HiP: Hierarchical Perceiver Article Swipe
João Carreira
,
Skanda Koppula
,
Daniel Zoran
,
Adrià Recasens
,
Catalin Ionescu
,
Olivier J. Hénaff
,
Evan Shelhamer
,
Relja Arandjelović
,
Matt Botvinick
,
Oriol Vinyals
,
Karen Simonyan
,
Andrew Zisserman
,
Andrew Jaegle
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2202.10890
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2202.10890
General perception systems such as Perceivers can process arbitrary modalities in any combination and are able to handle up to a few hundred thousand inputs. They achieve this generality by using exclusively global attention operations. This however hinders them from scaling up to the inputs sizes required to process raw high-resolution images or video. In this paper, we show that some degree of locality can be introduced back into these models, greatly improving their efficiency while preserving their generality. To scale them further, we introduce a self-supervised approach that enables learning dense low-dimensional positional embeddings for very large signals. We call the resulting model a Hierarchical Perceiver (HiP). In sum our contributions are: 1) scaling Perceiver-type models to raw high-resolution images and audio+video, 2) showing the feasibility of learning 1M+ positional embeddings from scratch using masked auto-encoding, 3) demonstrating competitive performance on raw data from ImageNet, AudioSet, PASCAL VOC, ModelNet40 and Kinetics datasets with the same exact, unchanged model and without specialized preprocessing or any tokenization.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2202.10890
- https://arxiv.org/pdf/2202.10890
- OA Status
- green
- Cited By
- 2
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4226362570
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4226362570Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2202.10890Digital Object Identifier
- Title
-
HiP: Hierarchical PerceiverWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-02-22Full publication date if available
- Authors
-
João Carreira, Skanda Koppula, Daniel Zoran, Adrià Recasens, Catalin Ionescu, Olivier J. Hénaff, Evan Shelhamer, Relja Arandjelović, Matt Botvinick, Oriol Vinyals, Karen Simonyan, Andrew Zisserman, Andrew JaegleList of authors in order
- Landing page
-
https://arxiv.org/abs/2202.10890Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2202.10890Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2202.10890Direct OA link when available
- Concepts
-
Generality, Computer science, Preprocessor, Artificial intelligence, Pascal (unit), Scaling, Process (computing), Pattern recognition (psychology), Mathematics, Operating system, Geometry, Psychology, Psychotherapist, Programming languageTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
2Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 1, 2022: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4226362570 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2202.10890 |
| ids.doi | https://doi.org/10.48550/arxiv.2202.10890 |
| ids.openalex | https://openalex.org/W4226362570 |
| fwci | |
| type | preprint |
| title | HiP: Hierarchical Perceiver |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10688 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9939000010490417 |
| 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 | Image and Signal Denoising Methods |
| topics[1].id | https://openalex.org/T11307 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9926000237464905 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Domain Adaptation and Few-Shot Learning |
| topics[2].id | https://openalex.org/T10860 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9864000082015991 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1711 |
| topics[2].subfield.display_name | Signal Processing |
| topics[2].display_name | Speech and Audio Processing |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2780767217 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8331893682479858 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q5532421 |
| concepts[0].display_name | Generality |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7898809909820557 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C34736171 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6072167754173279 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q918333 |
| concepts[2].display_name | Preprocessor |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5656963586807251 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C75608658 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5281983017921448 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q44395 |
| concepts[4].display_name | Pascal (unit) |
| concepts[5].id | https://openalex.org/C99844830 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4997286796569824 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q102441924 |
| concepts[5].display_name | Scaling |
| concepts[6].id | https://openalex.org/C98045186 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4144141674041748 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q205663 |
| concepts[6].display_name | Process (computing) |
| concepts[7].id | https://openalex.org/C153180895 |
| concepts[7].level | 2 |
| concepts[7].score | 0.35793477296829224 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[7].display_name | Pattern recognition (psychology) |
| concepts[8].id | https://openalex.org/C33923547 |
| concepts[8].level | 0 |
| concepts[8].score | 0.09528917074203491 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[8].display_name | Mathematics |
| concepts[9].id | https://openalex.org/C111919701 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[9].display_name | Operating system |
| concepts[10].id | https://openalex.org/C2524010 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[10].display_name | Geometry |
| concepts[11].id | https://openalex.org/C15744967 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[11].display_name | Psychology |
