Shift-and-Balance Attention Article Swipe
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2103.13080
Attention is an effective mechanism to improve the deep model capability. Squeeze-and-Excite (SE) introduces a light-weight attention branch to enhance the network's representational power. The attention branch is gated using the Sigmoid function and multiplied by the feature map's trunk branch. It is too sensitive to coordinate and balance the trunk and attention branches' contributions. To control the attention branch's influence, we propose a new attention method, called Shift-and-Balance (SB). Different from Squeeze-and-Excite, the attention branch is regulated by the learned control factor to control the balance, then added into the feature map's trunk branch. Experiments show that Shift-and-Balance attention significantly improves the accuracy compared to Squeeze-and-Excite when applied in more layers, increasing more size and capacity of a network. Moreover, Shift-and-Balance attention achieves better or close accuracy compared to the state-of-art Dynamic Convolution.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2103.13080
- https://arxiv.org/pdf/2103.13080
- OA Status
- green
- Cited By
- 1
- References
- 39
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3138152811
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3138152811Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2103.13080Digital Object Identifier
- Title
-
Shift-and-Balance AttentionWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-03-24Full publication date if available
- Authors
-
Chunjie Luo, Jianfeng Zhan, Tianshu Hao, Lei Wang, Wanling GaoList of authors in order
- Landing page
-
https://arxiv.org/abs/2103.13080Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2103.13080Direct 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/2103.13080Direct OA link when available
- Concepts
-
Balance (ability), Feature (linguistics), Power (physics), Trunk, Computer science, Control (management), Attention network, Sigmoid function, Convolution (computer science), Dynamic balance, Control theory (sociology), Artificial intelligence, Engineering, Artificial neural network, Psychology, Physics, Neuroscience, Philosophy, Quantum mechanics, Ecology, Mechanical engineering, Biology, LinguisticsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2021: 1Per-year citation counts (last 5 years)
- References (count)
-
39Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3138152811 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2103.13080 |
| ids.doi | https://doi.org/10.48550/arxiv.2103.13080 |
| ids.mag | 3138152811 |
| ids.openalex | https://openalex.org/W3138152811 |
| fwci | |
| type | preprint |
| title | Shift-and-Balance Attention |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| 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/T11307 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9984999895095825 |
| 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/T10812 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9961000084877014 |
| 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 | Human Pose and Action Recognition |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C168031717 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7262881994247437 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1530280 |
| concepts[0].display_name | Balance (ability) |
| concepts[1].id | https://openalex.org/C2776401178 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6180199980735779 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[1].display_name | Feature (linguistics) |
| concepts[2].id | https://openalex.org/C163258240 |
| concepts[2].level | 2 |
| concepts[2].score | 0.601238489151001 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q25342 |
| concepts[2].display_name | Power (physics) |
| concepts[3].id | https://openalex.org/C2781197403 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5610832571983337 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q193472 |
| concepts[3].display_name | Trunk |
| concepts[4].id | https://openalex.org/C41008148 |
| concepts[4].level | 0 |
| concepts[4].score | 0.5435438752174377 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[4].display_name | Computer science |
| concepts[5].id | https://openalex.org/C2775924081 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5083860754966736 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q55608371 |
| concepts[5].display_name | Control (management) |
| concepts[6].id | https://openalex.org/C2993807640 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4935048818588257 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q103709453 |
