Optimized Learned Entropy Coding Parameters for Practical Neural-Based Image and Video Compression Article Swipe
Amir Said
,
Reza Pourreza
,
Hoang Le
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1109/icip46576.2022.9897505
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1109/icip46576.2022.9897505
Neural-based image and video codecs are significantly more power-efficient\nwhen weights and activations are quantized to low-precision integers. While\nthere are general-purpose techniques for reducing quantization effects, large\nlosses can occur when specific entropy coding properties are not considered.\nThis work analyzes how entropy coding is affected by parameter quantizations,\nand provides a method to minimize losses. It is shown that, by using a certain\ntype of coding parameters to be learned, uniform quantization becomes\npractically optimal, also simplifying the minimization of code memory\nrequirements. The mathematical properties of the new representation are\npresented, and its effectiveness is demonstrated by coding experiments, showing\nthat good results can be obtained with precision as low as 4~bits per network\noutput, and practically no loss with 8~bits.\n
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1109/icip46576.2022.9897505
- OA Status
- green
- Cited By
- 1
- References
- 21
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4308236220
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4308236220Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1109/icip46576.2022.9897505Digital Object Identifier
- Title
-
Optimized Learned Entropy Coding Parameters for Practical Neural-Based Image and Video CompressionWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-10-16Full publication date if available
- Authors
-
Amir Said, Reza Pourreza, Hoang LeList of authors in order
- Landing page
-
https://doi.org/10.1109/icip46576.2022.9897505Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2301.08752Direct OA link when available
- Concepts
-
Computer science, Data compression, Artificial intelligence, Entropy encoding, Entropy (arrow of time), Image compression, Coding (social sciences), Computer vision, Pattern recognition (psychology), Image processing, Image (mathematics), Mathematics, Statistics, Physics, Quantum mechanicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 1Per-year citation counts (last 5 years)
- References (count)
-
21Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4308236220 |
|---|---|
| doi | https://doi.org/10.1109/icip46576.2022.9897505 |
| ids.doi | https://doi.org/10.1109/icip46576.2022.9897505 |
| ids.openalex | https://openalex.org/W4308236220 |
| fwci | 0.06904426 |
| type | article |
| title | Optimized Learned Entropy Coding Parameters for Practical Neural-Based Image and Video Compression |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 665 |
| biblio.first_page | 661 |
| 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 | 0.9998999834060669 |
| 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 Data Compression Techniques |
| topics[1].id | https://openalex.org/T10741 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9991999864578247 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1711 |
| topics[1].subfield.display_name | Signal Processing |
| topics[1].display_name | Video Coding and Compression Technologies |
| topics[2].id | https://openalex.org/T10688 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9990000128746033 |
| 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 and Signal Denoising Methods |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.6689554452896118 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C78548338 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6209424138069153 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q2493 |
| concepts[1].display_name | Data compression |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.5672028064727783 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C1769480 |
| concepts[3].level | 3 |
| concepts[3].score | 0.5458356738090515 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1345239 |
| concepts[3].display_name | Entropy encoding |
| concepts[4].id | https://openalex.org/C106301342 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5062112212181091 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q4117933 |
| concepts[4].display_name | Entropy (arrow of time) |
| concepts[5].id | https://openalex.org/C13481523 |
| concepts[5].level | 4 |
