# Rethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to Correspondence

arXiv: https://arxiv.org/abs/2605.03650 · HTML: https://mlsanity.com/paper/2605.03650/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 32 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Kubric: A scalable dataset generator](https://mlsanity.com/paper/2203.03570/) (2022)
- [Conditional Object-Centric Learning from Video](https://mlsanity.com/paper/2111.12594/) (2021)
- [SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos](https://mlsanity.com/paper/2206.07764/) (2022)
- [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)
- [SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models](https://mlsanity.com/paper/2305.11281/) (2023)
- [Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities](https://mlsanity.com/paper/2306.04829/) (2023)
- [Improving Generative Imagination in Object-Centric World Models](https://mlsanity.com/paper/2010.02054/) (2020)
- [Self-supervised Object-Centric Learning for Videos](https://mlsanity.com/paper/2310.06907/) (2023)
- [Structured Object-Aware Physics Prediction for Video Modeling and Planning](https://mlsanity.com/paper/1910.02425/) (2019)
- [Temporally Consistent Object-Centric Learning by Contrasting Slots](https://mlsanity.com/paper/2412.14295/) (2024)
- [Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos](https://mlsanity.com/paper/2308.09951/) (2023)
- [Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?](https://mlsanity.com/paper/2510.24709/) (2025)
- [Object-Centric Multiple Object Tracking](https://mlsanity.com/paper/2309.00233/) (2023)
- [SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields](https://mlsanity.com/paper/2408.06697/) (2024)
- [CTRL-O: Language-Controllable Object-Centric Visual Representation Learning](https://mlsanity.com/paper/2503.21747/) (2025)
- [Predicting Video Slot Attention Queries from Random Slot-Feature Pairs](https://mlsanity.com/paper/2508.01345/) (2025)
- [MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning](https://mlsanity.com/paper/2505.20772/) (2025)
- [Reasoning-Enhanced Object-Centric Learning for Videos](https://mlsanity.com/paper/2403.15245/) (2024)
- [Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases](https://mlsanity.com/paper/2410.15728/) (2024)

## Built on by (most cited first, 1 of 1)

- [iSEE: Object Permanence Through Self-Supervision](https://mlsanity.com/paper/2610.01201/) (2026)

## Abstract (arXiv)

The de facto approach in video object-centric learning maintains temporal consistency through learned dynamics modules that predict future object representations, called slots. We demonstrate that these predictors function as expensive approximations of discrete correspondence problems. Modern self-supervised vision backbones already encode instance-discriminative features that distinguish objects reliably. Exploiting these features eliminates the need for learned temporal prediction. We introduce Grounded Correspondence, a framework that replaces learned transition functions with deterministic bipartite matching. Slots initialize from salient regions in frozen backbone features. Frame-to-frame identity is maintained through Hungarian matching on slot representations. The approach requires zero learnable parameters for temporal modeling yet achieves competitive performance on MOVi-D, MOVi-E, and YouTube-VIS. Project page: https://magenta-sherbet-85b101.netlify.app/