Graph transformer network with temporal kernel attention for skeleton-based action recognition Article Swipe
Yanan Liu
,
Hao Zhang
,
Dan Xu
,
Kangjian He
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1016/j.knosys.2022.108146
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1016/j.knosys.2022.108146
Skeleton-based human action recognition has caused wide concern, as skeleton data can robustly adapt to dynamic circumstances such as camera view changes and background interference thus allowing recognition methods to focus on robust features. In recent studies, the human body is modeled as a topological graph, and the graph convolution network (GCN) is used to extract features of actions. Although GCN has a strong ability to learn spatial modes, it ignores the varying degrees of higher-order dependencies that are captured by message passing. Moreover, the joints represented by vertices are interdependent, and hence incorporating an attention mechanism to weigh dependencies is beneficial. In this work, we propose a kernel attention adaptive graph transformer network (KA-AGTN), which models the higher-order spatial dependencies between joints by the graph transformer operator based on multihead self-attention. In addition, the Temporal Kernel Attention (TKA) block in KA-AGTN generates a channel-level attention score using temporal features, which can enhance temporal motion correlation. After combining the two-stream framework and adaptive graph strategy, KA-AGTN outperforms the baseline 2s-AGCN by 1.9% and by 1% under X-Sub and X-View on the NTU-RGBD 60 dataset, by 3.2% and 3.1% under X-Sub and X-Set on the NTU-RGBD 120 dataset, and by 2% and 2.3% under Top-1 and Top-5 and achieves the state-of-the-art performance on the Kinetics-Skeleton 400 dataset.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1016/j.knosys.2022.108146
- OA Status
- hybrid
- Cited By
- 134
- References
- 84
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4205947138
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4205947138Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1016/j.knosys.2022.108146Digital Object Identifier
- Title
-
Graph transformer network with temporal kernel attention for skeleton-based action recognitionWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-01-10Full publication date if available
- Authors
-
Yanan Liu, Hao Zhang, Dan Xu, Kangjian HeList of authors in order
- Landing page
-
https://doi.org/10.1016/j.knosys.2022.108146Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
hybridOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.1016/j.knosys.2022.108146Direct OA link when available
- Concepts
-
Computer science, Pattern recognition (psychology), Action recognition, Graph, Artificial intelligence, Attention network, Transformer, Theoretical computer science, Algorithm, Voltage, Class (philosophy), Physics, Quantum mechanicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
134Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 34, 2024: 44, 2023: 42, 2022: 14Per-year citation counts (last 5 years)
- References (count)
-
84Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4205947138 |
|---|---|
| doi | https://doi.org/10.1016/j.knosys.2022.108146 |
| ids.doi | https://doi.org/10.1016/j.knosys.2022.108146 |
| ids.openalex | https://openalex.org/W4205947138 |
| fwci | 16.58810135 |
| type | article |
| title | Graph transformer network with temporal kernel attention for skeleton-based action recognition |
| biblio.issue | |
| biblio.volume | 240 |
| biblio.last_page | 108146 |
| biblio.first_page | 108146 |
| 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 | 1.0 |
| 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/T11398 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9947999715805054 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1709 |
| topics[1].subfield.display_name | Human-Computer Interaction |
| topics[1].display_name | Hand Gesture Recognition Systems |
| topics[2].id | https://openalex.org/T11512 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9866999983787537 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Anomaly Detection Techniques and Applications |
| is_xpac | False |
| apc_list.value | 3130 |
| apc_list.currency | USD |
| apc_list.value_usd | 3130 |
| apc_paid.value | 3130 |
| apc_paid.currency | USD |
| apc_paid.value_usd | 3130 |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.6428952217102051 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C153180895 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5663106441497803 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[1].display_name | Pattern recognition (psychology) |
| concepts[2].id | https://openalex.org/C2987834672 |
| concepts[2].level | 3 |
| concepts[2].score | 0.5460843443870544 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q4677630 |
| concepts[2].display_name | Action recognition |
| concepts[3].id | https://openalex.org/C132525143 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5056476593017578 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q141488 |
