{"id":"https://openalex.org/W4293112749","doi":"https://doi.org/10.48550/arxiv.2208.11112","title":"DeepInteraction: 3D Object Detection via Modality Interaction","display_name":"DeepInteraction: 3D Object Detection via Modality Interaction","publication_year":2022,"publication_date":"2022-08-23","ids":{"openalex":"https://openalex.org/W4293112749","doi":"https://doi.org/10.48550/arxiv.2208.11112"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2208.11112","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.11112","pdf_url":"https://arxiv.org/pdf/2208.11112","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":"","raw_type":null},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2208.11112","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100728275","display_name":"Zeyu Yang","orcid":"https://orcid.org/0000-0002-7232-5678"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yang, Zeyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434210","display_name":"Jiaqi Chen","orcid":"https://orcid.org/0009-0002-5126-3460"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jiaqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025330751","display_name":"Zhenwei Miao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miao, Zhenwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318032","display_name":"Wei Li","orcid":"https://orcid.org/0000-0001-8124-4645"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028643592","display_name":"Xiatian Zhu","orcid":"https://orcid.org/0000-0002-9284-2955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Xiatian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418950","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0001-6674-692X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Li","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100728275"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":65,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9988999962806702,"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":0.9976999759674072,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.8520111441612244},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7568091154098511},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6311858892440796},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5991967916488647},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5870280861854553},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5778706669807434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5762059688568115},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5115145444869995},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.46195319294929504},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3834025263786316},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2810705900192261},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.22318702936172485}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8520111441612244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7568091154098511},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6311858892440796},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5991967916488647},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5870280861854553},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5778706669807434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5762059688568115},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5115145444869995},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.46195319294929504},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3834025263786316},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2810705900192261},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.22318702936172485},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2208.11112","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.11112","pdf_url":"https://arxiv.org/pdf/2208.11112","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":"","raw_type":null},{"id":"doi:10.48550/arxiv.2208.11112","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2208.11112","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2208.11112","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.11112","pdf_url":"https://arxiv.org/pdf/2208.11112","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":"","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2530972254","https://openalex.org/W2017776670","https://openalex.org/W2952760143","https://openalex.org/W2347897961","https://openalex.org/W2979236518","https://openalex.org/W627697492"],"abstract_inverted_index":{"Existing":[0],"top-performance":[1],"3D":[2],"object":[3,63,122],"detectors":[4],"typically":[5],"rely":[6],"on":[7,89],"the":[8,21,28,90,114,118],"multi-modal":[9,78,84],"fusion":[10],"strategy.":[11],"This":[12],"design":[13,71],"is":[14,111],"however":[15],"fundamentally":[16],"restricted":[17],"due":[18],"to":[19,59],"overlooking":[20],"modality-specific":[22],"useful":[23],"information":[24],"and":[25,51,82],"finally":[26],"hampering":[27],"model":[29],"performance.":[30],"To":[31,65],"address":[32],"this":[33,36,67],"limitation,":[34],"in":[35],"work":[37],"we":[38,70],"introduce":[39],"a":[40,72,77,83,105],"novel":[41],"modality":[42],"interaction":[43,80,86],"strategy":[44],"where":[45],"individual":[46],"per-modality":[47],"representations":[48],"are":[49],"learned":[50],"maintained":[52],"throughout":[53],"for":[54],"enabling":[55],"their":[56],"unique":[57],"characteristics":[58],"be":[60],"exploited":[61],"during":[62],"detection.":[64],"realize":[66],"proposed":[68,97],"strategy,":[69],"DeepInteraction":[73],"architecture":[74],"characterized":[75],"by":[76,104],"representational":[79],"encoder":[81],"predictive":[85],"decoder.":[87],"Experiments":[88],"large-scale":[91],"nuScenes":[92,121],"dataset":[93],"show":[94],"that":[95],"our":[96,109],"method":[98,110],"surpasses":[99],"all":[100],"prior":[101],"arts":[102],"often":[103],"large":[106],"margin.":[107],"Crucially,":[108],"ranked":[112],"at":[113,117],"first":[115],"position":[116],"highly":[119],"competitive":[120],"detection":[123],"leaderboard.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":25}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}