{"id":"https://openalex.org/W3217304284","doi":"https://doi.org/10.1109/tmm.2022.3185900","title":"LiVLR: A Lightweight Visual-Linguistic Reasoning Framework for Video Question Answering","display_name":"LiVLR: A Lightweight Visual-Linguistic Reasoning Framework for Video Question Answering","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W3217304284","doi":"https://doi.org/10.1109/tmm.2022.3185900","mag":"3217304284"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3185900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3185900","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/A5101477192","display_name":"Jingjing Jiang","orcid":"https://orcid.org/0000-0002-8241-4877"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Jiang","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shannxi, China"],"raw_orcid":"https://orcid.org/0000-0002-8241-4877","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shannxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383203","display_name":"Ziyi Liu","orcid":"https://orcid.org/0000-0002-2407-9599"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyi Liu","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shannxi, China"],"raw_orcid":"https://orcid.org/0000-0002-2407-9599","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shannxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047405956","display_name":"Nanning Zheng","orcid":"https://orcid.org/0000-0003-1608-8257"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shannxi, China"],"raw_orcid":"https://orcid.org/0000-0003-1608-8257","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, Shannxi, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":1.462,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.81827152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"5002","last_page":"5013"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9990000128746033,"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":0.9958999752998352,"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/notation","display_name":"Notation","score":0.6377374529838562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5502649545669556},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.49446845054626465},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4396301209926605},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.43679705262184143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41685599088668823},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35019543766975403},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3385833203792572},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2339959740638733},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.09026288986206055}],"concepts":[{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.6377374529838562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5502649545669556},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.49446845054626465},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4396301209926605},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.43679705262184143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41685599088668823},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35019543766975403},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3385833203792572},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2339959740638733},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.09026288986206055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3185900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3185900","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G1534200972","display_name":null,"funder_award_id":"61773312","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","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":110,"referenced_works":["https://openalex.org/W637153065","https://openalex.org/W1514535095","https://openalex.org/W1522734439","https://openalex.org/W1662382123","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1839118408","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2116341502","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2325939864","https://openalex.org/W2425121537","https://openalex.org/W2519887557","https://openalex.org/W2600702321","https://openalex.org/W2606982687","https://openalex.org/W2613718673","https://openalex.org/W2624431344","https://openalex.org/W2745461083","https://openalex.org/W2765716052","https://openalex.org/W2788919350","https://openalex.org/W2808877322","https://openalex.org/W2883429621","https://openalex.org/W2890531016","https://openalex.org/W2890904455","https://openalex.org/W2908510526","https://openalex.org/W2908633661","https://openalex.org/W2916723116","https://openalex.org/W2936215830","https://openalex.org/W2946752867","https://openalex.org/W2949692512","https://openalex.