| concepts[5].score | 0.4409826397895813 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q412438 |
| concepts[5].display_name | Image compression |
| concepts[6].id | https://openalex.org/C179518139 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4302099943161011 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q5140297 |
| concepts[6].display_name | Coding (social sciences) |
| concepts[7].id | https://openalex.org/C31972630 |
| concepts[7].level | 1 |
| concepts[7].score | 0.4066624641418457 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[7].display_name | Computer vision |
| concepts[8].id | https://openalex.org/C153180895 |
| concepts[8].level | 2 |
| concepts[8].score | 0.33438926935195923 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[8].display_name | Pattern recognition (psychology) |
| concepts[9].id | https://openalex.org/C9417928 |
| concepts[9].level | 3 |
| concepts[9].score | 0.28022170066833496 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q1070689 |
| concepts[9].display_name | Image processing |
| concepts[10].id | https://openalex.org/C115961682 |
| concepts[10].level | 2 |
| concepts[10].score | 0.2133502960205078 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[10].display_name | Image (mathematics) |
| concepts[11].id | https://openalex.org/C33923547 |
| concepts[11].level | 0 |
| concepts[11].score | 0.15859845280647278 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[11].display_name | Mathematics |
| concepts[12].id | https://openalex.org/C105795698 |
| concepts[12].level | 1 |
| concepts[12].score | 0.08149188756942749 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[12].display_name | Statistics |
| concepts[13].id | https://openalex.org/C121332964 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[13].display_name | Physics |
| concepts[14].id | https://openalex.org/C62520636 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[14].display_name | Quantum mechanics |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.6689554452896118 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/data-compression |
| keywords[1].score | 0.6209424138069153 |
| keywords[1].display_name | Data compression |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.5672028064727783 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/entropy-encoding |
| keywords[3].score | 0.5458356738090515 |
| keywords[3].display_name | Entropy encoding |
| keywords[4].id | https://openalex.org/keywords/entropy |
| keywords[4].score | 0.5062112212181091 |
| keywords[4].display_name | Entropy (arrow of time) |
| keywords[5].id | https://openalex.org/keywords/image-compression |
| keywords[5].score | 0.4409826397895813 |
| keywords[5].display_name | Image compression |
| keywords[6].id | https://openalex.org/keywords/coding |
| keywords[6].score | 0.4302099943161011 |
| keywords[6].display_name | Coding (social sciences) |
| keywords[7].id | https://openalex.org/keywords/computer-vision |
| keywords[7].score | 0.4066624641418457 |
| keywords[7].display_name | Computer vision |
| keywords[8].id | https://openalex.org/keywords/pattern-recognition |
| keywords[8].score | 0.33438926935195923 |
| keywords[8].display_name | Pattern recognition (psychology) |
| keywords[9].id | https://openalex.org/keywords/image-processing |
| keywords[9].score | 0.28022170066833496 |
| keywords[9].display_name | Image processing |
| keywords[10].id | https://openalex.org/keywords/image |
| keywords[10].score | 0.2133502960205078 |
| keywords[10].display_name | Image (mathematics) |
| keywords[11].id | https://openalex.org/keywords/mathematics |
| keywords[11].score | 0.15859845280647278 |
| keywords[11].display_name | Mathematics |
| keywords[12].id | https://openalex.org/keywords/statistics |
| keywords[12].score | 0.08149188756942749 |
| keywords[12].display_name | Statistics |
| language | en |
| locations[0].id | doi:10.1109/icip46576.2022.9897505 |
| locations[0].is_oa | False |
| locations[0].source.id | https://openalex.org/S4363607719 |
| locations[0].source.issn | |
| locations[0].source.type | conference |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | 2022 IEEE International Conference on Image Processing (ICIP) |
| locations[0].source.host_organization | |
| locations[0].source.host_organization_name | |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | 2022 IEEE International Conference on Image Processing (ICIP) |
| locations[0].landing_page_url | https://doi.org/10.1109/icip46576.2022.9897505 |
| locations[1].id | pmh:oai:arXiv.org:2301.08752 |
| 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/2301.08752 |
| 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/2301.08752 |
| indexed_in | arxiv, crossref |
| authorships[0].author.id | https://openalex.org/A5017153875 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-1802-3513 |
| authorships[0].author.display_name | Amir Said |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I4210087596 |
| authorships[0].affiliations[0].raw_affiliation_string | Qualcomm AI Research, San Diego, CA, USA |
| authorships[0].institutions[0].id | https://openalex.org/I4210087596 |
| authorships[0].institutions[0].ror | https://ror.org/002zrf773 |
| authorships[0].institutions[0].type | company |
| authorships[0].institutions[0].lineage | https://openalex.org/I4210087596 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | Qualcomm (United States) |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Amir Said |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Qualcomm AI Research, San Diego, CA, USA |
| authorships[1].author.id | https://openalex.org/A5032352523 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-9667-1209 |
| authorships[1].author.display_name | Reza Pourreza |
| authorships[1].countries | US |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I4210087596 |
| authorships[1].affiliations[0].raw_affiliation_string | Qualcomm AI Research, San Diego, CA, USA |
| authorships[1].institutions[0].id | https://openalex.org/I4210087596 |
| authorships[1].institutions[0].ror | https://ror.org/002zrf773 |
| authorships[1].institutions[0].type | company |
| authorships[1].institutions[0].lineage | https://openalex.org/I4210087596 |
| authorships[1].institutions[0].country_code | US |
| authorships[1].institutions[0].display_name | Qualcomm (United States) |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Reza Pourreza |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Qualcomm AI Research, San Diego, CA, USA |
| authorships[2].author.id | https://openalex.org/A5017657388 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Hoang Le |
| authorships[2].countries | US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I4210087596 |
| authorships[2].affiliations[0].raw_affiliation_string | Qualcomm AI Research, San Diego, CA, USA |
| authorships[2].institutions[0].id | https://openalex.org/I4210087596 |
| authorships[2].institutions[0].ror | https://ror.org/002zrf773 |
| authorships[2].institutions[0].type | company |
| authorships[2].institutions[0].lineage | https://openalex.org/I4210087596 |
| authorships[2].institutions[0].country_code | US |
| authorships[2].institutions[0].display_name | Qualcomm (United States) |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Hoang Le |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Qualcomm AI Research, San Diego, CA, USA |
| 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/2301.08752 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Optimized Learned Entropy Coding Parameters for Practical Neural-Based Image and Video 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 | 0.9998999834060669 |
| 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 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/W3156493487, https://openalex.org/W2595043295 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2301.08752 |
| 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/2301.08752 |
| 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/2301.08752 |
| primary_location.id | doi:10.1109/icip46576.2022.9897505 |
| primary_location.is_oa | False |
| primary_location.source.id | https://openalex.org/S4363607719 |
| primary_location.source.issn | |
| primary_location.source.type | conference |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | 2022 IEEE International Conference on Image Processing (ICIP) |
| primary_location.source.host_organization | |
| primary_location.source.host_organization_name | |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | 2022 IEEE International Conference on Image Processing (ICIP) |
| primary_location.landing_page_url | https://doi.org/10.1109/icip46576.2022.9897505 |
| publication_date | 2022-10-16 |
| publication_year | 2022 |
