4312246181","https://openalex.org/W4312544061","https://openalex.org/W4312862805","https://openalex.org/W4313163028","https://openalex.org/W4313186260","https://openalex.org/W4319300272","https://openalex.org/W4324116476","https://openalex.org/W4362653417","https://openalex.org/W4377235294","https://openalex.org/W4382998936","https://openalex.org/W4383112678","https://openalex.org/W4385245566","https://openalex.org/W4386902900","https://openalex.org/W4387546363","https://openalex.org/W4387968406","https://openalex.org/W4388692349","https://openalex.org/W4389519587","https://openalex.org/W4389692339","https://openalex.org/W4389988129","https://openalex.org/W4390873420","https://openalex.org/W4391407221","https://openalex.org/W4392399489","https://openalex.org/W4393252595","https://openalex.org/W4402780269","https://openalex.org/W4402980288","https://openalex.org/W4407317130","https://openalex.org/W4408565081","https://openalex.org/W6631190155","https://openalex.org/W6639432524","https://openalex.org/W6719057275","https://openalex.org/W6804277322","https://openalex.org/W6804424445","https://openalex.org/W6838434436","https://openalex.org/W6847435255"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","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","https://openalex.org/W2115758952"],"abstract_inverted_index":{"Precise":[0],"measurement":[1,17,28,41,46,56,98,114,124,134,149,199],"and":[2,9,24,35,48,77,91,104,132,192],"quantification":[3],"of":[4,167],"semantic":[5,37,73,93,119],"relationships":[6],"between":[7,75],"visual":[8,76],"textual":[10,78],"data":[11],"streams":[12],"is":[13,183],"essential":[14],"for":[15],"video-based":[16],"systems,":[18,206],"particularly":[19],"in":[20,33,44,216],"automated":[21],"video":[22,113,153,190],"inspection":[23],"analysis":[25,154],"applications.":[26],"Current":[27],"methodologies":[29],"face":[30],"significant":[31],"challenges":[32],"calibrating":[34],"aligning":[36],"distributions":[38],"across":[39,151,158],"different":[40],"modalities,":[42],"resulting":[43],"reduced":[45],"accuracy":[47,150],"system":[49,82,115],"reliability.":[50],"This":[51,136],"paper":[52],"presents":[53],"a":[54,67,88,97,122,213],"novel":[55],"approach":[57,137],"called":[58],"Semantic":[59],"Distance-aware":[60],"Cross-modal":[61],"Attention":[62],"Mechanism":[63],"(SDCAM),":[64],"which":[65],"introduces":[66],"cross-modal":[68,102],"calibration":[69,103],"function":[70],"to":[71,143,204],"quantify":[72],"disparities":[74],"features.":[79],"The":[80,180],"proposed":[81,169],"employs":[83],"the":[84,165,168],"query":[85,145],"text":[86],"as":[87,96],"reference":[89],"standard":[90],"utilizes":[92],"relative":[94],"distance":[95],"metric,":[99],"enabling":[100],"precise":[101],"measurement.":[105],"Building":[106],"on":[107],"SDCAM,":[108],"we":[109],"develop":[110],"an":[111],"advanced":[112],"that":[116],"achieves":[117],"multi-scale":[118],"alignment":[120],"through":[121,186],"three-stage":[123],"process:":[125],"collaborative":[126],"representation":[127],"measurement,":[128],"hierarchical":[129],"feature":[130],"aggregation,":[131],"contextual":[133,140],"synthesis.":[135],"generates":[138],"comprehensive":[139],"measurements":[141],"tailored":[142],"specific":[144],"parameters,":[146],"significantly":[147],"improving":[148],"diverse":[152],"tasks.":[155],"Experiments":[156],"conducted":[157],"four":[159],"widely":[160],"used":[161],"VideoQA":[162],"datasets":[163],"demonstrate":[164],"superiority":[166],"model":[170,217],"over":[171],"existing":[172],"state-of-the-art":[173],"methods,":[174],"while":[175,207],"reducing":[176],"parameters":[177],"by":[178,201],"62%.":[179],"system\u2019s":[181],"effectiveness":[182],"further":[184],"validated":[185],"integration":[187],"testing":[188],"with":[189],"retrieval":[191],"highlight":[193],"detection":[194],"tasks,":[195],"where":[196],"it":[197],"improves":[198],"precision":[200],"2%":[202],"compared":[203],"baseline":[205],"maintaining":[208],"this":[209],"performance":[210],"advantage":[211],"despite":[212],"42%":[214],"reduction":[215],"parameters.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}