# A Variational Auto-Encoder Model for Stochastic Point Processes

arXiv: https://arxiv.org/abs/1904.03273 · HTML: https://mlsanity.com/paper/1904.03273/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Apr 2019.

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

- [P3IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervision](https://mlsanity.com/paper/2205.02300/) (2022)
- [Spatio-temporal Diffusion Point Processes](https://mlsanity.com/paper/2305.12403/) (2023)
- [Bayesian Prompt Learning for Image-Language Model Generalization](https://mlsanity.com/paper/2210.02390/) (2022)
- [Deep Learning-Enabled Semantic Communication Systems with Task-Unaware Transmitter and Dynamic Data](https://mlsanity.com/paper/2205.00271/) (2022)
- [Intention-Conditioned Long-Term Human Egocentric Action Forecasting](https://mlsanity.com/paper/2207.12080/) (2022)
- [Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization](https://mlsanity.com/paper/2206.04496/) (2022)
- [Rethinking Learning Approaches for Long-Term Action Anticipation](https://mlsanity.com/paper/2210.11566/) (2022)
- [Pretrained Language Models as Visual Planners for Human Assistance](https://mlsanity.com/paper/2304.09179/) (2023)
- [Predicting the Next Action by Modeling the Abstract Goal](https://mlsanity.com/paper/2209.05044/) (2022)
- [ProActive: Self-Attentive Temporal Point Process Flows for Activity Sequences](https://mlsanity.com/paper/2206.05291/) (2022)
- [A Survey on Deep Learning Techniques for Action Anticipation](https://mlsanity.com/paper/2309.17257/) (2023)
- [DiffAnt: Diffusion Models for Action Anticipation](https://mlsanity.com/paper/2311.15991/) (2023)
- [Human Action Anticipation: A Survey](https://mlsanity.com/paper/2410.14045/) (2024)
- [Non-Autoregressive Diffusion-based Temporal Point Processes for Continuous-Time Long-Term Event Prediction](https://mlsanity.com/paper/2311.01033/) (2023)
- [Deep Neyman-Scott Processes](https://mlsanity.com/paper/2111.03949/) (2021)
- [Modeling Events and Interactions through Temporal Processes -- A Survey](https://mlsanity.com/paper/2303.06067/) (2023)
- [Review of Video Predictive Understanding: Early Action Recognition and Future Action Prediction](https://mlsanity.com/paper/2107.05140/) (2021)
- [PCENet: High Dimensional Surrogate Modeling for Learning Uncertainty](https://mlsanity.com/paper/2202.05063/) (2022)
- [Streaming egocentric action anticipation: An evaluation scheme and approach](https://mlsanity.com/paper/2306.16682/) (2023)
- [LAST SToP For Modeling Asynchronous Time Series](https://mlsanity.com/paper/2502.01922/) (2025)
- [Modeling Continuous Time Sequences with Intermittent Observations using Marked Temporal Point Processes](https://mlsanity.com/paper/2206.12414/) (2022)
- [Individual Mobility Prediction via Attentive Marked Temporal Point Processes](https://mlsanity.com/paper/2109.02715/) (2021)
- [Modeling Time-Series and Spatial Data for Recommendations and Other Applications](https://mlsanity.com/paper/2212.13259/) (2022)
- [Tapestry of Time and Actions: Modeling Human Activity Sequences using Temporal Point Process Flows](https://mlsanity.com/paper/2307.10305/) (2023)
- [Pretext Training Algorithms for Event Sequence Data](https://mlsanity.com/paper/2402.10392/) (2024)
- [Neural Diffusion Intensity Models for Point Process Data](https://mlsanity.com/paper/2602.24083/) (2026)
- [ReDiTT: Retrieval Augmented Conditional Diffusion Transformers for Asynchronous Time Series](https://mlsanity.com/paper/2607.12391/) (2026)
- [PLAN-B: Predicting Likely Alternative Next Best Sequences for Action Prediction](https://mlsanity.com/paper/2103.15987/) (2021)
- [Analysis of ODE2VAE with Examples](https://mlsanity.com/paper/2108.04899/) (2021)
- [Finding Islands of Predictability in Action Forecasting](https://mlsanity.com/paper/2210.07354/) (2022)

## Abstract (arXiv)

We propose a novel probabilistic generative model for action sequences. The model is termed the Action Point Process VAE (APP-VAE), a variational auto-encoder that can capture the distribution over the times and categories of action sequences. Modeling the variety of possible action sequences is a challenge, which we show can be addressed via the APP-VAE's use of latent representations and non-linear functions to parameterize distributions over which event is likely to occur next in a sequence and at what time. We empirically validate the efficacy of APP-VAE for modeling action sequences on the MultiTHUMOS and Breakfast datasets.