{"id":"https://openalex.org/W4415309011","doi":"https://doi.org/10.1109/iccv51701.2025.00109","title":"MMOne: Representing Multiple Modalities in One Scene","display_name":"MMOne: Representing Multiple Modalities in One Scene","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415309011","doi":"https://doi.org/10.1109/iccv51701.2025.00109"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00109","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.11129","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088147402","display_name":"Zhifeng Gu","orcid":"https://orcid.org/0000-0002-3275-0733"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhifeng Gu","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103090753","display_name":"Bing Wang","orcid":"https://orcid.org/0009-0007-6166-7801"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bing Wang","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I14243506"],"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":"1088","last_page":"1098"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.907800018787384,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.907800018787384,"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/modalities","display_name":"Modalities","score":0.840399980545044},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.8102999925613403},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.671500027179718},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45179998874664307},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.41920000314712524},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.4052000045776367},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.3889000117778778},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.3736000061035156}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.840399980545044},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8102999925613403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7056999802589417},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.671500027179718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6510000228881836},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45179998874664307},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3407999873161316},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32109999656677246},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31119999289512634},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2992999851703644},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00109","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:2507.11129","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.11129","pdf_url":"https://arxiv.org/pdf/2507.11129","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},{"id":"doi:10.48550/arxiv.2507.11129","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.11129","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.11129","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.11129","pdf_url":"https://arxiv.org/pdf/2507.11129","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"id":"https://openalex.org/G7956405576","display_name":null,"funder_award_id":"42301520","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Humans":[0],"perceive":[1],"the":[2,12,24,85,111,143],"world":[3],"through":[4],"multimodal":[5,95,118,132],"cues":[6],"to":[7,56,68,83,98,152],"understand":[8],"and":[9,43,122,130,149],"interact":[10],"with":[11,76],"environment.":[13],"Learning":[14],"a":[15,52,72,77,94,127],"scene":[16,133],"representation":[17,144],"for":[18,146],"multiple":[19,58],"modalities":[20,59,115],"enhances":[21,142],"comprehension":[22],"of":[23,88],"physical":[25],"world.":[26],"However,":[27],"modality":[28,73,79,107,148],"conflicts,":[29],"arising":[30],"from":[31],"inherent":[32],"distinctions":[33,113],"among":[34,114],"different":[35],"modalities,":[36],"present":[37],"two":[38],"critical":[39],"challenges:":[40],"property":[41],"disparity":[42],"granularity":[44],"disparity.":[45],"To":[46],"address":[47,110],"these":[48],"challenges,":[49],"we":[50,92],"propose":[51],"general":[53],"framework,":[54],"MMOne,":[55],"represent":[57],"in":[60,126],"one":[61],"scene,":[62],"which":[63],"can":[64],"be":[65],"readily":[66],"extended":[67],"additional":[69,153],"modalities.":[70,154],"Specifically,":[71],"modeling":[74],"module":[75],"novel":[78],"indicator":[80],"is":[81,150,157],"proposed":[82],"capture":[84],"unique":[86],"properties":[87],"each":[89,147],"modality.":[90],"Additionally,":[91],"design":[93],"decomposition":[96],"mechanism":[97],"separate":[99],"multi-modal":[100],"Gaussians":[101,104],"into":[102,120],"single-modal":[103],"based":[105],"on":[106],"differences.":[108],"We":[109],"essential":[112],"by":[116],"disentangling":[117],"information":[119],"shared":[121],"modality-specific":[123],"components,":[124],"resulting":[125],"more":[128],"compact":[129],"efficient":[131],"representation.":[134],"Extensive":[135],"experiments":[136],"demonstrate":[137],"that":[138],"our":[139],"method":[140],"consistently":[141],"capability":[145],"scalable":[151],"The":[155],"code":[156],"available":[158],"at":[159],"https://github.com/Neal2020GitHub/MMOne.":[160]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-18T00:00:00"}
