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/Poseidon

Poseidon

Reported on 9 benchmarks across 5 tasks · 1 paper · 8 SOTA

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

Computer Vision4 results

Pose EstimationonPoseTrack21
Mean mAP· uses extra data· 2025-01-14
88.3
SOTA
Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature Fusion arXiv:2501.08446
Pose EstimationonPoseTrack2018
Mean mAP· uses extra data· 2025-01-14
87.8
SOTA
Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature Fusion arXiv:2501.08446
Multi-Person Pose EstimationonPoseTrack21
Mean mAP· uses extra data· 2025-01-14
88.3
SOTA
Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature Fusion arXiv:2501.08446
Multi-Person Pose EstimationonPoseTrack2018
Mean mAP· uses extra data· 2025-01-14
87.8
SOTA
Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature Fusion arXiv:2501.08446

Methodology2 results

3DonPoseTrack21
Mean mAP· uses extra data· 2025-01-14
88.3
SOTA
Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature Fusion arXiv:2501.08446
3DonPoseTrack2018
Mean mAP· uses extra data· 2025-01-14
87.8
SOTA
Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature Fusion arXiv:2501.08446

Audio2 results

1 Image, 2*2 StitchionPoseTrack21
Mean mAP· uses extra data· 2025-01-14
88.3
SOTA
Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature Fusion arXiv:2501.08446
1 Image, 2*2 StitchionPoseTrack2018
Mean mAP· uses extra data· 2025-01-14
87.8
SOTA
Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature Fusion arXiv:2501.08446

Knowledge Base1 result

2D Human Pose EstimationonJHMDB (2D poses only)
PCK· 2025-01-14
97.3
best: 98.8 (DeciWatch)
Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature Fusion arXiv:2501.08446