DeLiVoTr: Deep and light-weight voxel transformer for 3D object detection Article Swipe
Gopi Krishna Erabati
,
Hélder Araújo
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.1016/j.iswa.2024.200361
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.1016/j.iswa.2024.200361
The image-based backbone (feature extraction) networks downsample the feature maps not only to increase the receptive field but also to efficiently detect objects of various scales. The existing feature extraction networks in LiDAR-based 3D object detection tasks follow the feature map downsampling similar to image-based feature extraction networks to increase the receptive field. But, such downsampling of LiDAR feature maps in large-scale autonomous driving scenarios hinder the detection of small size objects, such as pedestrians. To solve this issue we design an architecture that not only maintains the same scale of the feature maps but also the receptive field in the feature extraction network to aid for efficient detection of small size objects. We resort to attention mechanism to build sufficient receptive field and we propose a Deep and Light-weight Voxel Transformer (DeLiVoTr) network with voxel intra- and inter-region transformer modules to extract voxel local and global features respectively. We introduce DeLiVoTr block that uses transformations with expand and reduce strategy to vary the width and depth of the network efficiently. This facilitates to learn wider and deeper voxel representations and enables to use not only smaller dimension for attention mechanism but also a light-weight feed-forward network, facilitating the reduction of parameters and operations. In addition to model scaling, we employ layer-level scaling of DeLiVoTr encoder layers for efficient parameter allocation in each encoder layer instead of fixed number of parameters as in existing approaches. Leveraging layer-level depth and width scaling we formulate three variants of DeLiVoTr network. We conduct extensive experiments and analysis on large-scale Waymo and KITTI datasets. Our network surpasses state-of-the-art methods for detection of small objects (pedestrians) with an inference speed of 20.5 FPS.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1016/j.iswa.2024.200361
- OA Status
- gold
- Cited By
- 3
- References
- 65
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4392947162
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4392947162Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1016/j.iswa.2024.200361Digital Object Identifier
- Title
-
DeLiVoTr: Deep and light-weight voxel transformer for 3D object detectionWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-03-19Full publication date if available
- Authors
-
Gopi Krishna Erabati, Hélder AraújoList of authors in order
- Landing page
-
https://doi.org/10.1016/j.iswa.2024.200361Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.1016/j.iswa.2024.200361Direct OA link when available
- Concepts
-
Transformer, Voxel, Artificial intelligence, Computer vision, Computer science, Pattern recognition (psychology), Engineering, Electrical engineering, VoltageTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
3Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 2, 2024: 1Per-year citation counts (last 5 years)
- References (count)
-
65Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4392947162 |
|---|---|
| doi | https://doi.org/10.1016/j.iswa.2024.200361 |
| ids.doi | https://doi.org/10.1016/j.iswa.2024.200361 |
| ids.openalex | https://openalex.org/W4392947162 |
| fwci | 1.59047268 |
| type | article |
| title | DeLiVoTr: Deep and light-weight voxel transformer for 3D object detection |
| biblio.issue | |
| biblio.volume | 22 |
| biblio.last_page | 200361 |
| biblio.first_page | 200361 |
| topics[0].id | https://openalex.org/T10036 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9998999834060669 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1707 |
| topics[0].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[0].display_name | Advanced Neural Network Applications |
| topics[1].id | https://openalex.org/T10191 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9987000226974487 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2202 |
