{"id":"https://openalex.org/W7225188382","doi":"https://doi.org/10.48550/arxiv.2611.02356","title":"Exploiting Textual Semantics for Robust Cross-View Object Correspondence","display_name":"Exploiting Textual Semantics for Robust Cross-View Object Correspondence","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225188382","doi":"https://doi.org/10.48550/arxiv.2611.02356"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.02356","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02356","pdf_url":"https://arxiv.org/pdf/2611.02356","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.02356","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124411724","display_name":"Bing Fan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Bing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160482711","display_name":"Yunhe Feng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Yunhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160563946","display_name":"Yan Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160523176","display_name":"Heng Fan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Heng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.8320000171661377,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.8320000171661377,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.15209999680519104,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.007000000216066837,"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/text-semantics","display_name":"text semantics","score":0.7179999947547913},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7689999938011169},{"id":"https://openalex.org/keywords/viewpoint-invariance","display_name":"viewpoint invariance","score":0.7260000109672546},{"id":"https://openalex.org/keywords/appearance-variation","display_name":"appearance variation","score":0.8740000128746033},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"video retrieval","score":0.5149999856948853},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.6159999966621399},{"id":"https://openalex.org/keywords/object-localization","display_name":"object localization","score":0.46000000834465027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8151000142097473},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.66839998960495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6449999809265137},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6291999816894531},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5877000093460083},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4519999921321869},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4440999925136566},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38089999556541443},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.3287000060081482},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3091999888420105},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30320000648498535},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.02356","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02356","pdf_url":"https://arxiv.org/pdf/2611.02356","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2611.02356","doi":"https://doi.org/10.48550/arxiv.2611.02356","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.02356","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:2611.02356","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02356","pdf_url":"https://arxiv.org/pdf/2611.02356","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415540255","https://openalex.org/W7160321844","https://openalex.org/W4417076960","https://openalex.org/W7131421821","https://openalex.org/W4417097417","https://openalex.org/W7224104931","https://openalex.org/W7168379883","https://openalex.org/W3008449400","https://openalex.org/W7160822890","https://openalex.org/W7160130767"],"abstract_inverted_index":{"Cross-view":[0],"object":[1,75,181],"correspondence":[2,111],"(CVOC)":[3],"aims":[4],"to":[5,47,69,104,142,223,231],"establish":[6],"associations":[7],"of":[8,64,83,125],"the":[9,126,129,149,165,192,216],"same":[10],"target":[11,50,127,178,193],"between":[12],"query":[13,131],"and":[14,43,94,98,107,137,229,239,245],"search":[15,150],"videos":[16],"captured":[17],"from":[18,128],"different":[19],"viewpoints.":[20],"Existing":[21],"methods":[22,34],"often":[23],"rely":[24],"on":[25,237],"visual":[26,71,105,144,169,227],"cues":[27,106,187],"for":[28,73,146,180],"CVOC.":[29],"Despite":[30],"recent":[31],"progress,":[32],"these":[33],"struggle":[35],"in":[36,67,113,148,194],"complicated":[37,114],"scenarios":[38],"with":[39,171,191],"substantial":[40],"viewpoint":[41],"changes":[42],"appearance":[44],"variations,":[45],"due":[46],"lacking":[48],"sufficient":[49],"information.":[51],"Addressing":[52],"this,":[53,118,154],"we":[54,155,198],"introduce":[55,156],"TeSCo,":[56],"a":[57,84,122,134,157],"framework":[58],"that":[59,163,207],"exploits":[60],"rich":[61],"Textual":[62],"Semantics":[63],"an":[65,200],"object,":[66],"addition":[68],"its":[70,251],"cues,":[72],"cross-view":[74],"Correspondence.":[76],"Our":[77,253],"key":[78],"insight":[79],"is,":[80],"textual":[81,123,140,166,186,202,210,221],"description":[82],"target,":[85],"by":[86,117],"capturing":[87],"diverse":[88],"attributes":[89],"such":[90],"as":[91],"category,":[92],"texture,":[93],"color,":[95],"provides":[96],"viewpoint-":[97],"appearance-invariant":[99],"semantics,":[100],"which":[101],"are":[102,188],"complementary":[103],"can":[108],"hence":[109],"enhance":[110,143],"robustness":[112],"scenes.":[115],"Inspired":[116],"TeSCo":[119,241],"first":[120],"generates":[121],"expression":[124],"given":[130],"view":[132],"using":[133,212],"vision-language":[135],"model,":[136],"then":[138],"extracts":[139],"feature":[141,167,203,211],"features":[145,170,228],"localization":[147],"view.":[151],"To":[152],"realize":[153],"text-conditioned":[158],"cross-modal":[159],"fusion":[160],"(TCF)":[161],"module":[162,206],"incorporates":[164],"into":[168,226],"text-guided":[172],"modulation,":[173],"producing":[174],"more":[175],"robust":[176],"multimodal":[177],"representation":[179],"correspondence.":[182],"Since":[183],"not":[184],"all":[185],"equally":[189],"compatible":[190],"current":[195],"search-view":[196,213],"frame,":[197],"propose":[199],"iterative":[201],"refinement":[204],"(ITFR)":[205],"progressively":[208],"adjusts":[209],"information":[214],"before":[215],"TCF":[217],"module,":[218],"enabling":[219],"search-view-aware":[220],"semantics":[222],"be":[224],"fused":[225],"leading":[230],"better":[232],"performance.":[233],"In":[234],"extensive":[235],"experiments":[236],"Ego-Exo4D":[238],"HANDAL-X,":[240],"demonstrates":[242],"state-of-the-art":[243],"results":[244],"largely":[246],"outperforms":[247],"other":[248],"models,":[249],"validating":[250],"efficacy.":[252],"code":[254],"is":[255],"released":[256],"at":[257],"https://github.com/VAIL-Fan/TeSCo.":[258]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-04T00:00:00"}