{"id":"https://openalex.org/W4405717815","doi":"https://doi.org/10.1109/tmm.2024.3521816","title":"Semantic-Enhanced ULIP for Zero-Shot 3D Shape Recognition","display_name":"Semantic-Enhanced ULIP for Zero-Shot 3D Shape Recognition","publication_year":2024,"publication_date":"2024-12-23","ids":{"openalex":"https://openalex.org/W4405717815","doi":"https://doi.org/10.1109/tmm.2024.3521816"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3521816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521816","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5041422139","display_name":"Bo Ding","orcid":"https://orcid.org/0000-0002-9154-776X"},"institutions":[{"id":"https://openalex.org/I100188998","display_name":"Harbin University of Science and Technology","ror":"https://ror.org/04e6y1282","country_code":"CN","type":"education","lineage":["https://openalex.org/I100188998"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Ding","raw_affiliation_strings":["School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China","institution_ids":["https://openalex.org/I100188998"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Libao Zhang","orcid":"https://orcid.org/0000-0002-5130-013X"},"institutions":[{"id":"https://openalex.org/I100188998","display_name":"Harbin University of Science and Technology","ror":"https://ror.org/04e6y1282","country_code":"CN","type":"education","lineage":["https://openalex.org/I100188998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libao Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China","institution_ids":["https://openalex.org/I100188998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763595","display_name":"Hongbo Sun","orcid":"https://orcid.org/0009-0009-1157-5903"},"institutions":[{"id":"https://openalex.org/I100188998","display_name":"Harbin University of Science and Technology","ror":"https://ror.org/04e6y1282","country_code":"CN","type":"education","lineage":["https://openalex.org/I100188998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbo Sun","raw_affiliation_strings":["School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China","institution_ids":["https://openalex.org/I100188998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026346396","display_name":"Yongjun He","orcid":"https://orcid.org/0000-0002-5156-651X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjun He","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, Harbin, China","School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088167949","display_name":"Jian Qin","orcid":"https://orcid.org/0000-0001-8791-0370"},"institutions":[{"id":"https://openalex.org/I100188998","display_name":"Harbin University of Science and Technology","ror":"https://ror.org/04e6y1282","country_code":"CN","type":"education","lineage":["https://openalex.org/I100188998"]},{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Qin","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University of Technology, Maanshan, China","School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University of Technology, Maanshan, China","institution_ids":["https://openalex.org/I92178344"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China","institution_ids":["https://openalex.org/I100188998"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041422139"],"corresponding_institution_ids":["https://openalex.org/I100188998"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34793742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"1926","last_page":"1936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10531","display_name":"Advanced Vision and Imaging","score":0.9900000095367432,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.781998872756958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.488665372133255},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3612877428531647},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35079964995384216},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3502342700958252}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781998872756958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.488665372133255},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3612877428531647},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35079964995384216},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3502342700958252}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3521816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521816","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1607685698","