GroupedMixer: An Entropy Model With Group-Wise Token-Mixers for Learned Image Compression Article Swipe
Daxin Li
,
Yuanchao Bai
,
Kai Wang
,
Junjun Jiang
,
Xianming Liu
,
Wen Gao
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.1109/tcsvt.2024.3395481
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.1109/tcsvt.2024.3395481
Transformer-based entropy models have gained prominence in recent years due\nto their superior ability to capture long-range dependencies in probability\ndistribution estimation compared to convolution-based methods. However,\nprevious transformer-based entropy models suffer from a sluggish coding process\ndue to pixel-wise autoregression or duplicated computation during inference. In\nthis paper, we propose a novel transformer-based entropy model called\nGroupedMixer, which enjoys both faster coding speed and better compression\nperformance than previous transformer-based methods. Specifically, our approach\nbuilds upon group-wise autoregression by first partitioning the latent\nvariables into groups along spatial-channel dimensions, and then entropy coding\nthe groups with the proposed transformer-based entropy model. The global causal\nself-attention is decomposed into more efficient group-wise interactions,\nimplemented using inner-group and cross-group token-mixers. The inner-group\ntoken-mixer incorporates contextual elements within a group while the\ncross-group token-mixer interacts with previously decoded groups. Alternate\narrangement of two token-mixers enables global contextual reference. To further\nexpedite the network inference, we introduce context cache optimization to\nGroupedMixer, which caches attention activation values in cross-group\ntoken-mixers and avoids complex and duplicated computation. Experimental\nresults demonstrate that the proposed GroupedMixer yields the state-of-the-art\nrate-distortion performance with fast compression speed.\n
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1109/tcsvt.2024.3395481
- OA Status
- green
- Cited By
- 9
- References
- 41
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4396505863
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4396505863Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1109/tcsvt.2024.3395481Digital Object Identifier
- Title
-
GroupedMixer: An Entropy Model With Group-Wise Token-Mixers for Learned Image CompressionWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-04-30Full publication date if available
- Authors
-
Daxin Li, Yuanchao Bai, Kai Wang, Junjun Jiang, Xianming Liu, Wen GaoList of authors in order
- Landing page
-
https://doi.org/10.1109/tcsvt.2024.3395481Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2405.01170Direct OA link when available
- Concepts
-
Image compression, Computer science, Entropy (arrow of time), Data compression, Artificial intelligence, Image processing, Image (mathematics), Computer vision, Quantum mechanics, PhysicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
9Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 6, 2024: 3Per-year citation counts (last 5 years)
- References (count)
-
41Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4396505863 |
|---|---|
| doi | https://doi.org/10.1109/tcsvt.2024.3395481 |
| ids.doi | https://doi.org/10.1109/tcsvt.2024.3395481 |
| ids.openalex | https://openalex.org/W4396505863 |
| fwci | 4.77141804 |
| type | article |
| title | GroupedMixer: An Entropy Model With Group-Wise Token-Mixers for Learned Image Compression |
| awards[0].id | https://openalex.org/G6167212925 |
| awards[0].funder_id | https://openalex.org/F4320321001 |
| awards[0].display_name | |
| awards[0].funder_award_id | 62071155 |
| awards[0].funder_display_name | National Natural Science Foundation of China |
| awards[1].id | https://openalex.org/G5778169039 |
| awards[1].funder_id | https://openalex.org/F4320321001 |
| awards[1].display_name | |
| awards[1].funder_award_id | U23B2009 |
| awards[1].funder_display_name | National Natural Science Foundation of China |
| awards[2].id | https://openalex.org/G5162550898 |
| awards[2].funder_id | https://openalex.org/F4320321543 |
| awards[2].display_name | |
| awards[2].funder_award_id | 2022M710958 |
| awards[2].funder_display_name | China Postdoctoral Science Foundation |
| awards[3].id | https://openalex.org/G2268537015 |
| awards[3].funder_id | https://openalex.org/F4320321001 |
| awards[3].display_name | |
| awards[3].funder_award_id | 92270116 |
| awards[3].funder_display_name | National Natural Science Foundation of China |
| awards[4].id | https://openalex.org/G8725055283 |
| awards[4].funder_id | https://openalex.org/F4320321001 |
| awards[4].display_name | |
| awards[4].funder_award_id | 62301188 |
| awards[4].funder_display_name | National Natural Science Foundation of China |
| biblio.issue | 10 |
| biblio.volume | 34 |
| biblio.last_page | 9619 |
| biblio.first_page | 9606 |
| topics[0].id | https://openalex.org/T10901 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9983000159263611 |
