# ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation

arXiv: https://arxiv.org/abs/2412.04353 · HTML: https://mlsanity.com/paper/2412.04353/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 49 of its 67 references that are in the map.
- First posted on arXiv 5 Dec 2024.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 49)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning](https://mlsanity.com/paper/2208.04202/) (2022)
- [DiffusionDet: Diffusion Model for Object Detection](https://mlsanity.com/paper/2211.09788/) (2022)
- [Flexible Diffusion Modeling of Long Videos](https://mlsanity.com/paper/2205.11495/) (2022)
- [Diffusion Probabilistic Modeling for Video Generation](https://mlsanity.com/paper/2203.09481/) (2022)
- [ASFormer: Transformer for Action Segmentation](https://mlsanity.com/paper/2110.08568/) (2021)
- [When will you do what? - Anticipating Temporal Occurrences of Activities](https://mlsanity.com/paper/1804.00892/) (2018)
- [Alleviating Over-segmentation Errors by Detecting Action Boundaries](https://mlsanity.com/paper/2007.06866/) (2020)
- [Temporal Action Segmentation: An Analysis of Modern Techniques](https://mlsanity.com/paper/2210.10352/) (2022)
- [Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis](https://mlsanity.com/paper/2208.13753/) (2022)
- [Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation](https://mlsanity.com/paper/2003.02824/) (2020)
- [Diffusion Action Segmentation](https://mlsanity.com/paper/2303.17959/) (2023)
- [VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation](https://mlsanity.com/paper/2309.00398/) (2023)

## Built on by (most cited first, 4 of 4)

- [Multi-level and Multi-modal Action Anticipation](https://mlsanity.com/paper/2506.02382/) (2025)
- [Countering Multi-modal Representation Collapse through Rank-targeted Fusion](https://mlsanity.com/paper/2511.06450/) (2025)
- [Learning Action Hierarchies via Hybrid Geometric Diffusion](https://mlsanity.com/paper/2601.01914/) (2026)
- [Boundary-Centric Clip-Budgeted Active Learning for Temporal Action Segmentation](https://mlsanity.com/paper/2604.15173/) (2026)

## Abstract (arXiv)

Temporal action segmentation and long-term action anticipation are two popular vision tasks for the temporal analysis of actions in videos. Despite apparent relevance and potential complementarity, these two problems have been investigated as separate and distinct tasks. In this work, we tackle these two problems, action segmentation and action anticipation, jointly using a unified diffusion model dubbed ActFusion. The key idea to unification is to train the model to effectively handle both visible and invisible parts of the sequence in an integrated manner; the visible part is for temporal segmentation, and the invisible part is for future anticipation. To this end, we introduce a new anticipative masking strategy during training in which a late part of the video frames is masked as invisible, and learnable tokens replace these frames to learn to predict the invisible future. Experimental results demonstrate the bi-directional benefits between action segmentation and anticipation. ActFusion achieves the state-of-the-art performance across the standard benchmarks of 50 Salads, Breakfast, and GTEA, outperforming task-specific models in both of the two tasks with a single unified model through joint learning.