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/T2M-GPT (τ ∈ U[0, 1])

T2M-GPT (τ ∈ U[0, 1])

Reported on 16 benchmarks across 4 tasks · 1 paper · 4 SOTA

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

Audio8 results

10-shot image generationonHumanML3D
FID· 2023-01-15
0.141
best: 0.028 (Motion Anything)
SOTA
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations arXiv:2301.06052
3D Human Pose TrackingonHumanML3D
FID· 2023-01-15
0.141
best: 0.028 (Motion Anything)
SOTA
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations arXiv:2301.06052
10-shot image generationonHumanML3D
Diversity· 2023-01-15
9.722
best: 23.692 (Diffuion Motion)
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations arXiv:2301.06052
10-shot image generationonHumanML3D
Multimodality· 2023-01-15
1.831
best: 4.139 (TM2D (t2m))
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations arXiv:2301.06052
10-shot image generationonHumanML3D
R Precision Top3· 2023-01-15
0.775
best: 0.842 (MotionPCM)
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations arXiv:2301.06052
3D Human Pose TrackingonHumanML3D
Diversity· 2023-01-15
9.722
best: 23.692 (Diffuion Motion)
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations arXiv:2301.06052
3D Human Pose TrackingonHumanML3D
Multimodality· 2023-01-15
1.831
best: 4.139 (TM2D (t2m))
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations arXiv:2301.06052
3D Human Pose TrackingonHumanML3D
R Precision Top3· 2023-01-15
0.775
best: 0.842 (MotionPCM)
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations arXiv:2301.06052

Computer Vision4 results

Pose TrackingonHumanML3D
FID· 2023-01-15
0.141
best: 0.028 (Motion Anything)
SOTA
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations arXiv:2301.06052
Pose TrackingonHumanML3D
Diversity· 2023-01-15
9.722
best: 23.692 (Diffuion Motion)
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations arXiv:2301.06052
Pose TrackingonHumanML3D
Multimodality· 2023-01-15
1.831
best: 4.139 (TM2D (t2m))
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations arXiv:2301.06052
Pose TrackingonHumanML3D
R Precision Top3· 2023-01-15
0.775
best: 0.842 (MotionPCM)
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations arXiv:2301.06052

Computer Code4 results

Motion SynthesisonHumanML3D
FID· 2023-01-15
0.141
best: 0.028 (Motion Anything)
SOTA
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations arXiv:2301.06052
Motion SynthesisonHumanML3D
Diversity· 2023-01-15
9.722
best: 23.692 (Diffuion Motion)
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations arXiv:2301.06052
Motion SynthesisonHumanML3D
Multimodality· 2023-01-15
1.831
best: 4.139 (TM2D (t2m))
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations arXiv:2301.06052
Motion SynthesisonHumanML3D
R Precision Top3· 2023-01-15
0.775
best: 0.842 (MotionPCM)
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations arXiv:2301.06052