{"id":"https://openalex.org/W4417493396","doi":"https://doi.org/10.1109/iccv51701.2025.02198","title":"DynImg: Key Frames with Visual Prompts are Good Representation for Multi-Modal Video Understanding","display_name":"DynImg: Key Frames with Visual Prompts are Good Representation for Multi-Modal Video Understanding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417493396","doi":"https://doi.org/10.1109/iccv51701.2025.02198"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.15569","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039389811","display_name":"Xiaoyi Bao","orcid":"https://orcid.org/0000-0002-5525-0694"},"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":"Xiaoyi Bao","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101500407","display_name":"Chen-Wei Xie","orcid":"https://orcid.org/0000-0003-1124-3422"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenwei Xie","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009743096","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-3379-1924"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Tang","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tingyu Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tingyu Weng","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038696302","display_name":"Xiao\u2010Feng Wang","orcid":"https://orcid.org/0000-0002-1628-6547"},"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":"Xiaofeng Wang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103234841","display_name":"Yun Zheng","orcid":"https://orcid.org/0009-0001-5767-014X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Zheng","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026151620","display_name":"Xingang Wang","orcid":"https://orcid.org/0000-0002-6851-0109"},"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":"Xingang Wang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23678","last_page":"23688"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9739999771118164,"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":0.9739999771118164,"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":0.003800000064074993,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.002099999925121665,"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/set","display_name":"Set (abstract data type)","score":0.5956000089645386},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5758000016212463},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5315999984741211},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5203999876976013},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.47999998927116394},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4683000147342682},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.4415999948978424},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4169999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763000130653381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5979999899864197},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5956000089645386},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5758000016212463},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5203999876976013},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.47999998927116394},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4415999948978424},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4277999997138977},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3384999930858612},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33480000495910645},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.28679999709129333},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C110484373","wikidata":"https://www.wikidata.org/wiki/Q264398","display_name":"Adjacency list","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccv51701.2025.02198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.15569","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15569","pdf_url":"https://arxiv.org/pdf/2507.15569","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.15569","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15569","pdf_url":"https://arxiv.org/pdf/2507.15569","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"the":[3,51,108,115,124,131,142,159,169,182,194],"introduction":[4],"of":[5,54,100,117,164,196],"Multi-modal":[6],"Large":[7],"Language":[8],"Models":[9],"(MLLMs)":[10],"into":[11],"video":[12,79,89,152,190,202],"understanding":[13,191],"tasks":[14],"has":[15],"become":[16],"increasingly":[17],"prevalent.":[18],"However,":[19],"how":[20],"to":[21,40,48,61,106,126,130,136,140],"effectively":[22],"integrate":[23],"temporal":[24,36,104,160,198],"information":[25,37,53],"remains":[26],"a":[27,98,149],"critical":[28],"research":[29],"focus.":[30],"Traditional":[31],"approaches":[32],"treat":[33],"spatial":[34,52,68,109,133,162],"and":[35,78,161],"separately.":[38],"Due":[39],"issues":[41],"like":[42],"motion":[43],"blur,":[44],"it":[45],"is":[46],"challenging":[47],"accurately":[49],"represent":[50],"rapidly":[55],"moving":[56],"objects.":[57,113],"This":[58,156],"can":[59],"lead":[60],"temporally":[62],"important":[63],"regions":[64],"being":[65],"underemphasized":[66],"during":[67],"feature":[69,119],"extraction,":[70,120],"which":[71],"in":[72,200],"turn":[73],"hinders":[74],"accurate":[75],"spatio-temporal":[76,170],"interaction":[77],"understanding.":[80],"To":[81],"address":[82],"this":[83,173],"limitation,":[84],"we":[85,96,147],"propose":[86],"an":[87],"innovative":[88],"representation":[90],"method":[91],"called":[92],"Dynamic-Image":[93],"(DynImg).":[94],"Specifically,":[95],"introduce":[97],"set":[99],"non-key":[101],"frames":[102],"as":[103],"prompts":[105,122,199],"highlight":[107],"areas":[110],"containing":[111],"fast-moving":[112],"During":[114],"process":[116],"visual":[118],"these":[121,137],"guide":[123],"model":[125],"pay":[127],"additional":[128],"attention":[129],"fine-grained":[132],"features":[134],"corresponding":[135,150],"regions.":[138],"Moreover,":[139],"maintain":[141],"correct":[143],"sequence":[144],"for":[145],"DynImg,":[146,165],"employ":[148],"4D":[151],"Rotary":[153],"Position":[154],"Embedding.":[155],"retains":[157],"both":[158],"adjacency":[163],"helping":[166],"MLLM":[167],"understand":[168],"order":[171],"within":[172],"combined":[174],"format.":[175],"Experimental":[176],"evaluations":[177],"reveal":[178],"that":[179],"DynImg":[180],"surpasses":[181],"state-of-the-art":[183],"methods":[184],"by":[185],"approximately":[186],"2%":[187],"across":[188],"multiple":[189],"benchmarks,":[192],"proving":[193],"effectiveness":[195],"our":[197],"enhancing":[201],"comprehension.":[203]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}