| concepts[12].id | https://openalex.org/C542102704 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q183257 |
| concepts[12].display_name | Psychotherapist |
| concepts[13].id | https://openalex.org/C199360897 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[13].display_name | Programming language |
| keywords[0].id | https://openalex.org/keywords/generality |
| keywords[0].score | 0.8331893682479858 |
| keywords[0].display_name | Generality |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7898809909820557 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/preprocessor |
| keywords[2].score | 0.6072167754173279 |
| keywords[2].display_name | Preprocessor |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.5656963586807251 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/pascal |
| keywords[4].score | 0.5281983017921448 |
| keywords[4].display_name | Pascal (unit) |
| keywords[5].id | https://openalex.org/keywords/scaling |
| keywords[5].score | 0.4997286796569824 |
| keywords[5].display_name | Scaling |
| keywords[6].id | https://openalex.org/keywords/process |
| keywords[6].score | 0.4144141674041748 |
| keywords[6].display_name | Process (computing) |
| keywords[7].id | https://openalex.org/keywords/pattern-recognition |
| keywords[7].score | 0.35793477296829224 |
| keywords[7].display_name | Pattern recognition (psychology) |
| keywords[8].id | https://openalex.org/keywords/mathematics |
| keywords[8].score | 0.09528917074203491 |
| keywords[8].display_name | Mathematics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2202.10890 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2202.10890 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2202.10890 |
| locations[1].id | doi:10.48550/arxiv.2202.10890 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2202.10890 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5057909195 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | João Carreira |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Carreira, Joao |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5035812263 |
| authorships[1].author.orcid | https://orcid.org/0009-0007-5397-1854 |
| authorships[1].author.display_name | Skanda Koppula |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Koppula, Skanda |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5009514242 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Daniel Zoran |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zoran, Daniel |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5020406406 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Adrià Recasens |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Recasens, Adria |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5046449484 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Catalin Ionescu |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Ionescu, Catalin |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5081732358 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-8183-9489 |
| authorships[5].author.display_name | Olivier J. Hénaff |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Henaff, Olivier |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5023786468 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-5228-3095 |
| authorships[6].author.display_name | Evan Shelhamer |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Shelhamer, Evan |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5105286682 |
| authorships[7].author.orcid | |
| authorships[7].author.display_name | Relja Arandjelović |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Arandjelovic, Relja |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5114032765 |
| authorships[8].author.orcid | |
| authorships[8].author.display_name | Matt Botvinick |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Botvinick, Matt |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5003562101 |
| authorships[9].author.orcid | https://orcid.org/0000-0001-7848-7283 |
| authorships[9].author.display_name | Oriol Vinyals |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Vinyals, Oriol |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5004625775 |
| authorships[10].author.orcid | https://orcid.org/0000-0003-0787-5507 |
| authorships[10].author.display_name | Karen Simonyan |
| authorships[10].author_position | middle |
| authorships[10].raw_author_name | Simonyan, Karen |
| authorships[10].is_corresponding | False |
| authorships[11].author.id | https://openalex.org/A5057678172 |
| authorships[11].author.orcid | https://orcid.org/0000-0002-8945-8573 |
| authorships[11].author.display_name | Andrew Zisserman |
| authorships[11].author_position | middle |
| authorships[11].raw_author_name | Zisserman, Andrew |
| authorships[11].is_corresponding | False |
| authorships[12].author.id | https://openalex.org/A5051121535 |
| authorships[12].author.orcid | https://orcid.org/0000-0003-1698-9901 |
| authorships[12].author.display_name | Andrew Jaegle |
| authorships[12].author_position | last |
| authorships[12].raw_author_name | Jaegle, Andrew |
| authorships[12].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2202.10890 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | HiP: Hierarchical Perceiver |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10688 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9939000010490417 |
| 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 | Image and Signal Denoising Methods |
| related_works | https://openalex.org/W2045049461, https://openalex.org/W1978893398, https://openalex.org/W2201908702, https://openalex.org/W4381094582, https://openalex.org/W2369625323, https://openalex.org/W2364579609, https://openalex.org/W1977906818, https://openalex.org/W1522139108, https://openalex.org/W2353528968, https://openalex.org/W2003276812 |
| cited_by_count | 2 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2022 |
