SOTAVerified

Human action generation

Yan et al. (2019) CSGN:

"When the dancer is stepping, jumping and spinning on the stage, attentions of all audiences are attracted by the streamof the fluent and graceful movements. Building a model that is capable of dancing is as fascinating a task as appreciating the performance itself. In this paper, we aim to generate long-duration human actions represented as skeleton sequences, e.g. those that cover the entirety of a dance, with hundreds of moves and countless possible combinations."

( Image credit: Convolutional Sequence Generation for Skeleton-Based Action Synthesis )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 13 papers

TitleStatusHype
FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance—0
FLAG3D: A 3D Fitness Activity Dataset with Language InstructionCode0
Action-conditioned On-demand Motion GenerationCode0
MUGL: Large Scale Multi Person Conditional Action Generation with LocomotionCode1
Generative Adversarial Graph Convolutional Networks for Human Action SynthesisCode1
Action-Conditioned 3D Human Motion Synthesis with Transformer VAECode1
Action2Motion: Conditioned Generation of 3D Human MotionsCode1
Structure-Aware Human-Action GenerationCode1
Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent TransitionsCode0
Convolutional Sequence Generation for Skeleton-Based Action Synthesis—0
Show:102550
← PrevPage 1 of 2Next →
All datasetsHuman3.6MNTU RGB+D 2DNTU RGB+DNTU RGB+D 120CMU MocapHumanAct12UESTC RGB-D

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ODMOAccuracy97.81—Unverified