| 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 Data Compression Techniques |
| topics[1].id | https://openalex.org/T10688 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9830999970436096 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Image and Signal Denoising Methods |
| topics[2].id | https://openalex.org/T10824 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9818999767303467 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Image Retrieval and Classification Techniques |
| funders[0].id | https://openalex.org/F4320321001 |
| funders[0].ror | https://ror.org/01h0zpd94 |
| funders[0].display_name | National Natural Science Foundation of China |
| funders[1].id | https://openalex.org/F4320321543 |
| funders[1].ror | https://ror.org/0426zh255 |
| funders[1].display_name | China Postdoctoral Science Foundation |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C13481523 |
| concepts[0].level | 4 |
| concepts[0].score | 0.6135194301605225 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q412438 |
| concepts[0].display_name | Image compression |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.5955279469490051 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C106301342 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5044752359390259 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q4117933 |
| concepts[2].display_name | Entropy (arrow of time) |
| concepts[3].id | https://openalex.org/C78548338 |
| concepts[3].level | 2 |
| concepts[3].score | 0.4342862665653229 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2493 |
| concepts[3].display_name | Data compression |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.42191582918167114 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C9417928 |
| concepts[5].level | 3 |
| concepts[5].score | 0.41670531034469604 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1070689 |
| concepts[5].display_name | Image processing |
| concepts[6].id | https://openalex.org/C115961682 |
| concepts[6].level | 2 |
| concepts[6].score | 0.37923941016197205 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[6].display_name | Image (mathematics) |
| concepts[7].id | https://openalex.org/C31972630 |
| concepts[7].level | 1 |
| concepts[7].score | 0.3654847741127014 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[7].display_name | Computer vision |
| concepts[8].id | https://openalex.org/C62520636 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[8].display_name | Quantum mechanics |
| concepts[9].id | https://openalex.org/C121332964 |
| concepts[9].level | 0 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[9].display_name | Physics |
| keywords[0].id | https://openalex.org/keywords/image-compression |
| keywords[0].score | 0.6135194301605225 |
| keywords[0].display_name | Image compression |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.5955279469490051 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/entropy |
| keywords[2].score | 0.5044752359390259 |
| keywords[2].display_name | Entropy (arrow of time) |
| keywords[3].id | https://openalex.org/keywords/data-compression |
| keywords[3].score | 0.4342862665653229 |
| keywords[3].display_name | Data compression |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.42191582918167114 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/image-processing |
| keywords[5].score | 0.41670531034469604 |
| keywords[5].display_name | Image processing |
| keywords[6].id | https://openalex.org/keywords/image |
| keywords[6].score | 0.37923941016197205 |
| keywords[6].display_name | Image (mathematics) |
| keywords[7].id | https://openalex.org/keywords/computer-vision |
| keywords[7].score | 0.3654847741127014 |
| keywords[7].display_name | Computer vision |
| language | en |
| locations[0].id | doi:10.1109/tcsvt.2024.3395481 |
| locations[0].is_oa | False |
| locations[0].source.id | https://openalex.org/S115173108 |
| locations[0].source.issn | 1051-8215, 1558-2205 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 1051-8215 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | IEEE Transactions on Circuits and Systems for Video Technology |
| locations[0].source.host_organization | https://openalex.org/P4310319808 |
| locations[0].source.host_organization_name | Institute of Electrical and Electronics Engineers |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310319808 |
| locations[0].source.host_organization_lineage_names | Institute of Electrical and Electronics Engineers |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | IEEE Transactions on Circuits and Systems for Video Technology |
| locations[0].landing_page_url | https://doi.org/10.1109/tcsvt.2024.3395481 |
| locations[1].id | pmh:oai:arXiv.org:2405.01170 |
| 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 | |
| locations[1].pdf_url | https://arxiv.org/pdf/2405.01170 |
| locations[1].version | submittedVersion |