| topics[1].subfield.display_name | Aerospace Engineering |
| topics[1].display_name | Robotics and Sensor-Based Localization |
| topics[2].id | https://openalex.org/T11211 |
| topics[2].field.id | https://openalex.org/fields/19 |
| topics[2].field.display_name | Earth and Planetary Sciences |
| topics[2].score | 0.9966999888420105 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1907 |
| topics[2].subfield.display_name | Geology |
| topics[2].display_name | 3D Surveying and Cultural Heritage |
| funders[0].id | https://openalex.org/F4320334779 |
| funders[0].ror | https://ror.org/00snfqn58 |
| funders[0].display_name | Fundação para a Ciência e a Tecnologia |
| funders[1].id | https://openalex.org/F4320338337 |
| funders[1].ror | |
| funders[1].display_name | H2020 Marie Skłodowska-Curie Actions |
| is_xpac | False |
| apc_list.value | 1500 |
| apc_list.currency | USD |
| apc_list.value_usd | 1500 |
| apc_paid.value | 1500 |
| apc_paid.currency | USD |
| apc_paid.value_usd | 1500 |
| concepts[0].id | https://openalex.org/C66322947 |
| concepts[0].level | 3 |
| concepts[0].score | 0.5907602906227112 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q11658 |
| concepts[0].display_name | Transformer |
| concepts[1].id | https://openalex.org/C54170458 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5328916311264038 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q663554 |
| concepts[1].display_name | Voxel |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.5189423561096191 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C31972630 |
| concepts[3].level | 1 |
| concepts[3].score | 0.39959266781806946 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[3].display_name | Computer vision |
| concepts[4].id | https://openalex.org/C41008148 |
| concepts[4].level | 0 |
| concepts[4].score | 0.38503363728523254 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[4].display_name | Computer science |
| concepts[5].id | https://openalex.org/C153180895 |
| concepts[5].level | 2 |
| concepts[5].score | 0.3221399784088135 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[5].display_name | Pattern recognition (psychology) |
| concepts[6].id | https://openalex.org/C127413603 |
| concepts[6].level | 0 |
| concepts[6].score | 0.12932798266410828 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[6].display_name | Engineering |
| concepts[7].id | https://openalex.org/C119599485 |
| concepts[7].level | 1 |
| concepts[7].score | 0.09237465262413025 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q43035 |
| concepts[7].display_name | Electrical engineering |
| concepts[8].id | https://openalex.org/C165801399 |
| concepts[8].level | 2 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q25428 |
| concepts[8].display_name | Voltage |
| keywords[0].id | https://openalex.org/keywords/transformer |
| keywords[0].score | 0.5907602906227112 |
| keywords[0].display_name | Transformer |
| keywords[1].id | https://openalex.org/keywords/voxel |
| keywords[1].score | 0.5328916311264038 |
| keywords[1].display_name | Voxel |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.5189423561096191 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/computer-vision |
| keywords[3].score | 0.39959266781806946 |
| keywords[3].display_name | Computer vision |
| keywords[4].id | https://openalex.org/keywords/computer-science |
| keywords[4].score | 0.38503363728523254 |
| keywords[4].display_name | Computer science |
| keywords[5].id | https://openalex.org/keywords/pattern-recognition |
| keywords[5].score | 0.3221399784088135 |
| keywords[5].display_name | Pattern recognition (psychology) |
| keywords[6].id | https://openalex.org/keywords/engineering |
| keywords[6].score | 0.12932798266410828 |
| keywords[6].display_name | Engineering |
| keywords[7].id | https://openalex.org/keywords/electrical-engineering |
| keywords[7].score | 0.09237465262413025 |
| keywords[7].display_name | Electrical engineering |
| language | en |
| locations[0].id | doi:10.1016/j.iswa.2024.200361 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4210234522 |
| locations[0].source.issn | 2667-3053 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2667-3053 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | True |
