{"id":"https://openalex.org/W4413145095","doi":"https://doi.org/10.1109/cvpr52734.2025.01773","title":"VideoGLaMM : A Large Multimodal Model for Pixel-Level Visual Grounding in Videos","display_name":"VideoGLaMM : A Large Multimodal Model for Pixel-Level Visual Grounding in Videos","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145095","doi":"https://doi.org/10.1109/cvpr52734.2025.01773"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01773","doi":"https://doi.org/10.1109/cvpr52734.2025.01773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01773","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"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"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.04923","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007081590","display_name":"Shehan Munasinghe","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Shehan Munasinghe","raw_affiliation_strings":["Mohamed bin Zayed University of AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of AI","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043165192","display_name":"Hanan Gani","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Hanan Gani","raw_affiliation_strings":["Mohamed bin Zayed University of AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of AI","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016293792","display_name":"Wenqi Zhu","orcid":"https://orcid.org/0000-0001-7832-189X","observed_orcids":["https://orcid.org/0000-0001-7832-189X"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqi Zhu","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037129512","display_name":"Jiale Cao","orcid":"https://orcid.org/0000-0002-5160-6841","observed_orcids":["https://orcid.org/0000-0002-5160-6841"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Cao","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009547049","display_name":"Eric P. Xing","orcid":"https://orcid.org/0009-0005-9158-4201","observed_orcids":["https://orcid.org/0009-0005-9158-4201","https://orcid.org/0000-0002-3683-4280"]},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Eric Xing","raw_affiliation_strings":["Mohamed bin Zayed University of AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of AI","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760570","display_name":"Fahad Shahbaz Khan","orcid":"https://orcid.org/0000-0002-4263-3143","observed_orcids":["https://orcid.org/0000-0002-4263-3143"]},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Fahad Shahbaz Khan","raw_affiliation_strings":["Mohamed bin Zayed University of AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of AI","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101483978","display_name":"Salman Khan","orcid":"https://orcid.org/0000-0001-8732-3395","observed_orcids":["https://orcid.org/0000-0001-8732-3395"]},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Salman Khan","raw_affiliation_strings":["Mohamed bin Zayed University of AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of AI","institution_ids":["https://openalex.org/I4210113480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.6125,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.98903441,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"19036","last_page":"19046"},"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/video-grounding","display_name":"video grounding","score":0.4729999899864197},{"id":"https://openalex.org/keywords/large-multimodal-models","display_name":"large multimodal models","score":0.9190000295639038},{"id":"https://openalex.org/keywords/vision-language-alignment","display_name":"vision-language alignment","score":0.7400000095367432},{"id":"https://openalex.org/keywords/vision-encoder","display_name":"vision encoder","score":0.7289999723434448},{"id":"https://openalex.org/keywords/video-text-alignment","display_name":"video-text alignment","score":0.33000001311302185},{"id":"https://openalex.org/keywords/multimodal-dataset","display_name":"multimodal