# Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases

arXiv: https://arxiv.org/abs/2410.15728 · HTML: https://mlsanity.com/paper/2410.15728/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 59 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Builds on (most cited first, 30 of 44)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [CLEVRER: CoLlision Events for Video REpresentation and Reasoning](https://mlsanity.com/paper/1910.01442/) (2019)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [Multi-Object Representation Learning with Iterative Variational Inference](https://mlsanity.com/paper/1903.00450/) (2019)
- [Learning Blind Video Temporal Consistency](https://mlsanity.com/paper/1808.00449/) (2018)
- [Conditional Object-Centric Learning from Video](https://mlsanity.com/paper/2111.12594/) (2021)
- [On the Binding Problem in Artificial Neural Networks](https://mlsanity.com/paper/2012.05208/) (2020)
- [Bridging the Gap to Real-World Object-Centric Learning](https://mlsanity.com/paper/2209.14860/) (2022)
- [Recurrent Independent Mechanisms](https://mlsanity.com/paper/1909.10893/) (2019)
- [Contrastive Learning of Structured World Models](https://mlsanity.com/paper/1911.12247/) (2019)
- [SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos](https://mlsanity.com/paper/2206.07764/) (2022)
- [Physion: Evaluating Physical Prediction from Vision in Humans and Machines](https://mlsanity.com/paper/2106.08261/) (2021)
- [Illiterate DALL-E Learns to Compose](https://mlsanity.com/paper/2110.11405/) (2021)
- [SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models](https://mlsanity.com/paper/2210.05861/) (2022)
- [Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos](https://mlsanity.com/paper/2205.14065/) (2022)
- [Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs](https://mlsanity.com/paper/1901.07017/) (2019)
- [Entity Abstraction in Visual Model-Based Reinforcement Learning](https://mlsanity.com/paper/1910.12827/) (2019)
- [SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models](https://mlsanity.com/paper/2305.11281/) (2023)
- [Generalization and Robustness Implications in Object-Centric Learning](https://mlsanity.com/paper/2107.00637/) (2021)
- [Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities](https://mlsanity.com/paper/2306.04829/) (2023)
- [Neural Production Systems: Learning Rule-Governed Visual Dynamics](https://mlsanity.com/paper/2103.01937/) (2021)
- [FAENet: Frame Averaging Equivariant GNN for Materials Modeling](https://mlsanity.com/paper/2305.05577/) (2023)
- [Improving Generative Imagination in Object-Centric World Models](https://mlsanity.com/paper/2010.02054/) (2020)
- [Improving Object-centric Learning with Query Optimization](https://mlsanity.com/paper/2210.08990/) (2022)
- [Attention over learned object embeddings enables complex visual reasoning](https://mlsanity.com/paper/2012.08508/) (2020)

## Built on by (most cited first, 5 of 5)

- [Temporally Consistent Object-Centric Learning by Contrasting Slots](https://mlsanity.com/paper/2412.14295/) (2024)
- [PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning](https://mlsanity.com/paper/2502.07600/) (2025)
- [Evaluation of Vision-LLMs in Surveillance Video](https://mlsanity.com/paper/2510.23190/) (2025)
- [Rethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to Correspondence](https://mlsanity.com/paper/2605.03650/) (2026)
- [Grounding Foundational Vision Models with 3D Human Poses for Robust Action Recognition](https://mlsanity.com/paper/2511.05622/) (2025)

## Abstract (arXiv)

Unsupervised object-centric learning from videos is a promising approach towards learning compositional representations that can be applied to various downstream tasks, such as prediction and reasoning. Recently, it was shown that pretrained Vision Transformers (ViTs) can be useful to learn object-centric representations on real-world video datasets. However, while these approaches succeed at extracting objects from the scenes, the slot-based representations fail to maintain temporal consistency across consecutive frames in a video, i.e. the mapping of objects to slots changes across the video. To address this, we introduce Conditional Autoregressive Slot Attention (CA-SA), a framework that enhances the temporal consistency of extracted object-centric representations in video-centric vision tasks. Leveraging an autoregressive prior network to condition representations on previous timesteps and a novel consistency loss function, CA-SA predicts future slot representations and imposes consistency across frames. We present qualitative and quantitative results showing that our proposed method outperforms the considered baselines on downstream tasks, such as video prediction and visual question-answering tasks.