# Predicting Video Slot Attention Queries from Random Slot-Feature Pairs

arXiv: https://arxiv.org/abs/2508.01345 · HTML: https://mlsanity.com/paper/2508.01345/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 45 references that are in the map.
- First posted on arXiv 2 Aug 2025.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [Conditional Object-Centric Learning from Video](https://mlsanity.com/paper/2111.12594/) (2021)
- [Bridging the Gap to Real-World Object-Centric Learning](https://mlsanity.com/paper/2209.14860/) (2022)
- [SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos](https://mlsanity.com/paper/2206.07764/) (2022)
- [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)
- [Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects](https://mlsanity.com/paper/1806.01794/) (2018)
- [Entity Abstraction in Visual Model-Based Reinforcement Learning](https://mlsanity.com/paper/1910.12827/) (2019)
- [MAST: A Memory-Augmented Self-supervised Tracker](https://mlsanity.com/paper/2002.07793/) (2020)
- [SCALOR: Generative World Models with Scalable Object Representations](https://mlsanity.com/paper/1910.02384/) (2019)
- [Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions](https://mlsanity.com/paper/1802.10353/) (2018)
- [SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models](https://mlsanity.com/paper/2305.11281/) (2023)
- [Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective](https://mlsanity.com/paper/2103.17263/) (2021)
- [Joint-task Self-supervised Learning for Temporal Correspondence](https://mlsanity.com/paper/1909.11895/) (2019)
- [Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities](https://mlsanity.com/paper/2306.04829/) (2023)
- [SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition](https://mlsanity.com/paper/2106.03849/) (2021)
- [Attention over learned object embeddings enables complex visual reasoning](https://mlsanity.com/paper/2012.08508/) (2020)
- [SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers](https://mlsanity.com/paper/2312.00648/) (2023)
- [Temporally Consistent Object-Centric Learning by Contrasting Slots](https://mlsanity.com/paper/2412.14295/) (2024)
- [Unsupervised Deep Representation Learning for Real-Time Tracking](https://mlsanity.com/paper/2007.11984/) (2020)
- [Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learning](https://mlsanity.com/paper/2203.14333/) (2022)
- [Learning What and Where: Disentangling Location and Identity Tracking Without Supervision](https://mlsanity.com/paper/2205.13349/) (2022)
- [Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos](https://mlsanity.com/paper/2308.09951/) (2023)
- [Unsupervised Learning of Accurate Siamese Tracking](https://mlsanity.com/paper/2204.01475/) (2022)
- [Multi-Object Discovery by Low-Dimensional Object Motion](https://mlsanity.com/paper/2307.08027/) (2023)
- [Slot Attention with Re-Initialization and Self-Distillation](https://mlsanity.com/paper/2507.23755/) (2025)
- [Reasoning-Enhanced Object-Centric Learning for Videos](https://mlsanity.com/paper/2403.15245/) (2024)

## Built on by (most cited first, 12 of 12)

- [Smoothing Slot Attention Iterations and Recurrences](https://mlsanity.com/paper/2508.05417/) (2025)
- [Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learning](https://mlsanity.com/paper/2606.12601/) (2026)
- [TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation](https://mlsanity.com/paper/2606.13714/) (2026)
- [Selective Synergistic Learning for Video Object-Centric Learning](https://mlsanity.com/paper/2606.15527/) (2026)
- [Object-Centric Vision Token Pruning for Vision Language Models](https://mlsanity.com/paper/2511.20439/) (2025)
- [Rethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to Correspondence](https://mlsanity.com/paper/2605.03650/) (2026)
- [Cycle Consistency in Video Object-Centric Learning](https://mlsanity.com/paper/2605.30211/) (2026)
- [Internalizing Temporal Consistency in Video Object-Centric Learning without Explicit Regularization](https://mlsanity.com/paper/2605.31508/) (2026)
- [HSA: Hierarchical Slot Attention for Multi-granularity Scene-Decomposition](https://mlsanity.com/paper/2607.08249/) (2026)
- [Semantic Slots for Video Object-Centric Learning](https://mlsanity.com/paper/2608.21636/) (2026)
- [Does Attention-Guided Masking Really Help Object Discovery in Object-Centric Learning?](https://mlsanity.com/paper/2609.15187/) (2026)
- [iSEE: Object Permanence Through Self-Supervision](https://mlsanity.com/paper/2610.01201/) (2026)

## Abstract (arXiv)

Unsupervised video Object-Centric Learning (OCL) is promising as it enables object-level scene representation and understanding as we humans do. Mainstream video OCL methods adopt a recurrent architecture: An aggregator aggregates current video frame into object features, termed slots, under some queries; A transitioner transits current slots to queries for the next frame. This is an effective architecture but all existing implementations both (textiti1) neglect to incorporate next frame features, the most informative source for query prediction, and (textiti2) fail to learn transition dynamics, the knowledge essential for query prediction. To address these issues, we propose Random Slot-Feature pair for learning Query prediction (RandSF.Q): (textitt1) We design a new transitioner to incorporate both slots and features, which provides more information for query prediction; (textitt2) We train the transitioner to predict queries from slot-feature pairs randomly sampled from available recurrences, which drives it to learn transition dynamics. Experiments on scene representation demonstrate that our method surpass existing video OCL methods significantly, e.g., up to 10 points on object discovery, setting new state-of-the-art. Such superiority also benefits downstream tasks like scene understanding. Source Code, Model Checkpoints, Training Logs: https://github.com/Genera1Z/RandSF.Q