# R-SQAIR: Relational Sequential Attend, Infer, Repeat

arXiv: https://arxiv.org/abs/1910.05231 · HTML: https://mlsanity.com/paper/1910.05231/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Oct 2019.

## Built on by (most cited first, 21 of 21)

- [Conditional Object-Centric Learning from Video](https://mlsanity.com/paper/2111.12594/) (2021)
- [Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos](https://mlsanity.com/paper/2205.14065/) (2022)
- [Unsupervised Learning of Compositional Energy Concepts](https://mlsanity.com/paper/2111.03042/) (2021)
- [Neural Systematic Binder](https://mlsanity.com/paper/2211.01177/) (2022)
- [Compositional Scene Representation Learning via Reconstruction: A Survey](https://mlsanity.com/paper/2202.07135/) (2022)
- [Systematic Visual Reasoning through Object-Centric Relational Abstraction](https://mlsanity.com/paper/2306.02500/) (2023)
- [Unsupervised Image Representation Learning with Deep Latent Particles](https://mlsanity.com/paper/2205.15821/) (2022)
- [DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles](https://mlsanity.com/paper/2306.05957/) (2023)
- [Contrastive Training of Complex-Valued Autoencoders for Object Discovery](https://mlsanity.com/paper/2305.15001/) (2023)
- [Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling](https://mlsanity.com/paper/2603.04553/) (2026)
- [Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter](https://mlsanity.com/paper/2208.03374/) (2022)
- [Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints](https://mlsanity.com/paper/2112.03568/) (2021)
- [Object-Centric Learning with Slot Mixture Module](https://mlsanity.com/paper/2311.04640/) (2023)
- [GATSBI: Generative Agent-centric Spatio-temporal Object Interaction](https://mlsanity.com/paper/2104.04275/) (2021)
- [Reasoning-Enhanced Object-Centric Learning for Videos](https://mlsanity.com/paper/2403.15245/) (2024)
- [SlotPi: Physics-informed Object-centric Reasoning Models](https://mlsanity.com/paper/2506.10778/) (2025)
- [Unsupervised Object-Centric Learning from Multiple Unspecified Viewpoints](https://mlsanity.com/paper/2401.01922/) (2024)
- [Patch-based Object-centric Transformers for Efficient Video Generation](https://mlsanity.com/paper/2206.04003/) (2022)
- [Unsupervised Musical Object Discovery from Audio](https://mlsanity.com/paper/2311.07534/) (2023)
- [3D-DLP: Self-Supervised 3D Object-Centric Scene Representation Learning](https://mlsanity.com/paper/2606.19451/) (2026)
- [LinSlot: Exploiting Linear Representation hypothesis for unsupervised attribute discovery from slot based object representation](https://mlsanity.com/paper/2610.10722/) (2026)

## Abstract (arXiv)

Traditional sequential multi-object attention models rely on a recurrent mechanism to infer object relations. We propose a relational extension (R-SQAIR) of one such attention model (SQAIR) by endowing it with a module with strong relational inductive bias that computes in parallel pairwise interactions between inferred objects. Two recently proposed relational modules are studied on tasks of unsupervised learning from videos. We demonstrate gains over sequential relational mechanisms, also in terms of combinatorial generalization.