dataset","score":0.5680000185966492}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.759675920009613},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6602179408073425},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5808613300323486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5473766326904297},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.48487553000450134},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3543951213359833},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08717069029808044},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0474492609500885}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01773","doi":"https://doi.org/10.1109/cvpr52734.2025.01773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01773","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"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"},{"id":"pmh:oai:arXiv.org:2411.04923","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.04923","pdf_url":"https://arxiv.org/pdf/2411.04923","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,"listed_in":[],"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.04923","doi":"https://doi.org/10.48550/arxiv.2411.04923","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.04923","pdf_url":null,"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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.04923","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.04923","pdf_url":"https://arxiv.org/pdf/2411.04923","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,"listed_in":[],"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413145095.pdf","grobid_xml":"https://content.openalex.org/works/W4413145095.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2251512949","https://openalex.org/W2561196672","https://openalex.org/W2737258237","https://openalex.org/W2793407941","https://openalex.org/W2968101724","https://openalex.org/W3035590142","https://openalex.org/W3081168214","https://openalex.org/W3104844437","https://openalex.org/W3166712493","https://openalex.org/W4285294723","https://openalex.org/W4312517005","https://openalex.org/W4312614039","https://openalex.org/W4312649925","https://openalex.org/W4319300361","https://openalex.org/W4386071509","https://openalex.org/W4386075561","https://openalex.org/W4389519587","https://openalex.org/W4390872914","https://openalex.org/W4390874575","https://openalex.org/W4402671548","https://openalex.org/W4402704551","https://openalex.org/W4402727018","https://openalex.org/W4402727764","https://openalex.org/W4402754134","https://openalex.org/W4404724811","https://openalex.org/W4404784276"],"related_works":["https://openalex.org/W7106314791","https://openalex.org/W4388963747","https://openalex.org/W4416035957","https://openalex.org/W4415961091","https://openalex.org/W7155093361","https://openalex.org/W7136316570","https://openalex.org/W7137880032","https://openalex.org/W4414581696","https://openalex.org/W4402727018","https://openalex.org/W7148844004"],"abstract_inverted_index":{"Fine-grained":[0],"alignment":[1],"between":[2],"videos":[3,48],"and":[4,12,73,76,91,108,148,163],"text":[5],"is":[6,86,102],"challenging":[7,156],"due":[8],"to":[9,104],"complex":[10],"spatial":[11,72,107],"temporal":[13,74,109],"dynamics":[14],"in":[15,32,47,136],"videos.":[16,33],"Existing":[17],"video-based":[18],"Large":[19,62],"Multimodal":[20],"Models":[21],"(LMMs)":[22],"handle":[23],"basic":[24],"conversations":[25,129],"but":[26],"struggle":[27],"with":[28,114,145],"precise":[29],"pixel-level":[30,45],"grounding":[31,46],"To":[34,117],"address":[35],"this,":[36],"we":[37,121],"introduce":[38],"VideoGLaMM,":[39],"a":[40,61,65,77,123,131,137],"LMM":[41],"designed":[42],"for":[43,80],"fine-grained":[44,119],"based":[49],"on":[50,154],"user-provided":[51],"textual":[52,115],"inputs.":[53],"Our":[54],"design":[55],"seamlessly":[56],"connects":[57],"three":[58,155,179],"key":[59],"components:":[60],"Language":[63],"Model,":[64],"dual":[66],"vision":[67],"encoder":[68],"that":[69,94,170],"emphasizes":[70],"both":[71,106],"details,":[75],"spatio-temporal":[78],"decoder":[79],"accurate":[81],"mask":[82],"generation.":[83],"This":[84],"connection":[85],"facilitated":[87],"via":[88],"tunable":[89],"V\u2192L":[90],"L\u2192V":[92],"adapters":[93],"enable":[95,118],"close":[96],"Vision-Language":[97],"(VL)":[98],"alignment.":[99],"The":[100],"architecture":[101],"trained":[103],"synchronize":[105],"elements":[110],"of":[111,140],"video":[112],"content":[113],"instructions.":[116],"grounding,":[120],"curate":[122],"multimodal":[124],"dataset":[125],"featuring":[126],"detailed":[127],"visually-grounded":[128],"using":[130],"semiautomatic":[132],"annotation":[133],"pipeline,":[134],"resulting":[135],"diverse":[138],"set":[139],"38k":[141],"video-QA":[142],"triplets":[143],"along":[144],"83k":[146],"objects":[147],"671k":[149],"masks.":[150],"We":[151],"evaluate":[152],"VideoGLaMM":[153],"tasks:":[157],"Grounded":[158],"Conversation":[159],"Generation,":[160],"Visual":[161],"Grounding,":[162],"Referring":[164],"Video":[165],"Segmentation.":[166],"Experimental":[167],"results":[168],"show":[169],"our":[171],"model":[172],"consistently":[173],"outperforms":[174],"existing":[175],"approaches":[176],"across":[177],"all":[178],"tasks.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":5}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-10-10T00:00:00"}