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/A2J Transformer

A2J Transformer

Reported on 10 benchmarks across 5 tasks · 1 paper

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

Computer Vision4 results

HandonNYU Hands
Average 3D Error· 2023-04-07
8.43
best: 6.4 (Virtual View Selection)
A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image arXiv:2304.03635
HandonNYU Hands
FPS· 2023-04-07
24.8
best: 105.06 (A2J)
A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image arXiv:2304.03635
Pose EstimationonNYU Hands
Average 3D Error· 2023-04-07
8.43
best: 6.4 (Virtual View Selection)
A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image arXiv:2304.03635
Pose EstimationonNYU Hands
FPS· 2023-04-07
24.8
best: 105.06 (A2J)
A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image arXiv:2304.03635

Graphs2 results

Hand Pose EstimationonNYU Hands
Average 3D Error· 2023-04-07
8.43
best: 6.4 (Virtual View Selection)
A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image arXiv:2304.03635
Hand Pose EstimationonNYU Hands
FPS· 2023-04-07
24.8
best: 105.06 (A2J)
A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image arXiv:2304.03635

Methodology2 results

3DonNYU Hands
Average 3D Error· 2023-04-07
8.43
best: 6.4 (Virtual View Selection)
A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image arXiv:2304.03635
3DonNYU Hands
FPS· 2023-04-07
24.8
best: 105.06 (A2J)
A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image arXiv:2304.03635

Audio2 results

1 Image, 2*2 StitchionNYU Hands
Average 3D Error· 2023-04-07
8.43
best: 6.4 (Virtual View Selection)
A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image arXiv:2304.03635
1 Image, 2*2 StitchionNYU Hands
FPS· 2023-04-07
24.8
best: 105.06 (A2J)
A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image arXiv:2304.03635