{"id":"https://openalex.org/W4415125283","doi":"https://doi.org/10.1109/icmlt65785.2025.11193324","title":"VideoMamba-LLaVA: Efficient Video Question Answering with Selective Scanning and Lightweight Inference","display_name":"VideoMamba-LLaVA: Efficient Video Question Answering with Selective Scanning and Lightweight Inference","publication_year":2025,"publication_date":"2025-05-23","ids":{"openalex":"https://openalex.org/W4415125283","doi":"https://doi.org/10.1109/icmlt65785.2025.11193324"},"language":"en","primary_location":{"id":"doi:10.1109/icmlt65785.2025.11193324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlt65785.2025.11193324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on Machine Learning Technologies (ICMLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5038931430","display_name":"Rui Zhu","orcid":"https://orcid.org/0000-0003-0831-0145"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhu","raw_affiliation_strings":["National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107943977","display_name":"Tianyuan Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyuan Yu","raw_affiliation_strings":["National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079425523","display_name":"Yanming Guo","orcid":"https://orcid.org/0000-0001-9184-5313"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanming Guo","raw_affiliation_strings":["National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Laboratory for Big Data and Decision,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30515406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"488","last_page":"494"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9958000183105469,"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/encoder","display_name":"Encoder","score":0.6583999991416931},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6570000052452087},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6190999746322632},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6151999831199646},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5611000061035156},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5266000032424927},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5113000273704529},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.45489999651908875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8544999957084656},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6583999991416931},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6570000052452087},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6190999746322632},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6151999831199646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6000000238418579},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5611000061035156},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5266000032424927},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5113000273704529},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47589999437332153},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.45489999651908875},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3716000020503998},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29429998993873596},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2727999985218048}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmlt65785.2025.11193324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlt65785.2025.11193324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on Machine Learning Technologies (ICMLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2425121537","https://openalex.org/W2493922371","https://openalex.org/W2606982687","https://openalex.org/W2617085328","https://openalex.org/W2883429621","https://openalex.org/W2886641317","https://openalex.org/W2963524571","https://openalex.org/W2963820951","https://openalex.org/W2981851019","https://openalex.org/W2984287396","https://openalex.org/W3205497712","https://openalex.org/W4285345750","https://openalex.org/W4313042071","https://openalex.org/W4390465247","https://openalex.org/W4402671548","https://openalex.org/W4403842425"],"related_works":[],"abstract_inverted_index":{"Video":[0],"Question":[1],"Answering":[2],"(VideoQA)":[3],"is":[4],"a":[5,55,71,78,147],"challenging":[6],"task":[7],"that":[8,58,127],"combines":[9],"computer":[10],"vision":[11],"and":[12,84,88,124],"natural":[13],"language":[14,73],"processing":[15],"to":[16,45,82,101,144],"answer":[17],"questions":[18],"about":[19],"video":[20,42,152],"content.":[21],"While":[22],"Large":[23],"Multimodal":[24],"Models":[25],"(LMMs)":[26],"have":[27],"shown":[28],"great":[29],"promise":[30],"in":[31],"this":[32],"domain,":[33],"their":[34],"reliance":[35],"on":[36,119],"fixed-size":[37],"visual":[38,68],"tokens":[39],"extracted":[40],"from":[41],"frames":[43],"leads":[44],"high":[46],"computational":[47,111],"costs.":[48],"To":[49],"address":[50],"this,":[51],"we":[52],"propose":[53],"VideoMamba-LLaVA,":[54],"novel":[56],"framework":[57,105],"integrates":[59],"the":[60,67,97,102,139],"efficient":[61,151],"linear":[62],"complexity":[63],"model":[64,74],"VideoMamba":[65,76,143],"as":[66],"encoder":[69],"with":[70,114,132],"large":[72],"(LLM).":[75],"employs":[77],"selective":[79],"scanning":[80],"mechanism":[81],"retain":[83],"aggregate":[85],"essential":[86],"temporal":[87],"spatial":[89],"information,":[90],"enabling":[91],"lightweight":[92],"inference":[93],"by":[94],"significantly":[95],"reducing":[96],"input":[98],"token":[99],"size":[100],"LLM.":[103],"Our":[104],"achieves":[106],"competitive":[107],"accuracy":[108],"while":[109],"maintaining":[110],"efficiency,":[112],"even":[113],"limited":[115],"tokens.":[116],"Extensive":[117],"experiments":[118],"VideoQA":[120],"benchmarks":[121],"(MSVD-QA,":[122],"MSRVTT-QA,":[123],"TGIF-QA)":[125],"demonstrate":[126],"VideoMamba-LLaVA":[128],"outperforms":[129],"state-of-the-art":[130],"methods":[131],"substantial":[133],"efficiency":[134],"gains.":[135],"This":[136],"work":[137],"introduces":[138],"first":[140],"application":[141],"of":[142],"VideoQA,":[145],"establishing":[146],"new":[148],"benchmark":[149],"for":[150],"reasoning.":[153]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-14T00:00:00"}