| locations[1].raw_type | text |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | http://arxiv.org/abs/2405.01170 |
| indexed_in | arxiv, crossref |
| authorships[0].author.id | https://openalex.org/A5007227942 |
| authorships[0].author.orcid | https://orcid.org/0009-0001-6886-3342 |
| authorships[0].author.display_name | Daxin Li |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I204983213 |
| authorships[0].affiliations[0].raw_affiliation_string | School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China, |
| authorships[0].institutions[0].id | https://openalex.org/I204983213 |
| authorships[0].institutions[0].ror | https://ror.org/01yqg2h08 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I204983213 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Harbin Institute of Technology |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Daxin Li |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China, |
| authorships[1].author.id | https://openalex.org/A5024093994 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-3449-6537 |
| authorships[1].author.display_name | Yuanchao Bai |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I204983213 |
| authorships[1].affiliations[0].raw_affiliation_string | School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China, |
| authorships[1].institutions[0].id | https://openalex.org/I204983213 |
| authorships[1].institutions[0].ror | https://ror.org/01yqg2h08 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I204983213 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Harbin Institute of Technology |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Yuanchao Bai |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China, |
| authorships[2].author.id | https://openalex.org/A5100766811 |
| authorships[2].author.orcid | https://orcid.org/0009-0007-3132-0495 |
| authorships[2].author.display_name | Kai Wang |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I204983213 |
| authorships[2].affiliations[0].raw_affiliation_string | School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China, |
| authorships[2].institutions[0].id | https://openalex.org/I204983213 |
| authorships[2].institutions[0].ror | https://ror.org/01yqg2h08 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I204983213 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Harbin Institute of Technology |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Kai Wang |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China, |
| authorships[3].author.id | https://openalex.org/A5087165831 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-5694-505X |
| authorships[3].author.display_name | Junjun Jiang |
| authorships[3].countries | CN |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I204983213 |
| authorships[3].affiliations[0].raw_affiliation_string | School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China, |
| authorships[3].institutions[0].id | https://openalex.org/I204983213 |
| authorships[3].institutions[0].ror | https://ror.org/01yqg2h08 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I204983213 |
| authorships[3].institutions[0].country_code | CN |
| authorships[3].institutions[0].display_name | Harbin Institute of Technology |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Junjun Jiang |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China, |
| authorships[4].author.id | https://openalex.org/A5100654390 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-8857-1785 |
| authorships[4].author.display_name | Xianming Liu |
| authorships[4].countries | CN |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I204983213 |
| authorships[4].affiliations[0].raw_affiliation_string | School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China, |
| authorships[4].institutions[0].id | https://openalex.org/I204983213 |
| authorships[4].institutions[0].ror | https://ror.org/01yqg2h08 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I204983213 |
| authorships[4].institutions[0].country_code | CN |
| authorships[4].institutions[0].display_name | Harbin Institute of Technology |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Xianming Liu |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China, |
| authorships[5].author.id | https://openalex.org/A5018478553 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-8070-802X |
| authorships[5].author.display_name | Wen Gao |
| authorships[5].countries | CN |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I204983213 |
| authorships[5].affiliations[0].raw_affiliation_string | School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China, |
| authorships[5].institutions[0].id | https://openalex.org/I204983213 |
| authorships[5].institutions[0].ror | https://ror.org/01yqg2h08 |
| authorships[5].institutions[0].type | education |
| authorships[5].institutions[0].lineage | https://openalex.org/I204983213 |
| authorships[5].institutions[0].country_code | CN |