| locations[0].source.display_name | Intelligent Systems with Applications |
| locations[0].source.host_organization | https://openalex.org/P4310320990 |
| locations[0].source.host_organization_name | Elsevier BV |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320990 |
| locations[0].source.host_organization_lineage_names | Elsevier BV |
| locations[0].license | cc-by-nc-nd |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by-nc-nd |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Intelligent Systems with Applications |
| locations[0].landing_page_url | https://doi.org/10.1016/j.iswa.2024.200361 |
| locations[1].id | pmh:oai:doaj.org/article:9329712be7af4345a0dd91282fa5a33a |
| locations[1].is_oa | False |
| locations[1].source.id | https://openalex.org/S4306401280 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | DOAJ (DOAJ: Directory of Open Access Journals) |
| locations[1].source.host_organization | |
| locations[1].source.host_organization_name | |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | submittedVersion |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | Intelligent Systems with Applications, Vol 22, Iss , Pp 200361- (2024) |
| locations[1].landing_page_url | https://doaj.org/article/9329712be7af4345a0dd91282fa5a33a |
| indexed_in | crossref, doaj |
| authorships[0].author.id | https://openalex.org/A5059685843 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-0167-5670 |
| authorships[0].author.display_name | Gopi Krishna Erabati |
| authorships[0].countries | PT |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I4210125590, https://openalex.org/I76903346 |
| authorships[0].affiliations[0].raw_affiliation_string | Institute of Systems and Robotics, University of Coimbra, Rua Silvio Lima- Polo II, Coimbra, 3030-290, Portugal |
| authorships[0].institutions[0].id | https://openalex.org/I4210125590 |
| authorships[0].institutions[0].ror | https://ror.org/033wn8m60 |
| authorships[0].institutions[0].type | nonprofit |
| authorships[0].institutions[0].lineage | https://openalex.org/I4210125590 |
| authorships[0].institutions[0].country_code | PT |
| authorships[0].institutions[0].display_name | Institute for Systems Engineering and Computers |
| authorships[0].institutions[1].id | https://openalex.org/I76903346 |
| authorships[0].institutions[1].ror | https://ror.org/04z8k9a98 |
| authorships[0].institutions[1].type | education |
| authorships[0].institutions[1].lineage | https://openalex.org/I76903346 |
| authorships[0].institutions[1].country_code | PT |
| authorships[0].institutions[1].display_name | University of Coimbra |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Gopi Krishna Erabati |
| authorships[0].is_corresponding | True |
| authorships[0].raw_affiliation_strings | Institute of Systems and Robotics, University of Coimbra, Rua Silvio Lima- Polo II, Coimbra, 3030-290, Portugal |
| authorships[1].author.id | https://openalex.org/A5023181397 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-9544-424X |
| authorships[1].author.display_name | Hélder Araújo |
| authorships[1].countries | PT |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I4210125590, https://openalex.org/I76903346 |
| authorships[1].affiliations[0].raw_affiliation_string | Institute of Systems and Robotics, University of Coimbra, Rua Silvio Lima- Polo II, Coimbra, 3030-290, Portugal |
| authorships[1].institutions[0].id | https://openalex.org/I4210125590 |
| authorships[1].institutions[0].ror | https://ror.org/033wn8m60 |
| authorships[1].institutions[0].type | nonprofit |
| authorships[1].institutions[0].lineage | https://openalex.org/I4210125590 |
| authorships[1].institutions[0].country_code | PT |
| authorships[1].institutions[0].display_name | Institute for Systems Engineering and Computers |
| authorships[1].institutions[1].id | https://openalex.org/I76903346 |
| authorships[1].institutions[1].ror | https://ror.org/04z8k9a98 |
| authorships[1].institutions[1].type | education |
| authorships[1].institutions[1].lineage | https://openalex.org/I76903346 |
| authorships[1].institutions[1].country_code | PT |
