Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration Article Swipe
Harry H. Cheng
,
Yangyang Guo
,
Liqiang Nie
,
Zhiyong Cheng
,
Mohan Kankanhalli
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2307.14866
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2307.14866
Training an effective video action recognition model poses significant computational challenges, particularly under limited resource budgets. Current methods primarily aim to either reduce model size or utilize pre-trained models, limiting their adaptability to various backbone architectures. This paper investigates the issue of over-sampled frames, a prevalent problem in many approaches yet it has received relatively little attention. Despite the use of fewer frames being a potential solution, this approach often results in a substantial decline in performance. To address this issue, we propose a novel method to restore the intermediate features for two sparsely sampled and adjacent video frames. This feature restoration technique brings a negligible increase in computational requirements compared to resource-intensive image encoders, such as ViT. To evaluate the effectiveness of our method, we conduct extensive experiments on four public datasets, including Kinetics-400, ActivityNet, UCF-101, and HMDB-51. With the integration of our method, the efficiency of three commonly used baselines has been improved by over 50%, with a mere 0.5% reduction in recognition accuracy. In addition, our method also surprisingly helps improve the generalization ability of the models under zero-shot settings.
Related Topics
Concepts
Computer science
Adaptability
Generalization
Feature (linguistics)
Artificial intelligence
Sample (material)
Resource (disambiguation)
Frame (networking)
Encoder
Limiting
Machine learning
Pattern recognition (psychology)
Action (physics)
Mathematics
Engineering
Philosophy
Biology
Operating system
Chemistry
Ecology
Mathematical analysis
Quantum mechanics
Physics
Telecommunications
Computer network
Mechanical engineering
Linguistics
Chromatography
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2307.14866
- https://arxiv.org/pdf/2307.14866
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4385372881
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4385372881Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2307.14866Digital Object Identifier
- Title
-
Sample Less, Learn More: Efficient Action Recognition via Frame Feature RestorationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-07-27Full publication date if available
- Authors
-
Harry H. Cheng, Yangyang Guo, Liqiang Nie, Zhiyong Cheng, Mohan KankanhalliList of authors in order
- Landing page
-
https://arxiv.org/abs/2307.14866Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2307.14866Direct 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/2307.14866Direct OA link when available
- Concepts
-
Computer science, Adaptability, Generalization, Feature (linguistics), Artificial intelligence, Sample (material), Resource (disambiguation), Frame (networking), Encoder, Limiting, Machine learning, Pattern recognition (psychology), Action (physics), Mathematics, Engineering, Philosophy, Biology, Operating system, Chemistry, Ecology, Mathematical analysis, Quantum mechanics, Physics, Telecommunications, Computer network, Mechanical engineering, Linguistics, ChromatographyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4385372881 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2307.14866 |
| ids.doi | https://doi.org/10.48550/arxiv.2307.14866 |
| ids.openalex | https://openalex.org/W4385372881 |
| fwci | |
| type | preprint |
| title | Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10812 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9991000294685364 |
| 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 | Human Pose and Action Recognition |
| topics[1].id | https://openalex.org/T11512 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9635999798774719 |
| 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 | Anomaly Detection Techniques and Applications |
| topics[2].id | https://openalex.org/T10036 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9447000026702881 |
| 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 | Advanced Neural Network Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7156105041503906 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C177606310 |
| concepts[1].level | 2 |
| concepts[1].score | 0.698783278465271 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q5674297 |
| concepts[1].display_name | Adaptability |
| concepts[2].id | https://openalex.org/C177148314 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6280396580696106 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q170084 |
| concepts[2].display_name | Generalization |
| concepts[3].id | https://openalex.org/C2776401178 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6082146167755127 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[3].display_name | Feature (linguistics) |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.5756592750549316 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C198531522 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5220691561698914 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q485146 |
