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/Text2Gesture

Text2Gesture

Reported on 24 benchmarks across 4 tasks · 1 paper · 8 SOTA

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

Audio12 results

10-shot image generationonHumanML3D
FID· 2022-07-04
5.012
best: 0.028 (Motion Anything)
SOTA
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
10-shot image generationonKIT Motion-Language
FID· 2022-07-04
12.12
best: 0.131 (Motion Anything)
SOTA
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
3D Human Pose TrackingonHumanML3D
FID· 2022-07-04
5.012
best: 0.028 (Motion Anything)
SOTA
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
3D Human Pose TrackingonKIT Motion-Language
FID· 2022-07-04
12.12
best: 0.131 (Motion Anything)
SOTA
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
10-shot image generationonHumanML3D
Diversity· 2022-07-04
6.409
best: 23.692 (Diffuion Motion)
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
10-shot image generationonHumanML3D
R Precision Top3· 2022-07-04
0.345
best: 0.842 (MotionPCM)
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
10-shot image generationonKIT Motion-Language
Diversity· 2022-07-04
9.334
best: 11.198 (T2M-GPT (τ = 0))
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
10-shot image generationonKIT Motion-Language
R Precision Top3· 2022-07-04
0.338
best: 0.803 (BiPO)
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
3D Human Pose TrackingonHumanML3D
Diversity· 2022-07-04
6.409
best: 23.692 (Diffuion Motion)
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
3D Human Pose TrackingonHumanML3D
R Precision Top3· 2022-07-04
0.345
best: 0.842 (MotionPCM)
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
3D Human Pose TrackingonKIT Motion-Language
Diversity· 2022-07-04
9.334
best: 11.198 (T2M-GPT (τ = 0))
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
3D Human Pose TrackingonKIT Motion-Language
R Precision Top3· 2022-07-04
0.338
best: 0.803 (BiPO)
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696

Computer Vision6 results

Pose TrackingonHumanML3D
FID· 2022-07-04
5.012
best: 0.028 (Motion Anything)
SOTA
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
Pose TrackingonKIT Motion-Language
FID· 2022-07-04
12.12
best: 0.131 (Motion Anything)
SOTA
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
Pose TrackingonHumanML3D
Diversity· 2022-07-04
6.409
best: 23.692 (Diffuion Motion)
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
Pose TrackingonHumanML3D
R Precision Top3· 2022-07-04
0.345
best: 0.842 (MotionPCM)
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
Pose TrackingonKIT Motion-Language
Diversity· 2022-07-04
9.334
best: 11.198 (T2M-GPT (τ = 0))
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
Pose TrackingonKIT Motion-Language
R Precision Top3· 2022-07-04
0.338
best: 0.803 (BiPO)
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696

Computer Code6 results

Motion SynthesisonHumanML3D
FID· 2022-07-04
5.012
best: 0.028 (Motion Anything)
SOTA
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
Motion SynthesisonKIT Motion-Language
FID· 2022-07-04
12.12
best: 0.131 (Motion Anything)
SOTA
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
Motion SynthesisonHumanML3D
Diversity· 2022-07-04
6.409
best: 23.692 (Diffuion Motion)
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
Motion SynthesisonHumanML3D
R Precision Top3· 2022-07-04
0.345
best: 0.842 (MotionPCM)
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
Motion SynthesisonKIT Motion-Language
Diversity· 2022-07-04
9.334
best: 11.198 (T2M-GPT (τ = 0))
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696
Motion SynthesisonKIT Motion-Language
R Precision Top3· 2022-07-04
0.338
best: 0.803 (BiPO)
TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts arXiv:2207.01696