# Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions

arXiv: https://arxiv.org/abs/1912.10150 · HTML: https://mlsanity.com/paper/1912.10150/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2019.

## Built on by (most cited first, 30 of 46)

- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset](https://mlsanity.com/paper/2307.00818/) (2023)
- [HumanTOMATO: Text-aligned Whole-body Motion Generation](https://mlsanity.com/paper/2310.12978/) (2023)
- [Single Motion Diffusion](https://mlsanity.com/paper/2302.05905/) (2023)
- [Large Motion Model for Unified Multi-Modal Motion Generation](https://mlsanity.com/paper/2404.01284/) (2024)
- [MoDi: Unconditional Motion Synthesis from Diverse Data](https://mlsanity.com/paper/2206.08010/) (2022)
- [Interaction Transformer for Human Reaction Generation](https://mlsanity.com/paper/2207.01685/) (2022)
- [MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling](https://mlsanity.com/paper/2409.17686/) (2024)
- [WANDR: Intention-guided Human Motion Generation](https://mlsanity.com/paper/2404.15383/) (2024)
- [PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision](https://mlsanity.com/paper/2203.15625/) (2022)
- [InsActor: Instruction-driven Physics-based Characters](https://mlsanity.com/paper/2312.17135/) (2023)
- [Generative Adversarial Graph Convolutional Networks for Human Action Synthesis](https://mlsanity.com/paper/2110.11191/) (2021)
- [FLAG3D: A 3D Fitness Activity Dataset with Language Instruction](https://mlsanity.com/paper/2212.04638/) (2022)
- [Scaling Large Motion Models with Million-Level Human Motions](https://mlsanity.com/paper/2410.03311/) (2024)
- [OmniMotionGPT: Animal Motion Generation with Limited Data](https://mlsanity.com/paper/2311.18303/) (2023)
- [UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation](https://mlsanity.com/paper/2508.01126/) (2025)
- [Action2video: Generating Videos of Human 3D Actions](https://mlsanity.com/paper/2111.06925/) (2021)
- [HERO: Human Reaction Generation from Videos](https://mlsanity.com/paper/2503.08270/) (2025)
- [Dynamic Motion Blending for Versatile Motion Editing](https://mlsanity.com/paper/2503.20724/) (2025)
- [Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model](https://mlsanity.com/paper/2508.07863/) (2025)
- [Text-driven Motion Generation: Overview, Challenges and Directions](https://mlsanity.com/paper/2505.09379/) (2025)
- [Efficient Text-driven Motion Generation via Latent Consistency Training](https://mlsanity.com/paper/2405.02791/) (2024)
- [BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis](https://mlsanity.com/paper/2412.00112/) (2024)
- [Learning Disentangled Representations for Controllable Human Motion Prediction](https://mlsanity.com/paper/2207.01388/) (2022)
- [Omni-Supervised Motion Editing: Balancing Change and Invariance through Positive-Negative Learning](https://mlsanity.com/paper/2605.30969/) (2026)
- [MPE4G: Multimodal Pretrained Encoder for Co-Speech Gesture Generation](https://mlsanity.com/paper/2305.15740/) (2023)
- [SIGHT: Synthesizing Image-Text Conditioned and Geometry-Guided 3D Hand-Object Trajectories](https://mlsanity.com/paper/2503.22869/) (2025)
- [OmniMotion: Multimodal Motion Generation with Continuous Masked Autoregression](https://mlsanity.com/paper/2510.14954/) (2025)

## Abstract (arXiv)

Human-motion generation is a long-standing challenging task due to the requirement of accurately modeling complex and diverse dynamic patterns. Most existing methods adopt sequence models such as RNN to directly model transitions in the original action space. Due to high dimensionality and potential noise, such modeling of action transitions is particularly challenging. In this paper, we focus on skeleton-based action generation and propose to model smooth and diverse transitions on a latent space of action sequences with much lower dimensionality. Conditioned on a latent sequence, actions are generated by a frame-wise decoder shared by all latent action-poses. Specifically, an implicit RNN is defined to model smooth latent sequences, whose randomness (diversity) is controlled by noise from the input. Different from standard action-prediction methods, our model can generate action sequences from pure noise without any conditional action poses. Remarkably, it can also generate unseen actions from mixed classes during training. Our model is learned with a bi-directional generative-adversarial-net framework, which not only can generate diverse action sequences of a particular class or mix classes, but also learns to classify action sequences within the same model. Experimental results show the superiority of our method in both diverse action-sequence generation and classification, relative to existing methods.