| counts_by_year[1].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2202.10890 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2202.10890 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2202.10890 |
| primary_location.id | pmh:oai:arXiv.org:2202.10890 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2202.10890 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2202.10890 |
| publication_date | 2022-02-22 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 20, 85, 104 |
| abstract_inverted_index.1) | 113 |
| abstract_inverted_index.2) | 123 |
| abstract_inverted_index.3) | 137 |
| abstract_inverted_index.In | 54, 108 |
| abstract_inverted_index.To | 79 |
| abstract_inverted_index.We | 99 |
| abstract_inverted_index.as | 4 |
| abstract_inverted_index.be | 65 |
| abstract_inverted_index.by | 29 |
| abstract_inverted_index.in | 10 |
| abstract_inverted_index.of | 62, 127 |
| abstract_inverted_index.on | 141 |
| abstract_inverted_index.or | 52, 163 |
| abstract_inverted_index.to | 16, 19, 42, 47, 117 |
| abstract_inverted_index.up | 18, 41 |
| abstract_inverted_index.we | 57, 83 |
| abstract_inverted_index.1M+ | 129 |
| abstract_inverted_index.and | 13, 121, 150, 159 |
| abstract_inverted_index.any | 11, 164 |
| abstract_inverted_index.are | 14 |
| abstract_inverted_index.can | 6, 64 |
| abstract_inverted_index.few | 21 |
| abstract_inverted_index.for | 95 |
| abstract_inverted_index.our | 110 |
| abstract_inverted_index.raw | 49, 118, 142 |
| abstract_inverted_index.sum | 109 |
| abstract_inverted_index.the | 43, 101, 125, 154 |
| abstract_inverted_index.They | 25 |
| abstract_inverted_index.This | 35 |
| abstract_inverted_index.VOC, | 148 |
| abstract_inverted_index.able | 15 |
| abstract_inverted_index.are: | 112 |
| abstract_inverted_index.back | 67 |
| abstract_inverted_index.call | 100 |
| abstract_inverted_index.data | 143 |
| abstract_inverted_index.from | 39, 132, 144 |
| abstract_inverted_index.into | 68 |
| abstract_inverted_index.same | 155 |
| abstract_inverted_index.show | 58 |
| abstract_inverted_index.some | 60 |
| abstract_inverted_index.such | 3 |
| abstract_inverted_index.that | 59, 88 |
| abstract_inverted_index.them | 38, 81 |
| abstract_inverted_index.this | 27, 55 |
| abstract_inverted_index.very | 96 |
| abstract_inverted_index.with | 153 |
| abstract_inverted_index.dense | 91 |
| abstract_inverted_index.large | 97 |
| abstract_inverted_index.model | 103, 158 |
| abstract_inverted_index.scale | 80 |
| abstract_inverted_index.sizes | 45 |
| abstract_inverted_index.their | 73, 77 |
| abstract_inverted_index.these | 69 |
| abstract_inverted_index.using | 30, 134 |
| abstract_inverted_index.while | 75 |
| abstract_inverted_index.(HiP). | 107 |
| abstract_inverted_index.PASCAL | 147 |
| abstract_inverted_index.degree | 61 |
| abstract_inverted_index.exact, | 156 |
| abstract_inverted_index.global | 32 |
| abstract_inverted_index.handle | 17 |
| abstract_inverted_index.images | 51, 120 |
| abstract_inverted_index.inputs | 44 |
| abstract_inverted_index.masked | 135 |
| abstract_inverted_index.models | 116 |
| abstract_inverted_index.paper, | 56 |
| abstract_inverted_index.video. | 53 |
| abstract_inverted_index.General | 0 |
| abstract_inverted_index.achieve | 26 |
| abstract_inverted_index.enables | 89 |
| abstract_inverted_index.greatly | 71 |
| abstract_inverted_index.hinders | 37 |
| abstract_inverted_index.however | 36 |
| abstract_inverted_index.hundred | 22 |
| abstract_inverted_index.inputs. | 24 |
| abstract_inverted_index.models, | 70 |
| abstract_inverted_index.process | 7, 48 |
| abstract_inverted_index.scaling | 40, 114 |
| abstract_inverted_index.scratch | 133 |
| abstract_inverted_index.showing | 124 |
| abstract_inverted_index.systems | 2 |
| abstract_inverted_index.without | 160 |
| abstract_inverted_index.Kinetics | 151 |
| abstract_inverted_index.approach | 87 |
| abstract_inverted_index.datasets | 152 |
| abstract_inverted_index.further, | 82 |
| abstract_inverted_index.learning | 90, 128 |
| abstract_inverted_index.locality | 63 |
| abstract_inverted_index.required | 46 |
| abstract_inverted_index.signals. | 98 |
| abstract_inverted_index.thousand | 23 |
| abstract_inverted_index.AudioSet, | 146 |
| abstract_inverted_index.ImageNet, | 145 |
| abstract_inverted_index.Perceiver | 106 |
| abstract_inverted_index.arbitrary | 8 |
| abstract_inverted_index.attention | 33 |
| abstract_inverted_index.improving | 72 |
| abstract_inverted_index.introduce | 84 |
| abstract_inverted_index.resulting | 102 |
| abstract_inverted_index.unchanged | 157 |
| abstract_inverted_index.ModelNet40 | 149 |
| abstract_inverted_index.Perceivers | 5 |
| abstract_inverted_index.efficiency | 74 |
| abstract_inverted_index.embeddings | 94, 131 |
| abstract_inverted_index.generality | 28 |
| abstract_inverted_index.introduced | 66 |
| abstract_inverted_index.modalities | 9 |
| abstract_inverted_index.perception | 1 |
| abstract_inverted_index.positional | 93, 130 |
| abstract_inverted_index.preserving | 76 |
| abstract_inverted_index.combination | 12 |
| abstract_inverted_index.competitive | 139 |
| abstract_inverted_index.exclusively | 31 |
| abstract_inverted_index.feasibility | 126 |
| abstract_inverted_index.generality. | 78 |
| abstract_inverted_index.operations. | 34 |
| abstract_inverted_index.performance | 140 |
| abstract_inverted_index.specialized | 161 |
| abstract_inverted_index.Hierarchical | 105 |
| abstract_inverted_index.audio+video, | 122 |
| abstract_inverted_index.contributions | 111 |
| abstract_inverted_index.demonstrating | 138 |
| abstract_inverted_index.preprocessing | 162 |
| abstract_inverted_index.tokenization. | 165 |
| abstract_inverted_index.Perceiver-type | 115 |
| abstract_inverted_index.auto-encoding, | 136 |
| abstract_inverted_index.high-resolution | 50, 119 |
| abstract_inverted_index.low-dimensional | 92 |
| abstract_inverted_index.self-supervised | 86 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 13 |
| citation_normalized_percentile |