Classification Matters: Improving Video Action Detection with Class-Specific Attention Article Swipe
Jinsung Lee
,
Taeoh Kim
,
Inwoong Lee
,
Minho Shim
,
Dongyoon Wee
,
Minsu Cho
,
Suha Kwak
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2407.19698
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2407.19698
Video action detection (VAD) aims to detect actors and classify their actions in a video. We figure that VAD suffers more from classification rather than localization of actors. Hence, we analyze how prevailing methods form features for classification and find that they prioritize actor regions, yet often overlooking the essential contextual information necessary for accurate classification. Accordingly, we propose to reduce the bias toward actor and encourage paying attention to the context that is relevant to each action class. By assigning a class-dedicated query to each action class, our model can dynamically determine where to focus for effective classification. The proposed model demonstrates superior performance on three challenging benchmarks with significantly fewer parameters and less computation.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2407.19698
- https://arxiv.org/pdf/2407.19698
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4401201961
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4401201961Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2407.19698Digital Object Identifier
- Title
-
Classification Matters: Improving Video Action Detection with Class-Specific AttentionWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-07-29Full publication date if available
- Authors
-
Jinsung Lee, Taeoh Kim, Inwoong Lee, Minho Shim, Dongyoon Wee, Minsu Cho, Suha KwakList of authors in order
- Landing page
-
https://arxiv.org/abs/2407.19698Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2407.19698Direct 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/2407.19698Direct OA link when available
- Concepts
-
Class action, Class (philosophy), Action (physics), Computer science, Artificial intelligence, Psychology, Cognitive psychology, Algorithm, State (computer science), Quantum mechanics, PhysicsTop 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/W4401201961 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2407.19698 |
| ids.doi | https://doi.org/10.48550/arxiv.2407.19698 |
| ids.openalex | https://openalex.org/W4401201961 |
| fwci | |
| type | preprint |
| title | Classification Matters: Improving Video Action Detection with Class-Specific Attention |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11512 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.989300012588501 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Anomaly Detection Techniques and Applications |
| topics[1].id | https://openalex.org/T10812 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9693999886512756 |
| 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 | Human Pose and Action Recognition |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2776687834 |
| concepts[0].level | 3 |
| concepts[0].score | 0.6809743642807007 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q2783852 |
| concepts[0].display_name | Class action |
| concepts[1].id | https://openalex.org/C2777212361 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6463156938552856 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q5127848 |
| concepts[1].display_name | Class (philosophy) |
| concepts[2].id | https://openalex.org/C2780791683 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5976964235305786 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q846785 |
| concepts[2].display_name | Action (physics) |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.5265277624130249 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.3499005436897278 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C15744967 |
| concepts[5].level | 0 |
| concepts[5].score | 0.3384428024291992 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[5].display_name | Psychology |
| concepts[6].id | https://openalex.org/C180747234 |
| concepts[6].level | 1 |
| concepts[6].score | 0.33311688899993896 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q23373 |
| concepts[6].display_name | Cognitive psychology |
| concepts[7].id | https://openalex.org/C11413529 |
| concepts[7].level | 1 |
| concepts[7].score | 0.049520522356033325 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[7].display_name | Algorithm |
| concepts[8].id | https://openalex.org/C48103436 |
| concepts[8].level | 2 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q599031 |
| concepts[8].display_name | State (computer science) |
| concepts[9].id | https://openalex.org/C62520636 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[9].display_name | Quantum mechanics |
| concepts[10].id | https://openalex.org/C121332964 |
| concepts[10].level | 0 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[10].display_name | Physics |
| keywords[0].id | https://openalex.org/keywords/class-action |
| keywords[0].score | 0.6809743642807007 |
| keywords[0].display_name | Class action |
| keywords[1].id | https://openalex.org/keywords/class |
| keywords[1].score | 0.6463156938552856 |
| keywords[1].display_name | Class (philosophy) |
| keywords[2].id | https://openalex.org/keywords/action |
| keywords[2].score | 0.5976964235305786 |
| keywords[2].display_name | Action (physics) |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.5265277624130249 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.3499005436897278 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/psychology |
| keywords[5].score | 0.3384428024291992 |
| keywords[5].display_name | Psychology |
| keywords[6].id | https://openalex.org/keywords/cognitive-psychology |
| keywords[6].score | 0.33311688899993896 |
| keywords[6].display_name | Cognitive psychology |
| keywords[7].id | https://openalex.org/keywords/algorithm |
| keywords[7].score | 0.049520522356033325 |
| keywords[7].display_name | Algorithm |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2407.19698 |
| 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/2407.19698 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2407.19698 |
| locations[1].id | doi:10.48550/arxiv.2407.19698 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2407.19698 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5032201384 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-9192-6623 |
| authorships[0].author.display_name | Jinsung Lee |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Lee, Jinsung |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5028212198 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-7252-5525 |
| authorships[1].author.display_name | Taeoh Kim |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Kim, Taeoh |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100349171 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-4356-7616 |
| authorships[2].author.display_name | Inwoong Lee |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Lee, Inwoong |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5071547535 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-9637-4909 |
| authorships[3].author.display_name | Minho Shim |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Shim, Minho |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5028451951 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-0359-146X |
| authorships[4].author.display_name | Dongyoon Wee |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Wee, Dongyoon |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5101998656 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-2498-1109 |
| authorships[5].author.display_name | Minsu Cho |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Cho, Minsu |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5060343759 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-4567-9091 |
| authorships[6].author.display_name | Suha Kwak |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Kwak, Suha |
| authorships[6].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/2407.19698 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-08-01T00:00:00 |
| display_name | Classification Matters: Improving Video Action Detection with Class-Specific Attention |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11512 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.989300012588501 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Anomaly Detection Techniques and Applications |
| related_works | https://openalex.org/W1494523486, https://openalex.org/W136506674, https://openalex.org/W2294250053, https://openalex.org/W2253550681, https://openalex.org/W39317772, https://openalex.org/W3122185720, https://openalex.org/W970202989, https://openalex.org/W2008243700, https://openalex.org/W2103249825, https://openalex.org/W197489520 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2407.19698 |
| 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/2407.19698 |
| 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/2407.19698 |
| primary_location.id | pmh:oai:arXiv.org:2407.19698 |
| 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/2407.19698 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2407.19698 |
| publication_date | 2024-07-29 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 13, 81 |
| abstract_inverted_index.By | 79 |
| abstract_inverted_index.We | 15 |
| abstract_inverted_index.in | 12 |
| abstract_inverted_index.is | 73 |
| abstract_inverted_index.of | 26 |
| abstract_inverted_index.on | 105 |
| abstract_inverted_index.to | 5, 59, 69, 75, 84, 94 |
| abstract_inverted_index.we | 29, 57 |
| abstract_inverted_index.The | 99 |
| abstract_inverted_index.VAD | 18 |
| abstract_inverted_index.and | 8, 38, 65, 113 |
| abstract_inverted_index.can | 90 |
| abstract_inverted_index.for | 36, 53, 96 |
| abstract_inverted_index.how | 31 |
| abstract_inverted_index.our | 88 |
| abstract_inverted_index.the | 48, 61, 70 |
| abstract_inverted_index.yet | 45 |
| abstract_inverted_index.aims | 4 |
| abstract_inverted_index.bias | 62 |
| abstract_inverted_index.each | 76, 85 |
| abstract_inverted_index.find | 39 |
| abstract_inverted_index.form | 34 |
| abstract_inverted_index.from | 21 |
| abstract_inverted_index.less | 114 |
| abstract_inverted_index.more | 20 |
| abstract_inverted_index.than | 24 |
| abstract_inverted_index.that | 17, 40, 72 |
| abstract_inverted_index.they | 41 |
| abstract_inverted_index.with | 109 |
| abstract_inverted_index.(VAD) | 3 |
| abstract_inverted_index.Video | 0 |
| abstract_inverted_index.actor | 43, 64 |
| abstract_inverted_index.fewer | 111 |
| abstract_inverted_index.focus | 95 |
| abstract_inverted_index.model | 89, 101 |
| abstract_inverted_index.often | 46 |
| abstract_inverted_index.query | 83 |
| abstract_inverted_index.their | 10 |
| abstract_inverted_index.three | 106 |
| abstract_inverted_index.where | 93 |
| abstract_inverted_index.Hence, | 28 |
| abstract_inverted_index.action | 1, 77, 86 |
| abstract_inverted_index.actors | 7 |
| abstract_inverted_index.class, | 87 |
| abstract_inverted_index.class. | 78 |
| abstract_inverted_index.detect | 6 |
| abstract_inverted_index.figure | 16 |
| abstract_inverted_index.paying | 67 |
| abstract_inverted_index.rather | 23 |
| abstract_inverted_index.reduce | 60 |
| abstract_inverted_index.toward | 63 |
| abstract_inverted_index.video. | 14 |
| abstract_inverted_index.actions | 11 |
| abstract_inverted_index.actors. | 27 |
| abstract_inverted_index.analyze | 30 |
| abstract_inverted_index.context | 71 |
| abstract_inverted_index.methods | 33 |
| abstract_inverted_index.propose | 58 |
| abstract_inverted_index.suffers | 19 |
| abstract_inverted_index.accurate | 54 |
| abstract_inverted_index.classify | 9 |
| abstract_inverted_index.features | 35 |
| abstract_inverted_index.proposed | 100 |
| abstract_inverted_index.regions, | 44 |
| abstract_inverted_index.relevant | 74 |
| abstract_inverted_index.superior | 103 |
| abstract_inverted_index.assigning | 80 |
| abstract_inverted_index.attention | 68 |
| abstract_inverted_index.detection | 2 |
| abstract_inverted_index.determine | 92 |
| abstract_inverted_index.effective | 97 |
| abstract_inverted_index.encourage | 66 |
| abstract_inverted_index.essential | 49 |
| abstract_inverted_index.necessary | 52 |
| abstract_inverted_index.benchmarks | 108 |
| abstract_inverted_index.contextual | 50 |
| abstract_inverted_index.parameters | 112 |
| abstract_inverted_index.prevailing | 32 |
| abstract_inverted_index.prioritize | 42 |
| abstract_inverted_index.challenging | 107 |
| abstract_inverted_index.dynamically | 91 |
| abstract_inverted_index.information | 51 |
| abstract_inverted_index.overlooking | 47 |
| abstract_inverted_index.performance | 104 |
| abstract_inverted_index.Accordingly, | 56 |
| abstract_inverted_index.computation. | 115 |
| abstract_inverted_index.demonstrates | 102 |
| abstract_inverted_index.localization | 25 |
| abstract_inverted_index.significantly | 110 |
| abstract_inverted_index.classification | 22, 37 |
| abstract_inverted_index.class-dedicated | 82 |
| abstract_inverted_index.classification. | 55, 98 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile |