{"id":"https://openalex.org/W4413105302","doi":"https://doi.org/10.1145/3760261","title":"Unbiased Embodied Visual Representation Learning with Causal Inference and Cross-Modality Alignment","display_name":"Unbiased Embodied Visual Representation Learning with Causal Inference and Cross-Modality Alignment","publication_year":2025,"publication_date":"2025-08-12","ids":{"openalex":"https://openalex.org/W4413105302","doi":"https://doi.org/10.1145/3760261"},"language":"en","primary_location":{"id":"doi:10.1145/3760261","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3760261","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3760261","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3760261","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102837695","display_name":"Jiaxu Kang","orcid":"https://orcid.org/0009-0006-2135-9532"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxu Kang","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0006-2135-9532","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003059879","display_name":"Bolei Chen","orcid":"https://orcid.org/0000-0002-2784-011X"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bolei Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-2784-011X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002771011","display_name":"Ping Zhong","orcid":"https://orcid.org/0000-0003-3393-8874"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Zhong","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-3393-8874","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yifei Wang","orcid":"https://orcid.org/0009-0006-0973-7721"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifei Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0006-0973-7721","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112896417","display_name":"H.R. Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonan Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0007-1558-7990","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101706948","display_name":"Yu Sheng","orcid":"https://orcid.org/0000-0002-6347-0769"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Sheng","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-6347-0769","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15399478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":"11","first_page":"1","last_page":"23"},"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9990000128746033,"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":0.8087939023971558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6161119341850281},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.5773876309394836},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5669199824333191},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4669206142425537},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45228123664855957},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4491375684738159},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4413367509841919},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.4386269152164459},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.43347904086112976},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.4216083288192749},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4205247759819031},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3769760727882385},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3251364529132843}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8087939023971558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6161119341850281},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.5773876309394836},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5669199824333191},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4669206142425537},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45228123664855957},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4491375684738159},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4413367509841919},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.4386269152164459},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.43347904086112976},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.4216083288192749},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4205247759819031},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3769760727882385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3251364529132843},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3760261","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3760261","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3760261","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3760261","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3760261","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3760261","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.550000011920929,"id":"https://metadata.un.org/sdg/10"},{"display_name":"Peace, Justice and strong institutions","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1737521470","display_name":null,"funder_award_id":"62272489","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5305027673","display_name":null,"funder_award_id":"62172443","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"},{"id":"https://openalex.org/F4320321514","display_name":"Central South University","ror":"https://ror.org/00f1zfq44"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413105302.pdf","grobid_xml":"https://content.openalex.org/works/W4413105302.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2107667896","https://openalex.org/W2194775991","https://openalex.org/W2963150697","https://openalex.org/W3009928773","https://openalex.org/W3035651653","https://openalex.org/W3088940539","https://openalex.org/W3102714038","https://openalex.org/W3172507977","https://openalex.org/W3206022579","https://openalex.org/W3206376852","https://openalex.org/W4236965008","https://openalex.org/W4283640928","https://openalex.org/W4379806366","https://openalex.org/W4379929708","https://openalex.org/W4382657797","https://openalex.org/W4386025780","https://openalex.org/W4386076477","https://openalex.org/W4387624022","https://openalex.org/W4390872665","https://openalex.org/W4393096665","https://openalex.org/W6774562791"],"related_works":["https://openalex.org/W3113091479","https://openalex.org/W2162899405","https://openalex.org/W941090075","https://openalex.org/W2044987316","https://openalex.org/W3134374554","https://openalex.org/W2237480245","https://openalex.org/W2075065631","https://openalex.org/W2519167559","https://openalex.org/W4311248832","https://openalex.org/W4386113923"],"abstract_inverted_index":{"Object":[0],"Goal":[1],"Navigation":[2],"(ObjectNav)":[3],"in":[4,30,46,54,157],"novel":[5],"environments":[6,56],"relies":[7],"on":[8,213],"comprehensive":[9],"scene":[10,28,203],"understanding,":[11],"including":[12],"precise":[13],"visual":[14,48,75],"perception":[15,43,76,105],"and":[16,110,130,206,216],"accurate":[17],"modeling":[18],"of":[19,37,41,81,200,222],"spatial-semantic":[20],"regularities.":[21],"However,":[22],"excessive":[23],"attention":[24],"to":[25,34,69,163,176],"the":[26,35,38,42,47,58,63,70,79,82,90,104,132,153,165,170,182,201,214,220,223],"hand-crafted":[27,51],"representation":[29],"prevailing":[31],"approaches":[32],"leads":[33],"neglect":[36],"negative":[39],"influence":[40],"bias":[44,66,135,155],"hidden":[45,156],"observations.":[49],"The":[50],"semantic":[52,64],"distribution":[53],"domestic":[55],"causes":[57],"spurious":[59,133],"association":[60],"bias,":[61],"while":[62],"conflict":[65],"arises":[67],"due":[68],"dynamic":[71],"perspective":[72],"changes.":[73],"Biased":[74],"significantly":[77],"limits":[78],"generalization":[80],"navigation":[83,225],"strategy.":[84],"In":[85],"this":[86],"article,":[87],"we":[88,114,161,186],"propose":[89,162],"U":[91],"nbiased":[92],"E":[93],"mbodied":[94],"V":[95],"isual":[96],"R":[97],"epresentation":[98],"(":[99,145,173],"UEVR":[100,194],"),":[101],"which":[102,198],"overcomes":[103],"biases":[106],"using":[107],"causal":[108],"inference":[109],"cross-modality":[111,166],"alignment.":[112],"Specifically,":[113],"establish":[115],"reasonable":[116],"assumptions":[117],"about":[118],"confounders":[119],"for":[120],"multi-object":[121],"features":[122],"through":[123,136],"our":[124],"proposed":[125],"Unbiased":[126],"Causal":[127],"R-CNN":[128],"framework":[129,191],"eliminate":[131],"associations":[134],"B":[137],"ackdoor":[138],"I":[139],"ntervention":[140],"C":[141],"ausal":[142],"A":[143],"djustment":[144],"BICA":[146],")":[147,175],"module":[148,205],"during":[149],"navigation.":[150],"To":[151],"overcome":[152],"dynamic-view":[154],"2D":[158,183],"image":[159],"features,":[160],"employ":[164],"alignment":[167],"mechanism":[168],"with":[169,193],"Geometric":[171],"Consistency":[172],"GeoCon":[174],"encode":[177],"3D":[178],"geometry":[179],"prior":[180],"into":[181],"representations.":[184],"Finally,":[185],"design":[187],"a":[188],"modular":[189],"ObjectNav":[190,229],"integrated":[192],"named":[195],"Causal-ObjectNav":[196],",":[197],"consists":[199],"corner-based":[202],"exploration":[204],"target":[207],"object":[208],"discrimination":[209],"module.":[210],"Extensive":[211],"experiments":[212],"MP3D":[215],"HM3D":[217],"datasets":[218],"demonstrate":[219],"superiority":[221],"unbiased":[224],"model":[226],"over":[227],"existing":[228],"methods.":[230]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