| concepts[6].display_name | Attention network |
| concepts[7].id | https://openalex.org/C81388566 |
| concepts[7].level | 3 |
| concepts[7].score | 0.4852294921875 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q526668 |
| concepts[7].display_name | Sigmoid function |
| concepts[8].id | https://openalex.org/C45347329 |
| concepts[8].level | 3 |
| concepts[8].score | 0.4610985517501831 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q5166604 |
| concepts[8].display_name | Convolution (computer science) |
| concepts[9].id | https://openalex.org/C166151169 |
| concepts[9].level | 2 |
| concepts[9].score | 0.41745609045028687 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q16946937 |
| concepts[9].display_name | Dynamic balance |
| concepts[10].id | https://openalex.org/C47446073 |
| concepts[10].level | 3 |
| concepts[10].score | 0.4063819944858551 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q5165890 |
| concepts[10].display_name | Control theory (sociology) |
| concepts[11].id | https://openalex.org/C154945302 |
| concepts[11].level | 1 |
| concepts[11].score | 0.38215699791908264 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[11].display_name | Artificial intelligence |
| concepts[12].id | https://openalex.org/C127413603 |
| concepts[12].level | 0 |
| concepts[12].score | 0.1698729693889618 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[12].display_name | Engineering |
| concepts[13].id | https://openalex.org/C50644808 |
| concepts[13].level | 2 |
| concepts[13].score | 0.15301671624183655 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[13].display_name | Artificial neural network |
| concepts[14].id | https://openalex.org/C15744967 |
| concepts[14].level | 0 |
| concepts[14].score | 0.15207195281982422 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[14].display_name | Psychology |
| concepts[15].id | https://openalex.org/C121332964 |
| concepts[15].level | 0 |
| concepts[15].score | 0.14863234758377075 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[15].display_name | Physics |
| concepts[16].id | https://openalex.org/C169760540 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q207011 |
| concepts[16].display_name | Neuroscience |
| concepts[17].id | https://openalex.org/C138885662 |
| concepts[17].level | 0 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[17].display_name | Philosophy |
| concepts[18].id | https://openalex.org/C62520636 |
| concepts[18].level | 1 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[18].display_name | Quantum mechanics |
| concepts[19].id | https://openalex.org/C18903297 |
| concepts[19].level | 1 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q7150 |
| concepts[19].display_name | Ecology |
| concepts[20].id | https://openalex.org/C78519656 |
| concepts[20].level | 1 |
| concepts[20].score | 0.0 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q101333 |
| concepts[20].display_name | Mechanical engineering |
| concepts[21].id | https://openalex.org/C86803240 |
| concepts[21].level | 0 |
| concepts[21].score | 0.0 |
| concepts[21].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[21].display_name | Biology |
| concepts[22].id | https://openalex.org/C41895202 |
| concepts[22].level | 1 |
| concepts[22].score | 0.0 |
| concepts[22].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[22].display_name | Linguistics |
| keywords[0].id | https://openalex.org/keywords/balance |
| keywords[0].score | 0.7262881994247437 |
| keywords[0].display_name | Balance (ability) |
| keywords[1].id | https://openalex.org/keywords/feature |
| keywords[1].score | 0.6180199980735779 |
| keywords[1].display_name | Feature (linguistics) |
| keywords[2].id | https://openalex.org/keywords/power |
| keywords[2].score | 0.601238489151001 |
| keywords[2].display_name | Power (physics) |
| keywords[3].id | https://openalex.org/keywords/trunk |
| keywords[3].score | 0.5610832571983337 |
| keywords[3].display_name | Trunk |
| keywords[4].id | https://openalex.org/keywords/computer-science |
| keywords[4].score | 0.5435438752174377 |
| keywords[4].display_name | Computer science |
| keywords[5].id | https://openalex.org/keywords/control |
| keywords[5].score | 0.5083860754966736 |
| keywords[5].display_name | Control (management) |
| keywords[6].id | https://openalex.org/keywords/attention-network |
| keywords[6].score | 0.4935048818588257 |
| keywords[6].display_name | Attention network |
| keywords[7].id | https://openalex.org/keywords/sigmoid-function |
| keywords[7].score | 0.4852294921875 |
| keywords[7].display_name | Sigmoid function |