| authorships[1].institutions[1].display_name | University of Coimbra |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Helder Araujo |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Institute of Systems and Robotics, University of Coimbra, Rua Silvio Lima- Polo II, Coimbra, 3030-290, Portugal |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.1016/j.iswa.2024.200361 |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | DeLiVoTr: Deep and light-weight voxel transformer for 3D object detection |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10036 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9998999834060669 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1707 |
| primary_topic.subfield.display_name | Computer Vision and Pattern Recognition |
| primary_topic.display_name | Advanced Neural Network Applications |
| related_works | https://openalex.org/W2058170566, https://openalex.org/W2755342338, https://openalex.org/W2772917594, https://openalex.org/W2775347418, https://openalex.org/W2166024367, https://openalex.org/W3116076068, https://openalex.org/W2229312674, https://openalex.org/W2951359407, https://openalex.org/W2079911747, https://openalex.org/W1969923398 |
| cited_by_count | 3 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 2 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | doi:10.1016/j.iswa.2024.200361 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4210234522 |
| best_oa_location.source.issn | 2667-3053 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2667-3053 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | True |
| best_oa_location.source.display_name | Intelligent Systems with Applications |
| best_oa_location.source.host_organization | https://openalex.org/P4310320990 |
| best_oa_location.source.host_organization_name | Elsevier BV |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310320990 |
| best_oa_location.source.host_organization_lineage_names | Elsevier BV |
| best_oa_location.license | cc-by-nc-nd |
| best_oa_location.pdf_url | |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Intelligent Systems with Applications |
| best_oa_location.landing_page_url | https://doi.org/10.1016/j.iswa.2024.200361 |
| primary_location.id | doi:10.1016/j.iswa.2024.200361 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4210234522 |
| primary_location.source.issn | 2667-3053 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2667-3053 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | True |
| primary_location.source.display_name | Intelligent Systems with Applications |
| primary_location.source.host_organization | https://openalex.org/P4310320990 |
| primary_location.source.host_organization_name | Elsevier BV |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320990 |
| primary_location.source.host_organization_lineage_names | Elsevier BV |
| primary_location.license | cc-by-nc-nd |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Intelligent Systems with Applications |
| primary_location.landing_page_url | https://doi.org/10.1016/j.iswa.2024.200361 |
| publication_date | 2024-03-19 |
| publication_year | 2024 |
| referenced_works | https://openalex.org/W6778485988, https://openalex.org/W6772150300, https://openalex.org/W6773340602, https://openalex.org/W6804552856, https://openalex.org/W6798837711, https://openalex.org/W6761689847, https://openalex.org/W6838322825, https://openalex.org/W6784333009, https://openalex.org/W6846347471, https://openalex.org/W6805849596, https://openalex.org/W6791123272, https://openalex.org/W6681934335, https://openalex.org/W6746463013, https://openalex.org/W3111535274, https://openalex.org/W6790690058, https://openalex.org/W6687483927, https://openalex.org/W6757384202, https://openalex.org/W6753494528, https://openalex.org/W6785652829, https://openalex.org/W6792155083, https://openalex.org/W6801065500, https://openalex.org/W6687932531, https://openalex.org/W6788684253, https://openalex.org/W6760825869, https://openalex.org/W6801377519, https://openalex.org/W6787910462, https://openalex.org/W6811122175, https://openalex.org/W6766978945, https://openalex.org/W6745673378, https://openalex.org/W6763422710, https://openalex.org/W6739778489, https://openalex.org/W6772595511, https://openalex.org/W4310078553, https://openalex.org/W6756795685, https://openalex.org/W2914821954, https://openalex.org/W6771941581, https://openalex.org/W6796872458, https://openalex.