| concepts[5].display_name | Sample (material) |
| concepts[6].id | https://openalex.org/C206345919 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5068653225898743 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q20380951 |
| concepts[6].display_name | Resource (disambiguation) |
| concepts[7].id | https://openalex.org/C126042441 |
| concepts[7].level | 2 |
| concepts[7].score | 0.5066490769386292 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1324888 |
| concepts[7].display_name | Frame (networking) |
| concepts[8].id | https://openalex.org/C118505674 |
| concepts[8].level | 2 |
| concepts[8].score | 0.5002391338348389 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q42586063 |
| concepts[8].display_name | Encoder |
| concepts[9].id | https://openalex.org/C188198153 |
| concepts[9].level | 2 |
| concepts[9].score | 0.48170024156570435 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q1613840 |
| concepts[9].display_name | Limiting |
| concepts[10].id | https://openalex.org/C119857082 |
| concepts[10].level | 1 |
| concepts[10].score | 0.45787686109542847 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[10].display_name | Machine learning |
| concepts[11].id | https://openalex.org/C153180895 |
| concepts[11].level | 2 |
| concepts[11].score | 0.4369054436683655 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[11].display_name | Pattern recognition (psychology) |
| concepts[12].id | https://openalex.org/C2780791683 |
| concepts[12].level | 2 |
| concepts[12].score | 0.4116674065589905 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q846785 |
| concepts[12].display_name | Action (physics) |
| concepts[13].id | https://openalex.org/C33923547 |
| concepts[13].level | 0 |
| concepts[13].score | 0.15167123079299927 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[13].display_name | Mathematics |
| concepts[14].id | https://openalex.org/C127413603 |
| concepts[14].level | 0 |
| concepts[14].score | 0.10446494817733765 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[14].display_name | Engineering |
| concepts[15].id | https://openalex.org/C138885662 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[15].display_name | Philosophy |
| concepts[16].id | https://openalex.org/C86803240 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[16].display_name | Biology |
| concepts[17].id | https://openalex.org/C111919701 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[17].display_name | Operating system |
| concepts[18].id | https://openalex.org/C185592680 |
| concepts[18].level | 0 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[18].display_name | Chemistry |
| 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/C134306372 |
| concepts[20].level | 1 |
| concepts[20].score | 0.0 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[20].display_name | Mathematical analysis |
| concepts[21].id | https://openalex.org/C62520636 |
| concepts[21].level | 1 |
| concepts[21].score | 0.0 |
| concepts[21].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[21].display_name | Quantum mechanics |
| concepts[22].id | https://openalex.org/C121332964 |
| concepts[22].level | 0 |
| concepts[22].score | 0.0 |
| concepts[22].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[22].display_name | Physics |
| concepts[23].id | https://openalex.org/C76155785 |
| concepts[23].level | 1 |
| concepts[23].score | 0.0 |
| concepts[23].wikidata | https://www.wikidata.org/wiki/Q418 |
| concepts[23].display_name | Telecommunications |
| concepts[24].id | https://openalex.org/C31258907 |
| concepts[24].level | 1 |
| concepts[24].score | 0.0 |
| concepts[24].wikidata | https://www.wikidata.org/wiki/Q1301371 |
| concepts[24].display_name | Computer network |
| concepts[25].id | https://openalex.org/C78519656 |
| concepts[25].level | 1 |
| concepts[25].score | 0.0 |
| concepts[25].wikidata | https://www.wikidata.org/wiki/Q101333 |
| concepts[25].display_name | Mechanical engineering |
| concepts[26].id | https://openalex.org/C41895202 |
| concepts[26].level | 1 |
| concepts[26].score | 0.0 |
| concepts[26].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[26].display_name | Linguistics |
| concepts[27].id | https://openalex.org/C43617362 |
| concepts[27].level | 1 |
| concepts[27].score | 0.0 |
| concepts[27].wikidata | https://www.wikidata.org/wiki/Q170050 |
| concepts[27].display_name | Chromatography |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7156105041503906 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/adaptability |
| keywords[1].score | 0.698783278465271 |
| keywords[1].display_name | Adaptability |
| keywords[2].id | https://openalex.org/keywords/generalization |
| keywords[2].score | 0.6280396580696106 |
| keywords[2].display_name | Generalization |
| keywords[3].id | https://openalex.org/keywords/feature |
| keywords[3].score | 0.6082146167755127 |
| keywords[3].display_name | Feature (linguistics) |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.5756592750549316 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/sample |
| keywords[5].score | 0.5220691561698914 |
| keywords[5].display_name | Sample (material) |
| keywords[6].id | https://openalex.org/keywords/resource |
| keywords[6].score | 0.5068653225898743 |
| keywords[6].display_name | Resource (disambiguation) |