| referenced_works | https://openalex.org/W2935381027, https://openalex.org/W3134670382, https://openalex.org/W3014840603, https://openalex.org/W2981751377, https://openalex.org/W6796815506, https://openalex.org/W3184606595, https://openalex.org/W2146395539, https://openalex.org/W105762734, https://openalex.org/W3202918664, https://openalex.org/W2128777897, https://openalex.org/W3022713761, https://openalex.org/W6679873336, https://openalex.org/W2785562966, https://openalex.org/W2913710883, https://openalex.org/W2325850497, https://openalex.org/W2741230247, https://openalex.org/W4239146293, https://openalex.org/W2964098744, https://openalex.org/W4319165719, https://openalex.org/W4287118909, https://openalex.org/W4287388223 |
| referenced_works_count | 21 |
| abstract_inverted_index.a | 47, 58 |
| abstract_inverted_index.It | 52 |
| abstract_inverted_index.as | 101, 103 |
| abstract_inverted_index.be | 64, 97 |
| abstract_inverted_index.by | 43, 56, 90 |
| abstract_inverted_index.is | 41, 53, 88 |
| abstract_inverted_index.no | 109 |
| abstract_inverted_index.of | 60, 74, 80 |
| abstract_inverted_index.to | 14, 49, 63 |
| abstract_inverted_index.The | 77 |
| abstract_inverted_index.and | 2, 10, 85, 107 |
| abstract_inverted_index.are | 5, 12, 18, 33 |
| abstract_inverted_index.can | 26, 96 |
| abstract_inverted_index.for | 21 |
| abstract_inverted_index.how | 38 |
| abstract_inverted_index.its | 86 |
| abstract_inverted_index.low | 102 |
| abstract_inverted_index.new | 82 |
| abstract_inverted_index.not | 34 |
| abstract_inverted_index.per | 105 |
| abstract_inverted_index.the | 72, 81 |
| abstract_inverted_index.also | 70 |
| abstract_inverted_index.code | 75 |
| abstract_inverted_index.good | 94 |
| abstract_inverted_index.loss | 110 |
| abstract_inverted_index.more | 7 |
| abstract_inverted_index.when | 28 |
| abstract_inverted_index.with | 99, 111 |
| abstract_inverted_index.work | 36 |
| abstract_inverted_index.image | 1 |
| abstract_inverted_index.occur | 27 |
| abstract_inverted_index.shown | 54 |
| abstract_inverted_index.that, | 55 |
| abstract_inverted_index.using | 57 |
| abstract_inverted_index.video | 3 |
| abstract_inverted_index.4~bits | 104 |
| abstract_inverted_index.codecs | 4 |
| abstract_inverted_index.coding | 31, 40, 61, 91 |
| abstract_inverted_index.method | 48 |
| abstract_inverted_index.entropy | 30, 39 |
| abstract_inverted_index.losses. | 51 |
| abstract_inverted_index.results | 95 |
| abstract_inverted_index.uniform | 66 |
| abstract_inverted_index.weights | 9 |
| abstract_inverted_index.affected | 42 |
| abstract_inverted_index.analyzes | 37 |
| abstract_inverted_index.effects, | 24 |
| abstract_inverted_index.learned, | 65 |
| abstract_inverted_index.minimize | 50 |
| abstract_inverted_index.obtained | 98 |
| abstract_inverted_index.optimal, | 69 |
| abstract_inverted_index.provides | 46 |
| abstract_inverted_index.reducing | 22 |
| abstract_inverted_index.specific | 29 |
| abstract_inverted_index.8~bits.\n | 112 |
| abstract_inverted_index.integers. | 16 |
| abstract_inverted_index.parameter | 44 |
| abstract_inverted_index.precision | 100 |
| abstract_inverted_index.quantized | 13 |
| abstract_inverted_index.parameters | 62 |
| abstract_inverted_index.properties | 32, 79 |
| abstract_inverted_index.techniques | 20 |
| abstract_inverted_index.activations | 11 |
| abstract_inverted_index.practically | 108 |
| abstract_inverted_index.simplifying | 71 |
| abstract_inverted_index.Neural-based | 0 |
| abstract_inverted_index.While\nthere | 17 |
| abstract_inverted_index.demonstrated | 89 |
| abstract_inverted_index.experiments, | 92 |
| abstract_inverted_index.mathematical | 78 |
| abstract_inverted_index.minimization | 73 |
| abstract_inverted_index.quantization | 23, 67 |
| abstract_inverted_index.certain\ntype | 59 |
| abstract_inverted_index.effectiveness | 87 |
| abstract_inverted_index.large\nlosses | 25 |
| abstract_inverted_index.low-precision | 15 |
| abstract_inverted_index.showing\nthat | 93 |
| abstract_inverted_index.significantly | 6 |
| abstract_inverted_index.representation | 83 |
| abstract_inverted_index.are\npresented, | 84 |
| abstract_inverted_index.general-purpose | 19 |
| abstract_inverted_index.network\noutput, | 106 |
| abstract_inverted_index.considered.\nThis | 35 |
| abstract_inverted_index.quantizations,\nand | 45 |
| abstract_inverted_index.becomes\npractically | 68 |
| abstract_inverted_index.memory\nrequirements. | 76 |
| abstract_inverted_index.power-efficient\nwhen | 8 |
| cited_by_percentile_year.max | 94 |
| cited_by_percentile_year.min | 90 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile.value | 0.29597373 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |