{"id":"https://openalex.org/W4413145892","doi":"https://doi.org/10.1109/cvpr52734.2025.02250","title":"Efficient Motion-Aware Video MLLM","display_name":"Efficient Motion-Aware Video MLLM","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145892","doi":"https://doi.org/10.1109/cvpr52734.2025.02250"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5102012495","display_name":"Zijia Zhao","orcid":"https://orcid.org/0009-0005-8242-6092"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijia Zhao","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031223720","display_name":"Yuqi Huo","orcid":"https://orcid.org/0009-0009-1202-4791"},"institutions":[{"id":"https://openalex.org/I4210103627","display_name":"BaiCheng Normal University","ror":"https://ror.org/01djkf495","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210103627"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqi Huo","raw_affiliation_strings":["Baichuan Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baichuan Inc","institution_ids":["https://openalex.org/I4210103627"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101322148","display_name":"Tongtian Yue","orcid":"https://orcid.org/0000-0001-5774-4084"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongtian Yue","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040424302","display_name":"Longteng Guo","orcid":"https://orcid.org/0000-0002-4340-4000"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longteng Guo","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030033393","display_name":"Haoyu Lu","orcid":"https://orcid.org/0000-0003-2620-6296"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Lu","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067986384","display_name":"Bingning Wang","orcid":"https://orcid.org/0009-0007-7748-7098"},"institutions":[{"id":"https://openalex.org/I4210103627","display_name":"BaiCheng Normal University","ror":"https://ror.org/01djkf495","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210103627"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingning Wang","raw_affiliation_strings":["Baichuan Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baichuan Inc","institution_ids":["https://openalex.org/I4210103627"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056336684","display_name":"Weipeng Chen","orcid":"https://orcid.org/0000-0001-9293-7578"},"institutions":[{"id":"https://openalex.org/I4210103627","display_name":"BaiCheng Normal University","ror":"https://ror.org/01djkf495","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210103627"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weipeng Chen","raw_affiliation_strings":["Baichuan Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baichuan Inc","institution_ids":["https://openalex.org/I4210103627"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077083938","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0002-4313-7272"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0156,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9123652,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"24159","last_page":"24168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9940999746322632,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9901000261306763,"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/computer-science","display_name":"Computer science","score":0.6624044179916382},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5156811475753784},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.48388418555259705},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.44172191619873047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.387920618057251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6624044179916382},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5156811475753784},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.48388418555259705},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.44172191619873047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.387920618057251}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Most":[0],"current":[1],"video":[2,31,36,62,128,149],"MLLMs":[3],"rely":[4],"on":[5,123,147],"uniform":[6],"frame":[7],"sampling":[8],"and":[9,17,52,92,113,126],"image-level":[10],"encoders,":[11],"resulting":[12],"in":[13,59,82],"inefficient":[14],"data":[15],"processing":[16],"limited":[18],"motion":[19,53,80,94,104,108],"awareness.":[20],"To":[21],"address":[22],"these":[23],"challenges,":[24],"we":[25,97],"introduce":[26,98],"EMA,":[27],"an":[28],"Efficient":[29],"Motion-Aware":[30],"MLLM":[32],"that":[33,49,118],"utilizes":[34],"compressed":[35,61],"structures":[37],"as":[38,141],"inputs.":[39],"We":[40],"propose":[41],"a":[42,56,100],"motion-aware":[43],"GOP":[44,57],"(Group":[45],"of":[46],"Pictures)":[47],"encoder":[48],"fuses":[50],"spatial":[51],"information":[54],"within":[55],"unit":[58],"the":[60],"stream,":[63],"generating":[64],"compact,":[65],"informative":[66],"visual":[67],"tokens.":[68],"By":[69],"integrating":[70],"fewer":[71],"but":[72,78],"denser":[73],"RGB":[74],"frames":[75],"with":[76],"more":[77],"sparser":[79],"vectors":[81],"this":[83],"native":[84],"slow-fast":[85],"input":[86],"architecture,":[87],"our":[88],"approach":[89],"reduces":[90],"redundancy":[91],"enhances":[93],"representation.":[95],"Additionally,":[96],"MotionBench,":[99],"benchmark":[101],"for":[102],"evaluating":[103],"understanding":[105,150],"across":[106],"four":[107],"types:":[109],"linear,":[110],"curved,":[111],"rotational,":[112],"contact-based.":[114],"Experimental":[115],"results":[116],"show":[117],"EMA":[119,137],"achieves":[120],"state-of-the-art":[121],"performance":[122,146],"both":[124],"MotionBench":[125],"popular":[127],"question":[129],"answering":[130],"benchmarks,":[131],"while":[132],"reducing":[133],"inference":[134],"costs.":[135],"Moreover,":[136],"demonstrates":[138],"strong":[139],"scalability,":[140],"evidenced":[142],"by":[143],"its":[144],"competitive":[145],"long":[148],"benchmarks.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}