org/W2950178297","https://openalex.org/W2950541952","https://openalex.org/W2951545716","https://openalex.org/W2954199749","https://openalex.org/W2962767366","https://openalex.org/W2962934715","https://openalex.org/W2962949233","https://openalex.org/W2963150697","https://openalex.org/W2963319519","https://openalex.org/W2963403868","https://openalex.org/W2963524571","https://openalex.org/W2963532541","https://openalex.org/W2963541336","https://openalex.org/W2963858333","https://openalex.org/W2963907629","https://openalex.org/W2964015378","https://openalex.org/W2964057271","https://openalex.org/W2964311892","https://openalex.org/W2964321699","https://openalex.org/W2969127500","https://openalex.org/W2969332757","https://openalex.org/W2981582341","https://openalex.org/W2981985547","https://openalex.org/W2982139784","https://openalex.org/W2988823324","https://openalex.org/W2997344006","https://openalex.org/W2997789966","https://openalex.org/W2997805943","https://openalex.org/W2998166190","https://openalex.org/W2998423439","https://openalex.org/W3004349648","https://openalex.org/W3010343788","https://openalex.org/W3034636873","https://openalex.org/W3034730770","https://openalex.org/W3034943799","https://openalex.org/W3034972674","https://openalex.org/W3035167603","https://openalex.org/W3035218869","https://openalex.org/W3035356601","https://openalex.org/W3035393139","https://openalex.org/W3035454069","https://openalex.org/W3043670582","https://openalex.org/W3043990051","https://openalex.org/W3089373619","https://openalex.org/W3089709427","https://openalex.org/W3117181316","https://openalex.org/W3167092180","https://openalex.org/W3168640669","https://openalex.org/W3172523222","https://openalex.org/W3173223111","https://openalex.org/W3173367591","https://openalex.org/W3176398504","https://openalex.org/W3181758331","https://openalex.org/W3197457832","https://openalex.org/W3207736102","https://openalex.org/W4285723986","https://openalex.org/W4288351558","https://openalex.org/W4288373939","https://openalex.org/W4294558607","https://openalex.org/W4299522971","https://openalex.org/W4385245566","https://openalex.org/W6620673361","https://openalex.org/W6630875275","https://openalex.org/W6637178625","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6638946568","https://openalex.org/W6720006811","https://openalex.org/W6726873649","https://openalex.org/W6738893770","https://openalex.org/W6738964360","https://openalex.org/W6739901393","https://openalex.org/W6757812085","https://openalex.org/W6757817989","https://openalex.org/W6760837195","https://openalex.org/W6763464472","https://openalex.org/W6779099115","https://openalex.org/W6787255299"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2504004674","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W2498744856","https://openalex.org/W763418848"],"abstract_inverted_index":{"Video":[0],"Question":[1],"Answering":[2],"(VideoQA),":[3],"aiming":[4],"to":[5,20,38,53,75],"correctly":[6],"answer":[7],"a":[8,33,62],"given":[9],"question":[10],"based":[11],"on":[12,131],"understanding":[13],"multimodal":[14],"video":[15,25,31,41,51],"content,":[16],"is":[17],"challenging":[18],"due":[19],"the":[21,24,28,40,84,90,102,112,119,144,147],"richness":[22],"of":[23,30,99,114,146],"content.":[26,56],"From":[27],"perspective":[29],"understanding,":[32],"complete":[34],"VideoQA":[35,133],"framework":[36,66],"needs":[37],"understand":[39],"content":[42,52],"at":[43],"different":[44,97,115],"semantic":[45],"levels":[46],"and":[47,72,79,126,138],"flexibly":[48,110],"integrate":[49],"diverse":[50],"distill":[54],"question-related":[55,120],"To":[57],"this":[58],"end,":[59],"we":[60],"propose":[61],"Lightweight":[63],"Visual-Linguistic":[64,93],"Reasoning":[65,94],"named$\\text{LiVLR}$.":[67],"Specifically,$\\text{LiVLR}$first":[68],"utilizes":[69],"graph-based":[70],"visual":[71,78],"linguistic":[73,80],"encoders":[74],"obtain":[76],"multi-grained":[77],"representations,":[81],"respectively.":[82],"Subsequently,":[83],"obtained":[85],"representations":[86,100,116],"are":[87],"integrated":[88],"with":[89,101],"devised":[91],"Diversity-aware":[92],"module":[95],"($\\text{DaVL}$).$\\text{DaVL}$distinguishes":[96],"types":[98],"learnable":[103],"index":[104],"embedding":[105],"in":[106],"graph":[107],"embedding.":[108],"Therefore,$\\text{DaVL}$can":[109],"adjust":[111],"importance":[113],"when":[117],"generating":[118],"joint":[121],"representation.":[122],"The":[123],"proposed$\\text{LiVLR}$is":[124],"lightweight":[125],"shows":[127],"its":[128],"performance":[129],"advantage":[130],"three":[132],"benchmarks,":[134],"MRSVTT-QA,":[135],"KnowIT":[136],"VQA,":[137],"TVQA.":[139],"Extensive":[140],"ablation":[141],"studies":[142],"demonstrate":[143],"effectiveness":[145],"key":[148],"components":[149],"of$\\text{LiVLR}$.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}