display_name":null,"funder_award_id":"61673142","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1644641054","https://openalex.org/W1920022804","https://openalex.org/W2021122545","https://openalex.org/W2089799371","https://openalex.org/W2108598243","https://openalex.org/W2799162093","https://openalex.org/W2910453440","https://openalex.org/W2927958594","https://openalex.org/W2960986959","https://openalex.org/W2963231572","https://openalex.org/W2963499153","https://openalex.org/W2963719584","https://openalex.org/W2963830382","https://openalex.org/W2979750740","https://openalex.org/W2981440248","https://openalex.org/W2990613095","https://openalex.org/W3009201938","https://openalex.org/W3034317823","https://openalex.org/W3034942609","https://openalex.org/W3111535274","https://openalex.org/W3152685972","https://openalex.org/W3155169629","https://openalex.org/W3159746229","https://openalex.org/W3198377975","https://openalex.org/W3204568647","https://openalex.org/W3213454282","https://openalex.org/W4205189682","https://openalex.org/W4210786150","https://openalex.org/W4212878186","https://openalex.org/W4214644223","https://openalex.org/W4214755140","https://openalex.org/W4225330657","https://openalex.org/W4225763874","https://openalex.org/W4312270234","https://openalex.org/W4312310776","https://openalex.org/W4312629998","https://openalex.org/W4312818263","https://openalex.org/W4319978676","https://openalex.org/W4382458283","https://openalex.org/W4385245566","https://openalex.org/W4386076048","https://openalex.org/W4386076097","https://openalex.org/W4386076598","https://openalex.org/W4386083131","https://openalex.org/W4390189960","https://openalex.org/W4390872570","https://openalex.org/W4390874324","https://openalex.org/W4402727761","https://openalex.org/W6687484953","https://openalex.org/W6739778489","https://openalex.org/W6763422710","https://openalex.org/W6764997072","https://openalex.org/W6778883912","https://openalex.org/W6784185929","https://openalex.org/W6784333009","https://openalex.org/W6785421021","https://openalex.org/W6790003725","https://openalex.org/W6790453339","https://openalex.org/W6791353385","https://openalex.org/W6810249204","https://openalex.org/W6810255026","https://openalex.org/W6839157500","https://openalex.org/W6839446344","https://openalex.org/W6853178439"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0,87,132],"recent":[1],"years,":[2],"the":[3,21,26,31,65,70,77,82,88,94,98,102,105,115,125,129,133,149,160,164,173,185,189],"zero-shot":[4,43,200],"image":[5,95],"recognition":[6],"with":[7,128],"semantic":[8,32,130,174],"knowledge":[9,33,175],"has":[10],"achieved":[11],"good":[12],"performance":[13,187],"due":[14],"to":[15,68,123,147,162,171],"vision-language":[16],"models.":[17],"However,":[18],"because":[19],"of":[20,23,34,42,110,176],"complexity":[22],"3D":[24,35,44,58,177,195,203],"shapes,":[25,36],"model":[27],"cannot":[28],"fully":[29],"use":[30],"which":[37,121,168],"results":[38],"in":[39,73],"low":[40],"accuracy":[41],"shape":[45,204],"recognition.":[46,205],"To":[47],"address":[48],"this":[49],"problem,":[50],"we":[51,92,138],"propose":[52,139],"a":[53],"Semantic-enhanced":[54],"ULIP":[55],"for":[56,198],"Zero-shot":[57],"Shape":[59],"Recognition":[60],"(SE-ULIP).":[61],"This":[62],"method":[63,183],"utilizes":[64],"contrastive":[66],"learning":[67],"fine-tune":[69,93,163],"text":[71,84,99,135,165,191],"encoder":[72,85,96,100,136,166,192],"two":[74],"stages,":[75],"including":[76],"domain":[78,89],"adaptation":[79,90],"fine-tuning":[80],"and":[81,97,104,201],"triplets-based":[83,134],"fine-tuning.":[86],"fine-tuning,":[91,137],"using":[101],"views":[103],"Semantic":[106],"Descriptive":[107],"Text":[108],"(SDT)":[109],"each":[111],"view":[112,126],"generated":[113],"by":[114],"Visual":[116],"Question":[117],"Answering":[118],"(VQA)":[119],"model,":[120],"aims":[122],"align":[124],"features":[127],"knowledge.":[131],"an":[140],"Adaptive":[141],"Conditional":[142],"Adjustment":[143],"Context":[144],"Optimization":[145],"(ACACoOp)":[146],"learn":[148],"optimal":[150,154],"context":[151,155],"vectors.":[152],"The":[153],"vectors":[156],"are":[157],"used":[158],"as":[159],"input":[161],"again,":[167],"enhance":[169],"SE-ULIP":[170],"understand":[172],"shapes.":[178],"Experiments":[179],"show":[180],"that":[181],"our":[182],"achieves":[184],"state-of-the-art":[186],"through":[188],"fine-tuned":[190],"on":[193],"three":[194],"backbone":[196],"networks":[197],"both":[199],"standard":[202]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}