| concepts[3].display_name | Graph |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.4971828758716583 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C2993807640 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4622063636779785 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q103709453 |
| concepts[5].display_name | Attention network |
| concepts[6].id | https://openalex.org/C66322947 |
| concepts[6].level | 3 |
| concepts[6].score | 0.41804736852645874 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11658 |
| concepts[6].display_name | Transformer |
| concepts[7].id | https://openalex.org/C80444323 |
| concepts[7].level | 1 |
| concepts[7].score | 0.3887965977191925 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[7].display_name | Theoretical computer science |
| concepts[8].id | https://openalex.org/C11413529 |
| concepts[8].level | 1 |
| concepts[8].score | 0.34921300411224365 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[8].display_name | Algorithm |
| concepts[9].id | https://openalex.org/C165801399 |
| concepts[9].level | 2 |
| concepts[9].score | 0.1417178213596344 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q25428 |
| concepts[9].display_name | Voltage |
| concepts[10].id | https://openalex.org/C2777212361 |
| concepts[10].level | 2 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q5127848 |
| concepts[10].display_name | Class (philosophy) |
| concepts[11].id | https://openalex.org/C121332964 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[11].display_name | Physics |
| concepts[12].id | https://openalex.org/C62520636 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[12].display_name | Quantum mechanics |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.6428952217102051 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/pattern-recognition |
| keywords[1].score | 0.5663106441497803 |
| keywords[1].display_name | Pattern recognition (psychology) |
| keywords[2].id | https://openalex.org/keywords/action-recognition |
| keywords[2].score | 0.5460843443870544 |
| keywords[2].display_name | Action recognition |
| keywords[3].id | https://openalex.org/keywords/graph |
| keywords[3].score | 0.5056476593017578 |
| keywords[3].display_name | Graph |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.4971828758716583 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/attention-network |
| keywords[5].score | 0.4622063636779785 |
| keywords[5].display_name | Attention network |
| keywords[6].id | https://openalex.org/keywords/transformer |
| keywords[6].score | 0.41804736852645874 |
| keywords[6].display_name | Transformer |
| keywords[7].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[7].score | 0.3887965977191925 |
| keywords[7].display_name | Theoretical computer science |
| keywords[8].id | https://openalex.org/keywords/algorithm |
| keywords[8].score | 0.34921300411224365 |
| keywords[8].display_name | Algorithm |
| keywords[9].id | https://openalex.org/keywords/voltage |
| keywords[9].score | 0.1417178213596344 |
| keywords[9].display_name | Voltage |
| language | en |
| locations[0].id | doi:10.1016/j.knosys.2022.108146 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S10169007 |
| locations[0].source.issn | 0950-7051, 1872-7409 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 0950-7051 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Knowledge-Based Systems |
| locations[0].source.host_organization | https://openalex.org/P4310320990 |
| locations[0].source.host_organization_name | Elsevier BV |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320990 |
| locations[0].source.host_organization_lineage_names | Elsevier BV |
| locations[0].license | cc-by-nc-nd |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by-nc-nd |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Knowledge-Based Systems |
| locations[0].landing_page_url | https://doi.org/10.1016/j.knosys.2022.108146 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5114949884 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-2320-229X |
| authorships[0].author.display_name | Yanan Liu |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I189210763 |
| authorships[0].affiliations[0].raw_affiliation_string | Department of Computer Science and Engineering, School of Information Science and Engineering, Yunnan University, Kunming 650504, China |
| authorships[0].institutions[0].id | https://openalex.org/I189210763 |
| authorships[0].institutions[0].ror | https://ror.org/0040axw97 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I189210763 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Yunnan University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yanan Liu |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Department of Computer Science and Engineering, School of Information Science and Engineering, Yunnan University, Kunming 650504, China |
| authorships[1].author.id | https://openalex.org/A5100396844 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-0404-6941 |
| authorships[1].author.display_name | Hao Zhang |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I189210763 |
| authorships[1].affiliations[0].raw_affiliation_string | Department of Computer Science and Engineering, School of Information Science and Engineering, Yunnan University, Kunming 650504, China |
| authorships[1].institutions[0].id | https://openalex.org/I189210763 |
| authorships[1].institutions[0].ror | https://ror.org/0040axw97 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I189210763 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Yunnan University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Hao Zhang |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Department of Computer Science and Engineering, School of Information Science and Engineering, Yunnan University, Kunming 650504, China |
| authorships[2].author.id | https://openalex.org/A5100778603 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-4602-3550 |
| authorships[2].author.display_name | Dan Xu |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I189210763 |
| authorships[2].affiliations[0].raw_affiliation_string | Department of Computer Science and Engineering, School of Information Science and Engineering, Yunnan University, Kunming 650504, China |
| authorships[2].institutions[0].id | https://openalex.org/I189210763 |
| authorships[2].institutions[0].ror | https://ror.org/0040axw97 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I189210763 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Yunnan University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Dan Xu |
| authorships[2].is_corresponding | True |
| authorships[2].raw_affiliation_strings | Department of Computer Science and Engineering, School of Information Science and Engineering, Yunnan University, Kunming 650504, China |
| authorships[3].author.id | https://openalex.org/A5044301101 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-6207-9728 |
| authorships[3].author.display_name | Kangjian He |
| authorships[3].countries | CN |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I189210763 |
| authorships[3].affiliations[0].raw_affiliation_string | Department of Computer Science and Engineering, School of Information Science and Engineering, Yunnan University, Kunming 650504, China |
| authorships[3].institutions[0].id | https://openalex.org/I189210763 |
| authorships[3].institutions[0].ror | https://ror.org/0040axw97 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I189210763 |
| authorships[3].institutions[0].country_code | CN |
| authorships[3].institutions[0].display_name | Yunnan University |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Kangjian He |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Department of Computer Science and Engineering, School of Information Science and Engineering, Yunnan University, Kunming 650504, China |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.1016/j.knosys.2022.108146 |
| open_access.oa_status | hybrid |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Graph transformer network with temporal kernel attention for skeleton-based action recognition |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| 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 | 1.0 |
| 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/W4283332100, https://openalex.org/W4361193049, https://openalex.org/W4386598245, https://openalex.org/W3200661810, https://openalex.org/W4389995241, https://openalex.org/W4287181611, https://openalex.org/W4200094402, https://openalex.org/W3213655484, https://openalex.org/W4320149722, https://openalex.org/W3104886537 |
| cited_by_count | 134 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 34 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 44 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 42 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 14 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1016/j.knosys.2022.108146 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S10169007 |
| best_oa_location.source.issn | 0950-7051, 1872-7409 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | 0950-7051 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Knowledge-Based Systems |
| best_oa_location.source.host_organization | https://openalex.org/P4310320990 |
| best_oa_location.source.host_organization_name | Elsevier BV |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310320990 |
| best_oa_location.source.host_organization_lineage_names | Elsevier BV |
| best_oa_location.license | cc-by-nc-nd |
| best_oa_location.pdf_url | |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Knowledge-Based Systems |
| best_oa_location.landing_page_url | https://doi.org/10.1016/j.knosys.2022.108146 |
| primary_location.id | doi:10.1016/j.knosys.2022.108146 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S10169007 |
| primary_location.source.issn | 0950-7051, 1872-7409 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 0950-7051 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Knowledge-Based Systems |
| primary_location.source.host_organization | https://openalex.org/P4310320990 |
| primary_location.source.host_organization_name | Elsevier BV |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320990 |
| primary_location.source.host_organization_lineage_names | Elsevier BV |
| primary_location.license | cc-by-nc-nd |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Knowledge-Based Systems |
| primary_location.landing_page_url | https://doi.org/10.1016/j.knosys.2022.108146 |
| publication_date | 2022-01-10 |
| publication_year | 2022 |
| referenced_works | https://openalex.org/W3128461539, https://openalex.org/W3003375623, https://openalex.org/W3109355347, https://openalex.org/W2017049184, https://openalex.org/W2583941031, https://openalex.org/W3164569956, https://openalex.org/W3134090706, https://openalex.org/W2965970896, https://openalex.org/W6677055838, https://openalex.org/W2039051707, https://openalex.org/W6785253800, https://openalex.org/W6791951655, https://openalex.org/W6684499055, https://openalex.org/W6775780680, https://openalex.org/W6800709229, https://openalex.org/W6762621715, https://openalex.org/W2963282966, https://openalex.org/W6750290883, https://openalex.org/W6779113007, https://openalex.org/W3129366157, https://openalex.org/W6662688328, https://openalex.org/W6655757585, https://openalex.org/W6681199532, https://openalex.org/W6726569863, https://openalex.org/W2143004591, https://openalex.org/W4240042586, https://openalex.org/W6743401523, https://openalex.org/W6766113013, https://openalex.org/W2792345332, https://openalex.org/W6759373541, https://openalex.org/W6746803634, https://openalex.org/W6725062358, https://openalex.org/W6740961951, https://openalex.org/W6763223085, https://openalex.org/W3135202376, https://openalex.org/W6750401302, https://openalex.org/W2026498605, https://openalex.org/W6704520437, https://openalex.org/W6730277886, https://openalex.org/W6748947987, https://openalex.org/W4200412139, https://openalex.org/W6743928348, https://openalex.org/W2966210862, https://openalex.org/W6778983983, https://openalex.org/W6768529555, https://openalex.org/W6766161741, https://openalex.org/W2956928039, https://openalex.org/W4247924304, https://openalex.org/W3209485964, https://openalex.org/W3009946848, https://openalex.org/W4230566620, https://openalex.org/W3006529527, https://openalex.org/W4312245820, https://openalex.org/W3138679477, https://openalex.org/W2803865273, https://openalex.org/W2619947201, https://openalex.org/W4292905395, https://openalex.org/W2342662179, https://openalex.org/W2996835428, https://openalex.org/W4302310419, https://openalex.org/W2608982575, https://openalex.org/W3039153384, https://openalex.org/W3092336341, https://openalex.org/W4385245566, https://openalex.org/W3049455300, https://openalex.org/W3113177135, https://openalex.org/W2944006115, https://openalex.org/W3034999503, https://openalex.org/W3148714641, https://openalex.org/W4205445494, https://openalex.org/W2981341885, https://openalex.org/W2802577319, https://openalex.org/W2606294640, https://openalex.org/W3215030504, https://openalex.org/W2963076818, https://openalex.org/W2978927732, https://openalex.org/W4249914127, https://openalex.org/W1924770834, https://openalex.org/W4255556797, https://openalex.org/W3093441220, https://openalex.org/W3197400233, https://openalex.org/W2962555132, https://openalex.org/W3094502228, https://openalex.org/W4247092244 |
| referenced_works_count | 84 |
| abstract_inverted_index.a | 43, 62, 107, 143 |
| abstract_inverted_index.1% | 174 |
| abstract_inverted_index.2% | 199 |
| abstract_inverted_index.60 | 182 |
| abstract_inverted_index.In | 34, 102, 132 |
| abstract_inverted_index.an | 94 |
| abstract_inverted_index.as | 8, 18, 42 |
| abstract_inverted_index.by | 80, 87, 123, 170, 173, 184, 198 |
| abstract_inverted_index.in | 140 |
| abstract_inverted_index.is | 40, 52, 100 |
| abstract_inverted_index.it | 69 |
| abstract_inverted_index.of | 57, 74 |
| abstract_inverted_index.on | 31, 129, 179, 192, 211 |
| abstract_inverted_index.to | 14, 29, 54, 65, 97 |
| abstract_inverted_index.we | 105 |
| abstract_inverted_index.120 | 195 |
| abstract_inverted_index.400 | 214 |
| abstract_inverted_index.GCN | 60 |
| abstract_inverted_index.and | 22, 46, 91, 161, 172, 177, 186, 190, 197, 200, 204, 206 |
| abstract_inverted_index.are | 78, 89 |
| abstract_inverted_index.can | 11, 151 |
| abstract_inverted_index.has | 4, 61 |
| abstract_inverted_index.the | 37, 47, 71, 84, 117, 124, 134, 158, 167, 180, 193, 208, 212 |
| abstract_inverted_index.1.9% | 171 |
| abstract_inverted_index.2.3% | 201 |
| abstract_inverted_index.3.1% | 187 |
| abstract_inverted_index.3.2% | 185 |
| abstract_inverted_index.body | 39 |
| abstract_inverted_index.data | 10 |
| abstract_inverted_index.such | 17 |
| abstract_inverted_index.that | 77 |
| abstract_inverted_index.this | 103 |
| abstract_inverted_index.thus | 25 |
| abstract_inverted_index.used | 53 |
| abstract_inverted_index.view | 20 |
| abstract_inverted_index.wide | 6 |
| abstract_inverted_index.(GCN) | 51 |
| abstract_inverted_index.(TKA) | 138 |
| abstract_inverted_index.After | 156 |
| abstract_inverted_index.Top-1 | 203 |
| abstract_inverted_index.Top-5 | 205 |
| abstract_inverted_index.X-Set | 191 |
| abstract_inverted_index.X-Sub | 176, 189 |
| abstract_inverted_index.adapt | 13 |
| abstract_inverted_index.based | 128 |
| abstract_inverted_index.block | 139 |
| abstract_inverted_index.focus | 30 |
| abstract_inverted_index.graph | 48, 111, 125, 163 |
| abstract_inverted_index.hence | 92 |
| abstract_inverted_index.human | 1, 38 |
| abstract_inverted_index.learn | 66 |
| abstract_inverted_index.score | 146 |
| abstract_inverted_index.under | 175, 188, 202 |
| abstract_inverted_index.using | 147 |
| abstract_inverted_index.weigh | 98 |
| abstract_inverted_index.which | 115, 150 |
| abstract_inverted_index.work, | 104 |
| abstract_inverted_index.Kernel | 136 |
| abstract_inverted_index.X-View | 178 |
| abstract_inverted_index.action | 2 |
| abstract_inverted_index.camera | 19 |
| abstract_inverted_index.caused | 5 |
| abstract_inverted_index.graph, | 45 |
| abstract_inverted_index.joints | 85, 122 |
| abstract_inverted_index.kernel | 108 |
| abstract_inverted_index.models | 116 |
| abstract_inverted_index.modes, | 68 |
| abstract_inverted_index.motion | 154 |
| abstract_inverted_index.recent | 35 |
| abstract_inverted_index.robust | 32 |
| abstract_inverted_index.strong | 63 |
| abstract_inverted_index.2s-AGCN | 169 |
| abstract_inverted_index.KA-AGTN | 141, 165 |
| abstract_inverted_index.ability | 64 |
| abstract_inverted_index.between | 121 |
| abstract_inverted_index.changes | 21 |
| abstract_inverted_index.degrees | 73 |
| abstract_inverted_index.dynamic | 15 |
| abstract_inverted_index.enhance | 152 |
| abstract_inverted_index.extract | 55 |
| abstract_inverted_index.ignores | 70 |
| abstract_inverted_index.message | 81 |
| abstract_inverted_index.methods | 28 |
| abstract_inverted_index.modeled | 41 |
| abstract_inverted_index.network | 50, 113 |
| abstract_inverted_index.propose | 106 |
| abstract_inverted_index.spatial | 67, 119 |
| abstract_inverted_index.varying | 72 |
| abstract_inverted_index.Although | 59 |
| abstract_inverted_index.NTU-RGBD | 181, 194 |
| abstract_inverted_index.Temporal | 135 |
| abstract_inverted_index.achieves | 207 |
| abstract_inverted_index.actions. | 58 |
| abstract_inverted_index.adaptive | 110, 162 |
| abstract_inverted_index.allowing | 26 |
| abstract_inverted_index.baseline | 168 |
| abstract_inverted_index.captured | 79 |
| abstract_inverted_index.concern, | 7 |
| abstract_inverted_index.dataset, | 183, 196 |
| abstract_inverted_index.dataset. | 215 |
| abstract_inverted_index.features | 56 |
| abstract_inverted_index.operator | 127 |
| abstract_inverted_index.passing. | 82 |
| abstract_inverted_index.robustly | 12 |
| abstract_inverted_index.skeleton | 9 |
| abstract_inverted_index.studies, | 36 |
| abstract_inverted_index.temporal | 148, 153 |
| abstract_inverted_index.vertices | 88 |
| abstract_inverted_index.Attention | 137 |
| abstract_inverted_index.Moreover, | 83 |
| abstract_inverted_index.addition, | 133 |
| abstract_inverted_index.attention | 95, 109, 145 |
| abstract_inverted_index.combining | 157 |
| abstract_inverted_index.features, | 149 |
| abstract_inverted_index.features. | 33 |
| abstract_inverted_index.framework | 160 |
| abstract_inverted_index.generates | 142 |
| abstract_inverted_index.mechanism | 96 |
| abstract_inverted_index.multihead | 130 |
| abstract_inverted_index.strategy, | 164 |
| abstract_inverted_index.(KA-AGTN), | 114 |
| abstract_inverted_index.background | 23 |
| abstract_inverted_index.two-stream | 159 |
| abstract_inverted_index.beneficial. | 101 |
| abstract_inverted_index.convolution | 49 |
| abstract_inverted_index.outperforms | 166 |
| abstract_inverted_index.performance | 210 |
| abstract_inverted_index.recognition | 3, 27 |
| abstract_inverted_index.represented | 86 |
| abstract_inverted_index.topological | 44 |
| abstract_inverted_index.transformer | 112, 126 |
| abstract_inverted_index.correlation. | 155 |
| abstract_inverted_index.dependencies | 76, 99, 120 |
| abstract_inverted_index.higher-order | 75, 118 |
| abstract_inverted_index.interference | 24 |
| abstract_inverted_index.channel-level | 144 |
| abstract_inverted_index.circumstances | 16 |
| abstract_inverted_index.incorporating | 93 |
| abstract_inverted_index.Skeleton-based | 0 |
| abstract_inverted_index.interdependent, | 90 |
| abstract_inverted_index.self-attention. | 131 |
| abstract_inverted_index.state-of-the-art | 209 |
| abstract_inverted_index.Kinetics-Skeleton | 213 |
| cited_by_percentile_year.max | 100 |
| cited_by_percentile_year.min | 99 |
| corresponding_author_ids | https://openalex.org/A5100778603 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 4 |
| corresponding_institution_ids | https://openalex.org/I189210763 |
| citation_normalized_percentile.value | 0.99450222 |
| citation_normalized_percentile.is_in_top_1_percent | True |
| citation_normalized_percentile.is_in_top_10_percent | True |