{"id":"https://openalex.org/W4402980625","doi":"https://doi.org/10.1109/icme57554.2024.10687928","title":"Structure-aware Residual-center Representation for Self-Supervised Open-set 3D Cross-modal Retrieval","display_name":"Structure-aware Residual-center Representation for Self-Supervised Open-set 3D Cross-modal Retrieval","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980625","doi":"https://doi.org/10.1109/icme57554.2024.10687928"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099043514","display_name":"Yang Xu","orcid":"https://orcid.org/0000-0002-8691-2726"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Xu","raw_affiliation_strings":["Tsinghua University,School of Software"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Software","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101819284","display_name":"Yifan Feng","orcid":"https://orcid.org/0000-0003-0878-2986"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Feng","raw_affiliation_strings":["Tsinghua University,School of Software"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Software","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043832320","display_name":"Yu Jiang","orcid":"https://orcid.org/0000-0001-8828-7832"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Jiang","raw_affiliation_strings":["Jilin University,College of Computer Science and Technology"],"affiliations":[{"raw_affiliation_string":"Jilin University,College of Computer Science and Technology","institution_ids":["https://openalex.org/I194450716"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5099043514"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.0526,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.78431031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9951000213623047,"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":0.9822999835014343,"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/modal","display_name":"Modal","score":0.7326325178146362},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6913809776306152},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6355810165405273},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5394784212112427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5189478397369385},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5179795026779175},{"id":"https://openalex.org/keywords/center","display_name":"Center (category theory)","score":0.5168726444244385},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40926575660705566},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38157325983047485},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3465626835823059},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32758551836013794},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23521921038627625}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7326325178146362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6913809776306152},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6355810165405273},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5394784212112427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5189478397369385},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5179795026779175},{"id":"https://openalex.org/C2779463800","wikidata":"https://www.wikidata.org/wiki/Q5062222","display_name":"Center (category theory)","level":2,"score":0.5168726444244385},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40926575660705566},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38157325983047485},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3465626835823059},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32758551836013794},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23521921038627625},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C8010536","wikidata":"https://www.wikidata.org/wiki/Q160398","display_name":"Crystallography","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1920022804","https://openalex.org/W1964073652","https://openalex.org/W2021122545","https://openalex.org/W2080067164","https://openalex.org/W2765440071","https://openalex.org/W2900802124","https://openalex.org/W2954672622","https://openalex.org/W3134961575","https://openalex.org/W3177034761","https://openalex.org/W3196056489","https://openalex.org/W3207409407","https://openalex.org/W4282926996","https://openalex.org/W4386072138","https://openalex.org/W6631216910","https://openalex.org/W6639103823","https://openalex.org/W6858567493"],"related_works":["https://openalex.org/W2560215812","https://openalex.org/W2949601986","https://openalex.org/W2788972299","https://openalex.org/W2498789492","https://openalex.org/W2521347458","https://openalex.org/W2729981612","https://openalex.org/W4233449973","https://openalex.org/W2925692864","https://openalex.org/W2768526084","https://openalex.org/W151988857"],"abstract_inverted_index":{"Existing":[0],"methods":[1],"of":[2,122],"3D":[3,43],"cross-modal":[4,44],"retrieval":[5],"heavily":[6],"lean":[7],"on":[8,104,116],"category":[9,53,77],"distribution":[10,54],"priors":[11],"within":[12],"the":[13,34,48,58,74,82,90,120],"training":[14],"set,":[15],"which":[16],"diminishes":[17],"their":[18],"efficacy":[19],"when":[20],"tasked":[21],"with":[22],"unseen":[23],"categories":[24],"under":[25],"open-set":[26,42],"environments.":[27],"To":[28,46],"tackle":[29],"this":[30],"problem,":[31],"we":[32,56,80],"propose":[33],"Structure-Aware":[35],"Residual-Center":[36,59],"Representation":[37],"(SRCR)":[38],"framework":[39,125],"for":[40,62,95],"self-supervised":[41],"retrieval.":[45],"address":[47],"center":[49],"deviation":[50],"due":[51],"to":[52,73,88,127],"differences,":[55],"utilize":[57],"Embedding":[60],"(RCE)":[61],"each":[63],"object":[64],"by":[65,97],"nested":[66],"auto-encoders,":[67],"rather":[68],"than":[69],"directly":[70],"mapping":[71],"them":[72],"modality":[75],"or":[76],"centers.":[78],"Besides,":[79],"perform":[81],"Hierarchical":[83],"Structure":[84],"Learning":[85],"(HSL)":[86],"approach":[87],"leverage":[89],"high-order":[91],"correlations":[92],"among":[93],"objects":[94],"generalization,":[96],"constructing":[98],"a":[99],"heterogeneous":[100],"hypergraph":[101],"structure":[102],"based":[103],"hierarchical":[105],"inter-modality,":[106],"intra-object,":[107],"and":[108,113],"implicit-category":[109],"correlations.":[110],"Extensive":[111],"experiments":[112],"ablation":[114],"studies":[115],"four":[117],"benchmarks":[118],"demonstrate":[119],"superiority":[121],"our":[123],"proposed":[124],"compared":[126],"state-of-the-art":[128],"methods.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}