| keywords[7].id | https://openalex.org/keywords/frame |
| keywords[7].score | 0.5066490769386292 |
| keywords[7].display_name | Frame (networking) |
| keywords[8].id | https://openalex.org/keywords/encoder |
| keywords[8].score | 0.5002391338348389 |
| keywords[8].display_name | Encoder |
| keywords[9].id | https://openalex.org/keywords/limiting |
| keywords[9].score | 0.48170024156570435 |
| keywords[9].display_name | Limiting |
| keywords[10].id | https://openalex.org/keywords/machine-learning |
| keywords[10].score | 0.45787686109542847 |
| keywords[10].display_name | Machine learning |
| keywords[11].id | https://openalex.org/keywords/pattern-recognition |
| keywords[11].score | 0.4369054436683655 |
| keywords[11].display_name | Pattern recognition (psychology) |
| keywords[12].id | https://openalex.org/keywords/action |
| keywords[12].score | 0.4116674065589905 |
| keywords[12].display_name | Action (physics) |
| keywords[13].id | https://openalex.org/keywords/mathematics |
| keywords[13].score | 0.15167123079299927 |
| keywords[13].display_name | Mathematics |
| keywords[14].id | https://openalex.org/keywords/engineering |
| keywords[14].score | 0.10446494817733765 |
| keywords[14].display_name | Engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2307.14866 |
| 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 | cc-by-sa |
| locations[0].pdf_url | https://arxiv.org/pdf/2307.14866 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| locations[0].license_id | https://openalex.org/licenses/cc-by-sa |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2307.14866 |
| locations[1].id | doi:10.48550/arxiv.2307.14866 |
| 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.2307.14866 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5059602960 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-7436-0162 |
| authorships[0].author.display_name | Harry H. Cheng |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Cheng, Harry |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5054313646 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-8691-5372 |
| authorships[1].author.display_name | Yangyang Guo |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Guo, Yangyang |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5038612499 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-1476-0273 |
| authorships[2].author.display_name | Liqiang Nie |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Nie, Liqiang |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5068843001 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-1109-5028 |
| authorships[3].author.display_name | Zhiyong Cheng |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Cheng, Zhiyong |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5016415049 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-4846-2015 |
| authorships[4].author.display_name | Mohan Kankanhalli |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Kankanhalli, Mohan |
| authorships[4].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2307.14866 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2023-07-29T00:00:00 |
| display_name | Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10812 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9991000294685364 |
| 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 | Human Pose and Action Recognition |
| related_works | https://openalex.org/W2357124094, https://openalex.org/W2387399993, https://openalex.org/W2389739210, https://openalex.org/W2348924972, https://openalex.org/W2365736347, https://openalex.org/W2047454415, https://openalex.org/W2070040999, https://openalex.org/W2387293848, https://openalex.org/W2250140200, https://openalex.org/W3121791438 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2307.14866 |
| 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 | cc-by-sa |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2307.14866 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by-sa |
| 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/2307.14866 |
| primary_location.id | pmh:oai:arXiv.org:2307.14866 |
| 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 | cc-by-sa |
| primary_location.pdf_url | https://arxiv.org/pdf/2307.14866 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| primary_location.license_id | https://openalex.org/licenses/cc-by-sa |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2307.14866 |
| publication_date | 2023-07-27 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 44, 64, 72, 83, 104, 159 |
| abstract_inverted_index.In | 166 |
| abstract_inverted_index.To | 77, 118 |
| abstract_inverted_index.an | 1 |
| abstract_inverted_index.as | 116 |
| abstract_inverted_index.by | 155 |
| abstract_inverted_index.in | 47, 71, 75, 107, 163 |
| abstract_inverted_index.it | 51 |
| abstract_inverted_index.of | 41, 60, 122, 142, 147, 177 |
| abstract_inverted_index.on | 129 |
| abstract_inverted_index.or | 25 |
| abstract_inverted_index.to | 20, 32, 86, 111 |
| abstract_inverted_index.we | 81, 125 |
| abstract_inverted_index.aim | 19 |
| abstract_inverted_index.and | 95, 137 |
| abstract_inverted_index.for | 91 |
| abstract_inverted_index.has | 52, 152 |
| abstract_inverted_index.our | 123, 143, 168 |
| abstract_inverted_index.the | 39, 58, 88, 120, 140, 145, 174, 178 |
| abstract_inverted_index.two | 92 |
| abstract_inverted_index.use | 59 |
| abstract_inverted_index.yet | 50 |
| abstract_inverted_index.0.5% | 161 |
| abstract_inverted_index.50%, | 157 |
| abstract_inverted_index.This | 36, 99 |
| abstract_inverted_index.ViT. | 117 |
| abstract_inverted_index.With | 139 |
| abstract_inverted_index.also | 170 |
| abstract_inverted_index.been | 153 |
| abstract_inverted_index.four | 130 |
| abstract_inverted_index.many | 48 |
| abstract_inverted_index.mere | 160 |
| abstract_inverted_index.over | 156 |
| abstract_inverted_index.size | 24 |
| abstract_inverted_index.such | 115 |
| abstract_inverted_index.this | 67, 79 |
| abstract_inverted_index.used | 150 |
| abstract_inverted_index.with | 158 |
| abstract_inverted_index.being | 63 |
| abstract_inverted_index.fewer | 61 |
| abstract_inverted_index.helps | 172 |
| abstract_inverted_index.image | 113 |
| abstract_inverted_index.issue | 40 |
| abstract_inverted_index.model | 6, 23 |
| abstract_inverted_index.novel | 84 |
| abstract_inverted_index.often | 69 |
| abstract_inverted_index.paper | 37 |
| abstract_inverted_index.poses | 7 |
| abstract_inverted_index.their | 30 |
| abstract_inverted_index.three | 148 |
| abstract_inverted_index.under | 12, 180 |
| abstract_inverted_index.video | 3, 97 |
| abstract_inverted_index.action | 4 |
| abstract_inverted_index.brings | 103 |
| abstract_inverted_index.either | 21 |
| abstract_inverted_index.frames | 62 |
| abstract_inverted_index.issue, | 80 |
| abstract_inverted_index.little | 55 |
| abstract_inverted_index.method | 85, 169 |
| abstract_inverted_index.models | 179 |
| abstract_inverted_index.public | 131 |
| abstract_inverted_index.reduce | 22 |
| abstract_inverted_index.Current | 16 |
| abstract_inverted_index.Despite | 57 |
| abstract_inverted_index.ability | 176 |
| abstract_inverted_index.address | 78 |
| abstract_inverted_index.conduct | 126 |
| abstract_inverted_index.decline | 74 |
| abstract_inverted_index.feature | 100 |
| abstract_inverted_index.frames, | 43 |
| abstract_inverted_index.frames. | 98 |
| abstract_inverted_index.improve | 173 |
| abstract_inverted_index.limited | 13 |
| abstract_inverted_index.method, | 124, 144 |
| abstract_inverted_index.methods | 17 |
| abstract_inverted_index.models, | 28 |
| abstract_inverted_index.problem | 46 |
| abstract_inverted_index.propose | 82 |
| abstract_inverted_index.restore | 87 |
| abstract_inverted_index.results | 70 |
| abstract_inverted_index.sampled | 94 |
| abstract_inverted_index.utilize | 26 |
| abstract_inverted_index.various | 33 |
| abstract_inverted_index.HMDB-51. | 138 |
| abstract_inverted_index.Training | 0 |
| abstract_inverted_index.UCF-101, | 136 |
| abstract_inverted_index.adjacent | 96 |
| abstract_inverted_index.approach | 68 |
| abstract_inverted_index.backbone | 34 |
| abstract_inverted_index.budgets. | 15 |
| abstract_inverted_index.commonly | 149 |
| abstract_inverted_index.compared | 110 |
| abstract_inverted_index.evaluate | 119 |
| abstract_inverted_index.features | 90 |
| abstract_inverted_index.improved | 154 |
| abstract_inverted_index.increase | 106 |
| abstract_inverted_index.limiting | 29 |
| abstract_inverted_index.received | 53 |
| abstract_inverted_index.resource | 14 |
| abstract_inverted_index.sparsely | 93 |
| abstract_inverted_index.accuracy. | 165 |
| abstract_inverted_index.addition, | 167 |
| abstract_inverted_index.baselines | 151 |
| abstract_inverted_index.datasets, | 132 |
| abstract_inverted_index.effective | 2 |
| abstract_inverted_index.encoders, | 114 |
| abstract_inverted_index.extensive | 127 |
| abstract_inverted_index.including | 133 |
| abstract_inverted_index.potential | 65 |
| abstract_inverted_index.prevalent | 45 |
| abstract_inverted_index.primarily | 18 |
| abstract_inverted_index.reduction | 162 |
| abstract_inverted_index.settings. | 182 |
| abstract_inverted_index.solution, | 66 |
| abstract_inverted_index.technique | 102 |
| abstract_inverted_index.zero-shot | 181 |
| abstract_inverted_index.approaches | 49 |
| abstract_inverted_index.attention. | 56 |
| abstract_inverted_index.efficiency | 146 |
| abstract_inverted_index.negligible | 105 |
| abstract_inverted_index.relatively | 54 |
| abstract_inverted_index.challenges, | 10 |
| abstract_inverted_index.experiments | 128 |
| abstract_inverted_index.integration | 141 |
| abstract_inverted_index.pre-trained | 27 |
| abstract_inverted_index.recognition | 5, 164 |
| abstract_inverted_index.restoration | 101 |
| abstract_inverted_index.significant | 8 |
| abstract_inverted_index.substantial | 73 |
| abstract_inverted_index.ActivityNet, | 135 |
| abstract_inverted_index.adaptability | 31 |
| abstract_inverted_index.intermediate | 89 |
| abstract_inverted_index.investigates | 38 |
| abstract_inverted_index.over-sampled | 42 |
| abstract_inverted_index.particularly | 11 |
| abstract_inverted_index.performance. | 76 |
| abstract_inverted_index.requirements | 109 |
| abstract_inverted_index.surprisingly | 171 |
| abstract_inverted_index.Kinetics-400, | 134 |
| abstract_inverted_index.computational | 9, 108 |
| abstract_inverted_index.effectiveness | 121 |
| abstract_inverted_index.architectures. | 35 |
| abstract_inverted_index.generalization | 175 |
| abstract_inverted_index.resource-intensive | 112 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile |