# ActionDiffusion: An Action-aware Diffusion Model for Procedure Planning in Instructional Videos

arXiv: https://arxiv.org/abs/2403.08591 · HTML: https://mlsanity.com/paper/2403.08591/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 33 of its 37 references that are in the map.
- First posted on arXiv 13 Mar 2024.

## Placed in

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

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation](https://mlsanity.com/paper/2303.08320/) (2023)
- [COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis](https://mlsanity.com/paper/1903.02874/) (2019)
- [Temporal Segment Networks for Action Recognition in Videos](https://mlsanity.com/paper/1705.02953/) (2017)
- [Diffusion-based Generation, Optimization, and Planning in 3D Scenes](https://mlsanity.com/paper/2301.06015/) (2023)
- [Cross-task weakly supervised learning from instructional videos](https://mlsanity.com/paper/1903.08225/) (2019)
- [Temporal Pyramid Network for Action Recognition](https://mlsanity.com/paper/2004.03548/) (2020)
- [Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video](https://mlsanity.com/paper/2005.02190/) (2020)
- [Unsupervised Learning from Narrated Instruction Videos](https://mlsanity.com/paper/1506.09215/) (2015)
- [Procedure Planning in Instructional Videos](https://mlsanity.com/paper/1907.01172/) (2019)
- [Future Transformer for Long-term Action Anticipation](https://mlsanity.com/paper/2205.14022/) (2022)
- [Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning](https://mlsanity.com/paper/2110.01770/) (2021)
- [P3IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervision](https://mlsanity.com/paper/2205.02300/) (2022)
- [PlaTe: Visually-Grounded Planning with Transformers in Procedural Tasks](https://mlsanity.com/paper/2109.04869/) (2021)
- [PDPP: Projected Diffusion for Procedure Planning in Instructional Videos](https://mlsanity.com/paper/2303.14676/) (2023)
- [Deep Learning of Koopman Representation for Control](https://mlsanity.com/paper/2010.07546/) (2020)
- [Latent Space Roadmap for Visual Action Planning of Deformable and Rigid Object Manipulation](https://mlsanity.com/paper/2003.08974/) (2020)
- [Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation](https://mlsanity.com/paper/1910.13395/) (2019)

## Built on by (most cited first, 8 of 8)

- [Diffusion Model for Planning: A Systematic Literature Review](https://mlsanity.com/paper/2408.10266/) (2024)
- [VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning](https://mlsanity.com/paper/2410.03478/) (2024)
- [GeoWorld: Geometric World Models](https://mlsanity.com/paper/2602.23058/) (2026)
- [HOIGaze: Gaze Estimation During Hand-Object Interactions in Extended Reality Exploiting Eye-Hand-Head Coordination](https://mlsanity.com/paper/2504.19828/) (2025)
- [OSEF: One-Step Evidence Fusion for Cross-Video Scene Procedure Planning](https://mlsanity.com/paper/2607.29401/) (2026)
- [CLAD: Constrained Latent Action Diffusion for Vision-Language Procedure Planning](https://mlsanity.com/paper/2503.06637/) (2025)
- [LAP: A Language-Aware Planning Model For Procedure Planning In Instructional Videos](https://mlsanity.com/paper/2603.09743/) (2026)
- [HAGI++: Head-Assisted Gaze Imputation and Generation](https://mlsanity.com/paper/2511.02468/) (2025)

## Abstract (arXiv)

We present ActionDiffusion -- a novel diffusion model for procedure planning in instructional videos that is the first to take temporal inter-dependencies between actions into account in a diffusion model for procedure planning. This approach is in stark contrast to existing methods that fail to exploit the rich information content available in the particular order in which actions are performed. Our method unifies the learning of temporal dependencies between actions and denoising of the action plan in the diffusion process by projecting the action information into the noise space. This is achieved 1) by adding action embeddings in the noise masks in the noise-adding phase and 2) by introducing an attention mechanism in the noise prediction network to learn the correlations between different action steps. We report extensive experiments on three instructional video benchmark datasets (CrossTask, Coin, and NIV) and show that our method outperforms previous state-of-the-art methods on all metrics on CrossTask and NIV and all metrics except accuracy on Coin dataset. We show that by adding action embeddings into the noise mask the diffusion model can better learn action temporal dependencies and increase the performances on procedure planning.