| authorships[5].institutions[0].display_name | Harbin Institute of Technology |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Wen Gao |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China, |
| 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/2405.01170 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-05-01T00:00:00 |
| display_name | GroupedMixer: An Entropy Model With Group-Wise Token-Mixers for Learned Image Compression |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10901 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9983000159263611 |
| 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 Data Compression Techniques |
| related_works | https://openalex.org/W2129829718, https://openalex.org/W2521595930, https://openalex.org/W4243608781, https://openalex.org/W3165542721, https://openalex.org/W4313046148, https://openalex.org/W1939109514, https://openalex.org/W4378191574, https://openalex.org/W2161981399, https://openalex.org/W2595043295, https://openalex.org/W2387043686 |
| cited_by_count | 9 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 6 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 3 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2405.01170 |
| 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/2405.01170 |
| 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/2405.01170 |
| primary_location.id | doi:10.1109/tcsvt.2024.3395481 |
| primary_location.is_oa | False |
| primary_location.source.id | https://openalex.org/S115173108 |
| primary_location.source.issn | 1051-8215, 1558-2205 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 1051-8215 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | IEEE Transactions on Circuits and Systems for Video Technology |
| primary_location.source.host_organization | https://openalex.org/P4310319808 |
| primary_location.source.host_organization_name | Institute of Electrical and Electronics Engineers |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310319808 |
| primary_location.source.host_organization_lineage_names | Institute of Electrical and Electronics Engineers |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | IEEE Transactions on Circuits and Systems for Video Technology |
| primary_location.landing_page_url | https://doi.org/10.1109/tcsvt.2024.3395481 |
| publication_date | 2024-04-30 |
| publication_year | 2024 |
| referenced_works | https://openalex.org/W6694251005, https://openalex.org/W2785562966, https://openalex.org/W3034469748, https://openalex.org/W2740336064, https://openalex.org/W6754634825, https://openalex.org/W3175457126, https://openalex.org/W3091266734, https://openalex.org/W4312806968, https://openalex.org/W6810067190, https://openalex.org/W4312934587, https://openalex.org/W4386075611, https://openalex.org/W4309134821, https://openalex.org/W3134748538, https://openalex.org/W6784858424, https://openalex.org/W3201765774, https://openalex.org/W3207351130, https://openalex.org/W3206996732, https://openalex.org/W6734035190, https://openalex.org/W3116647679, https://openalex.org/W4312949231, https://openalex.org/W3033326602, https://openalex.org/W4223425316, https://openalex.org/W3202918664, https://openalex.org/W4385245566, https://openalex.org/W4225619305, https://openalex.org/W4390480875, https://openalex.org/W6762805079, https://openalex.org/W6756754865, https://openalex.org/W6803277560, https://openalex.org/W3185645081, https://openalex.org/W4311415873, https://openalex.org/W6792695861, https://openalex.org/W3176998540, https://openalex.org/W6631190155, https://openalex.org/W3097448661, https://openalex.org/W2741137940, https://openalex.org/W68733909, https://openalex.org/W2117539524, https://openalex.org/W6696118455, https://openalex.org/W4297659253, https://openalex.org/W4287605633 |
| referenced_works_count | 41 |
| abstract_inverted_index.a | 30, 46, 113 |
| abstract_inverted_index.To | 131 |
| abstract_inverted_index.by | 71 |
| abstract_inverted_index.in | 6, 17, 147 |
| abstract_inverted_index.is | 95 |
| abstract_inverted_index.of | 124 |
| abstract_inverted_index.or | 37 |
| abstract_inverted_index.to | 13, 21, 34 |
| abstract_inverted_index.we | 44, 136 |
| abstract_inverted_index.The | 92, 107 |
| abstract_inverted_index.and | 58, 81, 104, 149, 152 |
| abstract_inverted_index.our | 66 |
| abstract_inverted_index.the | 74, 87, 133, 158, 162 |
| abstract_inverted_index.two | 125 |
| abstract_inverted_index.both | 54 |
| abstract_inverted_index.fast | 166 |
| abstract_inverted_index.from | 29 |
| abstract_inverted_index.have | 3 |
| abstract_inverted_index.into | 76, 97 |
| abstract_inverted_index.more | 98 |
| abstract_inverted_index.than | 61 |
| abstract_inverted_index.that | 157 |
| abstract_inverted_index.then | 82 |
| abstract_inverted_index.upon | 68 |
| abstract_inverted_index.with | 86, 119, 165 |
| abstract_inverted_index.along | 78 |
| abstract_inverted_index.cache | 139 |
| abstract_inverted_index.first | 72 |
| abstract_inverted_index.group | 114 |
| abstract_inverted_index.model | 50 |
| abstract_inverted_index.novel | 47 |
| abstract_inverted_index.speed | 57 |
| abstract_inverted_index.their | 10 |
| abstract_inverted_index.using | 102 |
| abstract_inverted_index.which | 52, 142 |
| abstract_inverted_index.while | 115 |
| abstract_inverted_index.years | 8 |
| abstract_inverted_index.avoids | 150 |
| abstract_inverted_index.better | 59 |
| abstract_inverted_index.caches | 143 |
| abstract_inverted_index.coding | 32, 56 |
| abstract_inverted_index.during | 40 |
| abstract_inverted_index.enjoys | 53 |
| abstract_inverted_index.faster | 55 |
| abstract_inverted_index.gained | 4 |
| abstract_inverted_index.global | 93, 128 |
| abstract_inverted_index.groups | 77, 85 |
| abstract_inverted_index.model. | 91 |
| abstract_inverted_index.models | 2, 27 |
| abstract_inverted_index.paper, | 43 |
| abstract_inverted_index.recent | 7 |
| abstract_inverted_index.suffer | 28 |
| abstract_inverted_index.values | 146 |
| abstract_inverted_index.within | 112 |
| abstract_inverted_index.yields | 161 |
| abstract_inverted_index.ability | 12 |
| abstract_inverted_index.capture | 14 |
| abstract_inverted_index.complex | 151 |
| abstract_inverted_index.context | 138 |
| abstract_inverted_index.decoded | 121 |
| abstract_inverted_index.due\nto | 9 |
| abstract_inverted_index.enables | 127 |
| abstract_inverted_index.entropy | 1, 26, 49, 83, 90 |
| abstract_inverted_index.groups. | 122 |
| abstract_inverted_index.network | 134 |
| abstract_inverted_index.propose | 45 |
| abstract_inverted_index.In\nthis | 42 |
| abstract_inverted_index.compared | 20 |
| abstract_inverted_index.elements | 111 |
| abstract_inverted_index.methods. | 23, 64 |
| abstract_inverted_index.previous | 62 |
| abstract_inverted_index.proposed | 88, 159 |
| abstract_inverted_index.sluggish | 31 |
| abstract_inverted_index.speed.\n | 168 |
| abstract_inverted_index.superior | 11 |
| abstract_inverted_index.attention | 144 |
| abstract_inverted_index.efficient | 99 |
| abstract_inverted_index.interacts | 118 |
| abstract_inverted_index.introduce | 137 |
| abstract_inverted_index.activation | 145 |
| abstract_inverted_index.contextual | 110, 129 |
| abstract_inverted_index.decomposed | 96 |
| abstract_inverted_index.duplicated | 38, 153 |
| abstract_inverted_index.estimation | 19 |
| abstract_inverted_index.group-wise | 69, 100 |
| abstract_inverted_index.inference, | 135 |
| abstract_inverted_index.inference. | 41 |
| abstract_inverted_index.long-range | 15 |
| abstract_inverted_index.pixel-wise | 35 |
| abstract_inverted_index.previously | 120 |
| abstract_inverted_index.prominence | 5 |
| abstract_inverted_index.reference. | 130 |
| abstract_inverted_index.coding\nthe | 84 |
| abstract_inverted_index.compression | 167 |
| abstract_inverted_index.computation | 39 |
| abstract_inverted_index.cross-group | 105 |
| abstract_inverted_index.demonstrate | 156 |
| abstract_inverted_index.dimensions, | 80 |
| abstract_inverted_index.inner-group | 103 |
| abstract_inverted_index.performance | 164 |
| abstract_inverted_index.token-mixer | 117 |
| abstract_inverted_index.GroupedMixer | 160 |
| abstract_inverted_index.computation. | 154 |
| abstract_inverted_index.dependencies | 16 |
| abstract_inverted_index.incorporates | 109 |
| abstract_inverted_index.optimization | 140 |
| abstract_inverted_index.partitioning | 73 |
| abstract_inverted_index.process\ndue | 33 |
| abstract_inverted_index.token-mixers | 126 |
| abstract_inverted_index.Specifically, | 65 |
| abstract_inverted_index.token-mixers. | 106 |
| abstract_inverted_index.autoregression | 36, 70 |
| abstract_inverted_index.spatial-channel | 79 |
| abstract_inverted_index.approach\nbuilds | 67 |
| abstract_inverted_index.the\ncross-group | 116 |
| abstract_inverted_index.Transformer-based | 0 |
| abstract_inverted_index.convolution-based | 22 |
| abstract_inverted_index.further\nexpedite | 132 |
| abstract_inverted_index.latent\nvariables | 75 |
| abstract_inverted_index.to\nGroupedMixer, | 141 |
| abstract_inverted_index.transformer-based | 25, 48, 63, 89 |
| abstract_inverted_index.However,\nprevious | 24 |
| abstract_inverted_index.Experimental\nresults | 155 |
| abstract_inverted_index.called\nGroupedMixer, | 51 |
| abstract_inverted_index.Alternate\narrangement | 123 |
| abstract_inverted_index.causal\nself-attention | 94 |
| abstract_inverted_index.compression\nperformance | 60 |
| abstract_inverted_index.inner-group\ntoken-mixer | 108 |
| abstract_inverted_index.cross-group\ntoken-mixers | 148 |
| abstract_inverted_index.probability\ndistribution | 18 |
| abstract_inverted_index.interactions,\nimplemented | 101 |
| abstract_inverted_index.state-of-the-art\nrate-distortion | 163 |
| cited_by_percentile_year.max | 99 |
| cited_by_percentile_year.min | 96 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile.value | 0.92422349 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |