Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/PGFA

PGFA

Reported on 51 benchmarks across 8 tasks · 1 paper · 28 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision23 results

VideoonNTU RGB+D 120
Accuracy (10 unseen classes)· 2025-07-01
79.99
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
VideoonNTU RGB+D 120
Random Split Accuracy· 2025-07-01
71.38
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
VideoonPKU-MMD
Random Split Accuracy· 2025-07-01
87.8
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
VideoonNTU RGB+D
Random Split Accuracy· 2025-07-01
93.17
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (10 unseen classes)· 2025-07-01
79.99
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Temporal Action LocalizationonNTU RGB+D 120
Random Split Accuracy· 2025-07-01
71.38
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Temporal Action LocalizationonPKU-MMD
Random Split Accuracy· 2025-07-01
87.8
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Temporal Action LocalizationonNTU RGB+D
Random Split Accuracy· 2025-07-01
93.17
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Action LocalizationonNTU RGB+D 120
Accuracy (10 unseen classes)· 2025-07-01
79.99
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Action LocalizationonNTU RGB+D 120
Random Split Accuracy· 2025-07-01
71.38
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Action LocalizationonPKU-MMD
Random Split Accuracy· 2025-07-01
87.8
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Action LocalizationonNTU RGB+D
Random Split Accuracy· 2025-07-01
93.17
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
VideoonNTU RGB+D 120
Accuracy (24 unseen classes)· 2025-07-01
59.42
best: 65.06 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
VideoonNTU RGB+D
Accuracy (12 unseen classes)· 2025-07-01
55.99
best: 56.03 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
VideoonNTU RGB+D
Accuracy (5 unseen classes)· 2025-07-01
80.26
best: 86.49 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (24 unseen classes)· 2025-07-01
59.42
best: 65.06 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Temporal Action LocalizationonNTU RGB+D
Accuracy (12 unseen classes)· 2025-07-01
55.99
best: 56.03 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Temporal Action LocalizationonNTU RGB+D
Accuracy (5 unseen classes)· 2025-07-01
80.26
best: 86.49 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Action LocalizationonNTU RGB+D 120
Accuracy (24 unseen classes)· 2025-07-01
59.42
best: 65.06 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Action LocalizationonNTU RGB+D
Accuracy (12 unseen classes)· 2025-07-01
55.99
best: 56.03 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Action LocalizationonNTU RGB+D
Accuracy (5 unseen classes)· 2025-07-01
80.26
best: 86.49 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Person Re-IdentificationonOccluded-DukeMTMC
Rank-1
51.4
best: 84.31 (KPR + SOLIDER)
Person Re-IdentificationonOccluded-DukeMTMC
mAP
37.3
best: 75.11 (KPR + SOLIDER)

Methodology7 results

Zero-Shot LearningonNTU RGB+D 120
Accuracy (10 unseen classes)· 2025-07-01
79.99
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Zero-Shot LearningonNTU RGB+D 120
Random Split Accuracy· 2025-07-01
71.38
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Zero-Shot LearningonPKU-MMD
Random Split Accuracy· 2025-07-01
87.8
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Zero-Shot LearningonNTU RGB+D
Random Split Accuracy· 2025-07-01
93.17
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Zero-Shot LearningonNTU RGB+D 120
Accuracy (24 unseen classes)· 2025-07-01
59.42
best: 65.06 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Zero-Shot LearningonNTU RGB+D
Accuracy (12 unseen classes)· 2025-07-01
55.99
best: 56.03 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Zero-Shot LearningonNTU RGB+D
Accuracy (5 unseen classes)· 2025-07-01
80.26
best: 86.49 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566

Robots7 results

Activity RecognitiononNTU RGB+D 120
Accuracy (10 unseen classes)· 2025-07-01
79.99
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Activity RecognitiononNTU RGB+D 120
Random Split Accuracy· 2025-07-01
71.38
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Activity RecognitiononPKU-MMD
Random Split Accuracy· 2025-07-01
87.8
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Activity RecognitiononNTU RGB+D
Random Split Accuracy· 2025-07-01
93.17
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Activity RecognitiononNTU RGB+D 120
Accuracy (24 unseen classes)· 2025-07-01
59.42
best: 65.06 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Activity RecognitiononNTU RGB+D
Accuracy (12 unseen classes)· 2025-07-01
55.99
best: 56.03 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Activity RecognitiononNTU RGB+D
Accuracy (5 unseen classes)· 2025-07-01
80.26
best: 86.49 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566

Natural Language Processing7 results

3D Action RecognitiononNTU RGB+D 120
Accuracy (10 unseen classes)· 2025-07-01
79.99
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
3D Action RecognitiononNTU RGB+D 120
Random Split Accuracy· 2025-07-01
71.38
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
3D Action RecognitiononPKU-MMD
Random Split Accuracy· 2025-07-01
87.8
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
3D Action RecognitiononNTU RGB+D
Random Split Accuracy· 2025-07-01
93.17
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
3D Action RecognitiononNTU RGB+D 120
Accuracy (24 unseen classes)· 2025-07-01
59.42
best: 65.06 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
3D Action RecognitiononNTU RGB+D
Accuracy (12 unseen classes)· 2025-07-01
55.99
best: 56.03 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
3D Action RecognitiononNTU RGB+D
Accuracy (5 unseen classes)· 2025-07-01
80.26
best: 86.49 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566

Time Series7 results

Action RecognitiononNTU RGB+D 120
Accuracy (10 unseen classes)· 2025-07-01
79.99
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Action RecognitiononNTU RGB+D 120
Random Split Accuracy· 2025-07-01
71.38
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Action RecognitiononPKU-MMD
Random Split Accuracy· 2025-07-01
87.8
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Action RecognitiononNTU RGB+D
Random Split Accuracy· 2025-07-01
93.17
SOTA
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Action RecognitiononNTU RGB+D 120
Accuracy (24 unseen classes)· 2025-07-01
59.42
best: 65.06 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Action RecognitiononNTU RGB+D
Accuracy (12 unseen classes)· 2025-07-01
55.99
best: 56.03 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566
Action RecognitiononNTU RGB+D
Accuracy (5 unseen classes)· 2025-07-01
80.26
best: 86.49 (TDSM)
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment arXiv:2507.00566