| keywords[8].id | https://openalex.org/keywords/convolution |
| keywords[8].score | 0.4610985517501831 |
| keywords[8].display_name | Convolution (computer science) |
| keywords[9].id | https://openalex.org/keywords/dynamic-balance |
| keywords[9].score | 0.41745609045028687 |
| keywords[9].display_name | Dynamic balance |
| keywords[10].id | https://openalex.org/keywords/control-theory |
| keywords[10].score | 0.4063819944858551 |
| keywords[10].display_name | Control theory (sociology) |
| keywords[11].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[11].score | 0.38215699791908264 |
| keywords[11].display_name | Artificial intelligence |
| keywords[12].id | https://openalex.org/keywords/engineering |
| keywords[12].score | 0.1698729693889618 |
| keywords[12].display_name | Engineering |
| keywords[13].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[13].score | 0.15301671624183655 |
| keywords[13].display_name | Artificial neural network |
| keywords[14].id | https://openalex.org/keywords/psychology |
| keywords[14].score | 0.15207195281982422 |
| keywords[14].display_name | Psychology |
| keywords[15].id | https://openalex.org/keywords/physics |
| keywords[15].score | 0.14863234758377075 |
| keywords[15].display_name | Physics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2103.13080 |
| 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/2103.13080 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| 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/2103.13080 |
| locations[1].id | doi:10.48550/arxiv.2103.13080 |
| 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 | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| 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.2103.13080 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5033347503 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-6977-929X |
| authorships[0].author.display_name | Chunjie Luo |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Chunjie Luo |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5085963553 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-3728-6837 |
| authorships[1].author.display_name | Jianfeng Zhan |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Jianfeng Zhan |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5002465838 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-5540-8722 |
| authorships[2].author.display_name | Tianshu Hao |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Tianshu Hao |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100435995 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-7014-2149 |
| authorships[3].author.display_name | Lei Wang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Lei Wang |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5075110031 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-3911-9389 |
| authorships[4].author.display_name | Wanling Gao |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Wanling Gao |
| authorships[4].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/2103.13080 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Shift-and-Balance Attention |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| 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/W4385957115, https://openalex.org/W2061372042, https://openalex.org/W3047779762, https://openalex.org/W1520030019, https://openalex.org/W2071654592, https://openalex.org/W3104477175, https://openalex.org/W2088157920, https://openalex.org/W4283785902, https://openalex.org/W4392232922, https://openalex.org/W1468175696 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2021 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2103.13080 |
| 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/2103.13080 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| 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/2103.13080 |
| primary_location.id | pmh:oai:arXiv.org:2103.13080 |
| 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/2103.13080 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| 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/2103.13080 |
| publication_date | 2021-03-24 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W2905741102, https://openalex.org/W2095705004, https://openalex.org/W2963495494, https://openalex.org/W2194775991, https://openalex.org/W2895340641, https://openalex.org/W2963393494, https://openalex.org/W2963794428, https://openalex.org/W3109269658, https://openalex.org/W2962935523, https://openalex.org/W2117539524, https://openalex.org/W2963125010, https://openalex.org/W2183341477, https://openalex.org/W2962835968, https://openalex.org/W2963446712, https://openalex.org/W2597655663, https://openalex.org/W3012740297, https://openalex.org/W2963918968, https://openalex.org/W2982083293, https://openalex.org/W2612445135, https://openalex.org/W2964169985, https://openalex.org/W2970107519, https://openalex.org/W2955058313, https://openalex.org/W2890782586, https://openalex.org/W2962944050, https://openalex.org/W3118608800, https://openalex.org/W2414711238, https://openalex.org/W2922509574, https://openalex.org/W2950014519, https://openalex.org/W2752037867, https://openalex.org/W2963420686, https://openalex.org/W2963163009, https://openalex.org/W2626778328, https://openalex.org/W2778955544, https://openalex.org/W2962891704, https://openalex.org/W2963843116, https://openalex.org/W3016719260, https://openalex.org/W2279098554, https://openalex.org/W2964081807, https://openalex.org/W3034421924 |
| referenced_works_count | 39 |
| abstract_inverted_index.a | 14, 63, 118 |
| abstract_inverted_index.It | 41 |
| abstract_inverted_index.To | 55 |
| abstract_inverted_index.an | 2 |
| abstract_inverted_index.by | 35, 78 |
| abstract_inverted_index.in | 109 |
| abstract_inverted_index.is | 1, 27, 42, 76 |
| abstract_inverted_index.of | 117 |
| abstract_inverted_index.or | 125 |
| abstract_inverted_index.to | 5, 18, 45, 83, 105, 129 |
| abstract_inverted_index.we | 61 |
| abstract_inverted_index.The | 24 |
| abstract_inverted_index.and | 33, 47, 51, 115 |
| abstract_inverted_index.new | 64 |
| abstract_inverted_index.the | 7, 20, 30, 36, 49, 57, 73, 79, 85, 90, 102, 130 |
| abstract_inverted_index.too | 43 |
| abstract_inverted_index.(SE) | 12 |
| abstract_inverted_index.deep | 8 |
| abstract_inverted_index.from | 71 |
| abstract_inverted_index.into | 89 |
| abstract_inverted_index.more | 110, 113 |
| abstract_inverted_index.show | 96 |
| abstract_inverted_index.size | 114 |
| abstract_inverted_index.that | 97 |
| abstract_inverted_index.then | 87 |
| abstract_inverted_index.when | 107 |
| abstract_inverted_index.(SB). | 69 |
| abstract_inverted_index.added | 88 |
| abstract_inverted_index.close | 126 |
| abstract_inverted_index.gated | 28 |
| abstract_inverted_index.map's | 38, 92 |
| abstract_inverted_index.model | 9 |
| abstract_inverted_index.trunk | 39, 50, 93 |
| abstract_inverted_index.using | 29 |
| abstract_inverted_index.better | 124 |
| abstract_inverted_index.branch | 17, 26, 75 |
| abstract_inverted_index.called | 67 |
| abstract_inverted_index.factor | 82 |
| abstract_inverted_index.power. | 23 |
| abstract_inverted_index.Dynamic | 132 |
| abstract_inverted_index.Sigmoid | 31 |
| abstract_inverted_index.applied | 108 |
| abstract_inverted_index.balance | 48 |
| abstract_inverted_index.branch. | 40, 94 |
| abstract_inverted_index.control | 56, 81, 84 |
| abstract_inverted_index.enhance | 19 |
| abstract_inverted_index.feature | 37, 91 |
| abstract_inverted_index.improve | 6 |
| abstract_inverted_index.layers, | 111 |
| abstract_inverted_index.learned | 80 |
| abstract_inverted_index.method, | 66 |
| abstract_inverted_index.propose | 62 |
| abstract_inverted_index.accuracy | 103, 127 |
| abstract_inverted_index.achieves | 123 |
| abstract_inverted_index.balance, | 86 |
| abstract_inverted_index.branch's | 59 |
| abstract_inverted_index.capacity | 116 |
| abstract_inverted_index.compared | 104, 128 |
| abstract_inverted_index.function | 32 |
| abstract_inverted_index.improves | 101 |
| abstract_inverted_index.network. | 119 |
| abstract_inverted_index.Attention | 0 |
| abstract_inverted_index.Different | 70 |
| abstract_inverted_index.Moreover, | 120 |
| abstract_inverted_index.attention | 16, 25, 52, 58, 65, 74, 99, 122 |
| abstract_inverted_index.branches' | 53 |
| abstract_inverted_index.effective | 3 |
| abstract_inverted_index.mechanism | 4 |
| abstract_inverted_index.network's | 21 |
| abstract_inverted_index.regulated | 77 |
| abstract_inverted_index.sensitive | 44 |
| abstract_inverted_index.coordinate | 46 |
| abstract_inverted_index.increasing | 112 |
| abstract_inverted_index.influence, | 60 |
| abstract_inverted_index.introduces | 13 |
| abstract_inverted_index.multiplied | 34 |
| abstract_inverted_index.Experiments | 95 |
| abstract_inverted_index.capability. | 10 |
| abstract_inverted_index.Convolution. | 133 |
| abstract_inverted_index.light-weight | 15 |
| abstract_inverted_index.state-of-art | 131 |
| abstract_inverted_index.significantly | 100 |
| abstract_inverted_index.contributions. | 54 |
| abstract_inverted_index.representational | 22 |
| abstract_inverted_index.Shift-and-Balance | 68, 98, 121 |
| abstract_inverted_index.Squeeze-and-Excite | 11, 106 |
| abstract_inverted_index.Squeeze-and-Excite, | 72 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile |