{"id":"https://openalex.org/W3192668118","doi":"https://doi.org/10.1145/3474085.3475397","title":"TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding","display_name":"TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3192668118","doi":"https://doi.org/10.1145/3474085.3475397","mag":"3192668118"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475397","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.02388","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056572647","display_name":"Dailan He","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dailan He","raw_affiliation_strings":["Beihang University, Beijing, China","BeiHang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"BeiHang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023158258","display_name":"Yusheng Zhao","orcid":"https://orcid.org/0000-0002-5893-504X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yusheng Zhao","raw_affiliation_strings":["Beihang University, Beijing, China","BeiHang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"BeiHang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101912906","display_name":"Junyu Luo","orcid":"https://orcid.org/0009-0001-6894-1144"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyu Luo","raw_affiliation_strings":["Beihang University, Beijing, China","BeiHang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"BeiHang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056811650","display_name":"Tianrui Hui","orcid":"https://orcid.org/0000-0002-1172-1554"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianrui Hui","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","Institute of Information Engineering Chinese Academy of Sciences Beijing China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Information Engineering Chinese Academy of Sciences Beijing China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024226895","display_name":"Shaofei Huang","orcid":"https://orcid.org/0000-0001-8996-9907"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaofei Huang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","Institute of Information Engineering Chinese Academy of Sciences Beijing China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Information Engineering Chinese Academy of Sciences Beijing China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049610245","display_name":"Aixi Zhang","orcid":"https://orcid.org/0000-0001-9863-0091"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aixi Zhang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100330138","display_name":"Si Liu","orcid":"https://orcid.org/0000-0002-9180-2935"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Liu","raw_affiliation_strings":["Institute of Artificial Intelligence, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5056572647"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.5826,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.68557117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2344","last_page":"2352"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9954000115394592,"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":0.8071393966674805},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5936408042907715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5456852912902832},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5030035376548767},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.49212712049484253},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4810390770435333},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.46825680136680603},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4206802546977997},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.41866278648376465},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1537761390209198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8071393966674805},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5936408042907715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5456852912902832},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5030035376548767},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.49212712049484253},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4810390770435333},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.46825680136680603},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4206802546977997},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.41866278648376465},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1537761390209198},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3474085.3475397","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.02388","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.02388","pdf_url":"https://arxiv.org/pdf/2108.02388","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":"mag:3192668118","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2108.02388","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2108.02388","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2108.02388","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":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2108.02388","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.02388","pdf_url":"https://arxiv.org/pdf/2108.02388","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":[{"id":"https://metadata.un.org/sdg/10","score":0.7300000190734863,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G5085687349","display_name":null,"funder_award_id":"Grant 61876177","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":40,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2463565445","https://openalex.org/W2560609797","https://openalex.org/W2626778328","https://openalex.org/W2745166287","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2889895098","https://openalex.org/W2896457183","https://openalex.org/W2950493473","https://openalex.org/W2953276893","https://openalex.org/W2954861308","https://openalex.org/W2963121255","https://openalex.org/W2963536419","https://openalex.org/W2963914122","https://openalex.org/W2965373594","https://openalex.org/W2968549119","https://openalex.org/W2971588465","https://openalex.org/W2979912832","https://openalex.org/W2981587852","https://openalex.org/W2984074464","https://openalex.org/W2986670728","https://openalex.org/W2987734933","https://openalex.org/W2995439012","https://openalex.org/W3014442964","https://openalex.org/W3016635207","https://openalex.org/W3030520226","https://openalex.org/W3034325957","https://openalex.org/W3034655362","https://openalex.org/W3089642432","https://openalex.org/W3092961994","https://openalex.org/W3093017735","https://openalex.org/W3093124244","https://openalex.org/W3094502228","https://openalex.org/W3095974555","https://openalex.org/W3096609285","https://openalex.org/W3109319753","https://openalex.org/W3110042533","https://openalex.org/W3133833192","https://openalex.org/W3175234951"],"related_works":["https://openalex.org/W3206171352","https://openalex.org/W2340196666","https://openalex.org/W2992859116","https://openalex.org/W3137884900","https://openalex.org/W2990645431","https://openalex.org/W3174336354","https://openalex.org/W2896632102","https://openalex.org/W3028924880","https://openalex.org/W2965068372","https://openalex.org/W2952913767","https://openalex.org/W3081278515","https://openalex.org/W2902620067","https://openalex.org/W3213639431","https://openalex.org/W3176858586","https://openalex.org/W3091184187","https://openalex.org/W3154581497","https://openalex.org/W3112491480","https://openalex.org/W3200840174","https://openalex.org/W3085189788","https://openalex.org/W2948519073"],"abstract_inverted_index":{"Recently":[0],"proposed":[1,188],"fine-grained":[2,118,219],"3D":[3,18,80,220],"visual":[4,64,130,142,221],"grounding":[5,222],"is":[6,14,211],"an":[7,105,158],"essential":[8],"and":[9,65,84,110,154,164,182,198],"challenging":[10],"task,":[11],"whose":[12],"goal":[13],"to":[15,41,51,59,89,116,168,196],"identify":[16],"the":[17,31,44,48,53,60,200,205,212],"object":[19,55],"referred":[20,54],"by":[21,123,194],"a":[22,86,111],"natural":[23,76],"language":[24],"sentence":[25],"from":[26,56],"other":[27],"distractive":[28],"objects":[29,96],"of":[30,63,207],"same":[32],"category.":[33],"Existing":[34],"works":[35],"usually":[36],"adopt":[37],"dynamic":[38],"graph":[39],"networks":[40],"indirectly":[42],"model":[43,49,189],"intra/inter-modal":[45],"interactions,":[46],"making":[47],"difficult":[50],"distinguish":[52],"distractors":[57],"due":[58],"monolithic":[61],"representations":[62],"linguistic":[66,134,146],"contents.":[67],"In":[68],"this":[69,210],"work,":[70],"we":[71,103],"exploit":[72],"Transformer":[73,216],"for":[74,97,172,218],"its":[75],"suitability":[77],"on":[78,179],"permutation-invariant":[79],"point":[81],"clouds":[82],"data":[83],"propose":[85],"TransRefer3D":[87,171],"network":[88],"extract":[90],"entity-and-relation":[91],"aware":[92,160],"multimodal":[93,174],"context":[94,175],"among":[95],"more":[98],"discriminative":[99],"feature":[100,120],"learning.":[101],"Concretely,":[102],"devise":[104],"Entity-aware":[106],"Attention":[107,113],"(EA)":[108],"module":[109,115,128,139],"Relation-aware":[112],"(RA)":[114],"conduct":[117],"cross-modal":[119],"matching.":[121],"Facilitated":[122],"co-attention":[124],"operation,":[125],"our":[126,170,187,208],"EA":[127,153],"matches":[129,140],"entity":[131,135],"features":[132,136,144],"with":[133,145],"while":[137],"RA":[138,155],"pair-wise":[141],"relation":[143,147],"features,":[148],"respectively.":[149],"We":[150],"further":[151],"integrate":[152],"modules":[156],"into":[157],"Entity-and-Relation":[159],"Contextual":[161],"Block":[162],"(ERCB)":[163],"stack":[165],"several":[166],"ERCBs":[167],"form":[169],"hierarchical":[173],"modeling.":[176],"Extensive":[177],"experiments":[178],"both":[180],"Nr3D":[181],"Sr3D":[183],"datasets":[184],"demonstrate":[185],"that":[186],"significantly":[190],"outperforms":[191],"existing":[192],"approaches":[193],"up":[195],"10.6%":[197],"claims":[199],"new":[201],"state-of-the-art":[202],"performance.":[203],"To":[204],"best":[206],"knowledge,":[209],"first":[213],"work":[214],"investigating":[215],"architecture":[217],"task.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}