org/W6781600403, https://openalex.org/W6739901393, https://openalex.org/W6790555728, https://openalex.org/W3175515048, https://openalex.org/W6780673685, https://openalex.org/W6802311648, https://openalex.org/W6802716934, https://openalex.org/W6756639113, https://openalex.org/W6797399245, https://openalex.org/W2897529137, https://openalex.org/W6773990164, https://openalex.org/W6779712747, https://openalex.org/W6788477181, https://openalex.org/W6788305448, https://openalex.org/W6788620109, https://openalex.org/W6769571200, https://openalex.org/W6745896446, https://openalex.org/W3213165621, https://openalex.org/W4236965008, https://openalex.org/W4200268060, https://openalex.org/W3211490618, https://openalex.org/W2963121255, https://openalex.org/W3153465022, https://openalex.org/W3207231145, https://openalex.org/W4295312788, https://openalex.org/W3133696297, https://openalex.org/W4281758439, https://openalex.org/W4385245566 |
| referenced_works_count | 65 |
| abstract_inverted_index.a | 126, 193 |
| abstract_inverted_index.3D | 33 |
| abstract_inverted_index.In | 204 |
| abstract_inverted_index.To | 75 |
| abstract_inverted_index.We | 113, 149, 248 |
| abstract_inverted_index.an | 81, 272 |
| abstract_inverted_index.as | 73, 231 |
| abstract_inverted_index.in | 31, 60, 99, 221, 232 |
| abstract_inverted_index.of | 23, 56, 68, 90, 109, 167, 200, 213, 226, 229, 245, 267, 275 |
| abstract_inverted_index.on | 254 |
| abstract_inverted_index.to | 12, 19, 43, 48, 104, 115, 118, 141, 161, 173, 182, 206 |
| abstract_inverted_index.we | 79, 124, 209, 241 |
| abstract_inverted_index.Our | 260 |
| abstract_inverted_index.The | 0, 26 |
| abstract_inverted_index.aid | 105 |
| abstract_inverted_index.and | 123, 128, 137, 145, 158, 165, 176, 180, 202, 238, 252, 257 |
| abstract_inverted_index.but | 17, 94, 191 |
| abstract_inverted_index.for | 106, 188, 217, 265 |
| abstract_inverted_index.map | 40 |
| abstract_inverted_index.not | 10, 84, 184 |
| abstract_inverted_index.the | 7, 14, 38, 50, 66, 87, 91, 96, 100, 163, 168, 198 |
| abstract_inverted_index.use | 183 |
| abstract_inverted_index.20.5 | 276 |
| abstract_inverted_index.But, | 53 |
| abstract_inverted_index.Deep | 127 |
| abstract_inverted_index.FPS. | 277 |
| abstract_inverted_index.This | 171 |
| abstract_inverted_index.also | 18, 95, 192 |
| abstract_inverted_index.each | 222 |
| abstract_inverted_index.maps | 9, 59, 93 |
| abstract_inverted_index.only | 11, 85, 185 |
| abstract_inverted_index.same | 88 |
| abstract_inverted_index.size | 70, 111 |
| abstract_inverted_index.such | 54, 72 |
| abstract_inverted_index.that | 83, 153 |
| abstract_inverted_index.this | 77 |
| abstract_inverted_index.uses | 154 |
| abstract_inverted_index.vary | 162 |
| abstract_inverted_index.with | 134, 156, 271 |
| abstract_inverted_index.KITTI | 258 |
| abstract_inverted_index.LiDAR | 57 |
| abstract_inverted_index.Voxel | 130 |
| abstract_inverted_index.Waymo | 256 |
| abstract_inverted_index.block | 152 |
| abstract_inverted_index.build | 119 |
| abstract_inverted_index.depth | 166, 237 |
| abstract_inverted_index.field | 16, 98, 122 |
| abstract_inverted_index.fixed | 227 |
| abstract_inverted_index.issue | 78 |
| abstract_inverted_index.layer | 224 |
| abstract_inverted_index.learn | 174 |
| abstract_inverted_index.local | 144 |
| abstract_inverted_index.model | 207 |
| abstract_inverted_index.scale | 89 |
| abstract_inverted_index.small | 69, 110, 268 |
| abstract_inverted_index.solve | 76 |
| abstract_inverted_index.speed | 274 |
| abstract_inverted_index.tasks | 36 |
| abstract_inverted_index.three | 243 |
| abstract_inverted_index.voxel | 135, 143, 178 |
| abstract_inverted_index.wider | 175 |
| abstract_inverted_index.width | 164, 239 |
| abstract_inverted_index.deeper | 177 |
| abstract_inverted_index.design | 80 |
| abstract_inverted_index.detect | 21 |
| abstract_inverted_index.employ | 210 |
| abstract_inverted_index.expand | 157 |
| abstract_inverted_index.field. | 52 |
| abstract_inverted_index.follow | 37 |
| abstract_inverted_index.global | 146 |
| abstract_inverted_index.hinder | 65 |
| abstract_inverted_index.intra- | 136 |
| abstract_inverted_index.layers | 216 |
| abstract_inverted_index.number | 228 |
| abstract_inverted_index.object | 34 |
| abstract_inverted_index.reduce | 159 |
| abstract_inverted_index.resort | 114 |
| abstract_inverted_index.conduct | 249 |
| abstract_inverted_index.driving | 63 |
| abstract_inverted_index.enables | 181 |
| abstract_inverted_index.encoder | 215, 223 |
| abstract_inverted_index.extract | 142 |
| abstract_inverted_index.feature | 8, 28, 39, 45, 58, 92, 101 |
| abstract_inverted_index.instead | 225 |
| abstract_inverted_index.methods | 264 |
| abstract_inverted_index.modules | 140 |
| abstract_inverted_index.network | 103, 133, 169, 261 |
| abstract_inverted_index.objects | 22, 269 |
| abstract_inverted_index.propose | 125 |
| abstract_inverted_index.scales. | 25 |
| abstract_inverted_index.scaling | 212, 240 |
| abstract_inverted_index.similar | 42 |
| abstract_inverted_index.smaller | 186 |
| abstract_inverted_index.various | 24 |
| abstract_inverted_index.(feature | 3 |
| abstract_inverted_index.DeLiVoTr | 151, 214, 246 |
| abstract_inverted_index.addition | 205 |
| abstract_inverted_index.analysis | 253 |
| abstract_inverted_index.backbone | 2 |
| abstract_inverted_index.existing | 27, 233 |
| abstract_inverted_index.features | 147 |
| abstract_inverted_index.increase | 13, 49 |
| abstract_inverted_index.network, | 196 |
| abstract_inverted_index.network. | 247 |
| abstract_inverted_index.networks | 5, 30, 47 |
| abstract_inverted_index.objects, | 71 |
| abstract_inverted_index.objects. | 112 |
| abstract_inverted_index.scaling, | 208 |
| abstract_inverted_index.strategy | 160 |
| abstract_inverted_index.variants | 244 |
| abstract_inverted_index.attention | 116, 189 |
| abstract_inverted_index.datasets. | 259 |
| abstract_inverted_index.detection | 35, 67, 108, 266 |
| abstract_inverted_index.dimension | 187 |
| abstract_inverted_index.efficient | 107, 218 |
| abstract_inverted_index.extensive | 250 |
| abstract_inverted_index.formulate | 242 |
| abstract_inverted_index.inference | 273 |
| abstract_inverted_index.introduce | 150 |
| abstract_inverted_index.maintains | 86 |
| abstract_inverted_index.mechanism | 117, 190 |
| abstract_inverted_index.parameter | 219 |
| abstract_inverted_index.receptive | 15, 51, 97, 121 |
| abstract_inverted_index.reduction | 199 |
| abstract_inverted_index.scenarios | 64 |
| abstract_inverted_index.surpasses | 262 |
| abstract_inverted_index.(DeLiVoTr) | 132 |
| abstract_inverted_index.Leveraging | 235 |
| abstract_inverted_index.allocation | 220 |
| abstract_inverted_index.autonomous | 62 |
| abstract_inverted_index.downsample | 6 |
| abstract_inverted_index.extraction | 29, 46, 102 |
| abstract_inverted_index.parameters | 201, 230 |
| abstract_inverted_index.sufficient | 120 |
| abstract_inverted_index.LiDAR-based | 32 |
| abstract_inverted_index.Transformer | 131 |
| abstract_inverted_index.approaches. | 234 |
| abstract_inverted_index.efficiently | 20 |
| abstract_inverted_index.experiments | 251 |
| abstract_inverted_index.extraction) | 4 |
| abstract_inverted_index.facilitates | 172 |
| abstract_inverted_index.image-based | 1, 44 |
| abstract_inverted_index.large-scale | 61, 255 |
| abstract_inverted_index.layer-level | 211, 236 |
| abstract_inverted_index.operations. | 203 |
| abstract_inverted_index.transformer | 139 |
| abstract_inverted_index.Light-weight | 129 |
| abstract_inverted_index.architecture | 82 |
| abstract_inverted_index.downsampling | 41, 55 |
| abstract_inverted_index.efficiently. | 170 |
| abstract_inverted_index.facilitating | 197 |
| abstract_inverted_index.feed-forward | 195 |
| abstract_inverted_index.inter-region | 138 |
| abstract_inverted_index.light-weight | 194 |
| abstract_inverted_index.pedestrians. | 74 |
| abstract_inverted_index.(pedestrians) | 270 |
| abstract_inverted_index.respectively. | 148 |
| abstract_inverted_index.representations | 179 |
| abstract_inverted_index.transformations | 155 |
| abstract_inverted_index.state-of-the-art | 263 |
| cited_by_percentile_year.max | 97 |
| cited_by_percentile_year.min | 90 |
| corresponding_author_ids | https://openalex.org/A5059685843 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 2 |
| corresponding_institution_ids | https://openalex.org/I4210125590, https://openalex.org/I76903346 |
| citation_normalized_percentile.value | 0.75945812 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |