{"total":108,"rows":[{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248,"area":"wm"},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220,"area":null},{"id":"2206.07764","title":"SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos","created":"2022-06-15","cited_by_count":166,"area":null},{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147,"area":null},{"id":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147,"area":null},{"id":"2205.14065","title":"Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos","created":"2022-05-27","cited_by_count":139,"area":null},{"id":"2104.09958","title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","created":"2021-04-20","cited_by_count":109,"area":null},{"id":"2303.10834","title":"Object-Centric Slot Diffusion","created":"2023-03-20","cited_by_count":90,"area":"diffusion"},{"id":"2305.11281","title":"SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models","created":"2023-05-18","cited_by_count":85,"area":"diffusion"},{"id":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81,"area":null},{"id":"2306.04829","title":"Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities","created":"2023-06-07","cited_by_count":78,"area":null},{"id":"2106.03849","title":"SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition","created":"2021-06-07","cited_by_count":69,"area":null},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60,"area":null},{"id":"2111.06349","title":"Unsupervised Part Discovery from Contrastive Reconstruction","created":"2021-11-11","cited_by_count":57,"area":null},{"id":"2302.04973","title":"Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames","created":"2023-02-09","cited_by_count":51,"area":null},{"id":"2104.11221","title":"Opening up Open-World Tracking","created":"2021-04-22","cited_by_count":50,"area":null},{"id":"2302.04419","title":"An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning","created":"2023-02-09","cited_by_count":49,"area":null},{"id":"2310.06907","title":"Self-supervised Object-Centric Learning for Videos","created":"2023-10-10","cited_by_count":49,"area":null},{"id":"2203.10159","title":"Discovering Objects that Can Move","created":"2022-03-18","cited_by_count":44,"area":null},{"id":"2210.11287","title":"MoCoDA: Model-based Counterfactual Data Augmentation","created":"2022-10-20","cited_by_count":44,"area":"offlinerl"},{"id":"2205.07844","title":"Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion","created":"2022-05-16","cited_by_count":42,"area":null},{"id":"2211.01177","title":"Neural Systematic Binder","created":"2022-11-02","cited_by_count":37,"area":null},{"id":"2104.14553","title":"MarioNette: Self-Supervised Sprite Learning","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2110.15245","title":"From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence","created":"2021-10-28","cited_by_count":35,"area":null},{"id":"2202.04178","title":"VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming","created":"2022-02-07","cited_by_count":31,"area":"lr"},{"id":"2206.11403","title":"Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation","created":"2022-06-22","cited_by_count":31,"area":"wm"},{"id":"2412.14295","title":"Temporally Consistent Object-Centric Learning by Contrasting Slots","created":"2024-12-18","cited_by_count":31,"area":null},{"id":"2110.06562","title":"Unsupervised Object Learning via Common Fate","created":"2021-10-13","cited_by_count":29,"area":null},{"id":"2202.07135","title":"Compositional Scene Representation Learning via Reconstruction: A Survey","created":"2022-02-15","cited_by_count":27,"area":null},{"id":"2404.01220","title":"Entity-Centric Reinforcement Learning for Object Manipulation from Pixels","created":"2024-04-01","cited_by_count":27,"area":"deeprl"},{"id":"2210.04458","title":"OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Clouds","created":"2022-10-10","cited_by_count":25,"area":null},{"id":"2303.15555","title":"Object Discovery from Motion-Guided Tokens","created":"2023-03-27","cited_by_count":25,"area":null},{"id":"2107.09240","title":"Generative Video Transformer: Can Objects be the Words?","created":"2021-07-20","cited_by_count":24,"area":null},{"id":"2311.02007","title":"Towards Unsupervised Object Detection From LiDAR Point Clouds","created":"2023-11-03","cited_by_count":23,"area":null},{"id":"2107.08577","title":"Structured World Belief for Reinforcement Learning in POMDP","created":"2021-07-19","cited_by_count":21,"area":"wm"},{"id":"2306.06997","title":"Slot-VAE: Object-Centric Scene Generation with Slot Attention","created":"2023-06-12","cited_by_count":20,"area":null},{"id":"2210.12148","title":"Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns","created":"2022-10-21","cited_by_count":19,"area":null},{"id":"2302.11850","title":"Object-Centric Video Prediction via Decoupling of Object Dynamics and Interactions","created":"2023-02-23","cited_by_count":19,"area":null},{"id":"2306.05957","title":"DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles","created":"2023-06-09","cited_by_count":19,"area":null},{"id":"2211.09771","title":"Boosting Object Representation Learning via Motion and Object Continuity","created":"2022-11-16","cited_by_count":17,"area":null},{"id":"2303.17842","title":"Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning","created":"2023-03-31","cited_by_count":17,"area":null},{"id":"2406.12272","title":"Slot State Space Models","created":"2024-06-18","cited_by_count":17,"area":"ssm"},{"id":"2109.04150","title":"Self-supervised Reinforcement Learning with Independently Controllable Subgoals","created":"2021-09-09","cited_by_count":16,"area":null},{"id":"2307.08027","title":"Multi-Object Discovery by Low-Dimensional Object Motion","created":"2023-07-16","cited_by_count":16,"area":null},{"id":"2309.00233","title":"Object-Centric Multiple Object Tracking","created":"2023-09-01","cited_by_count":15,"area":null},{"id":"2603.04553","title":"Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling","created":"2026-03-04","cited_by_count":15,"area":"wm"},{"id":"2210.00221","title":"Motion-inductive Self-supervised Object Discovery in Videos","created":"2022-10-01","cited_by_count":14,"area":null},{"id":"2210.12733","title":"Self-supervised Amodal Video Object Segmentation","created":"2022-10-23","cited_by_count":14,"area":null},{"id":"2407.15589","title":"Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models","created":"2024-07-22","cited_by_count":14,"area":null},{"id":"2107.08881","title":"Reasoning-Modulated Representations","created":"2021-07-19","cited_by_count":13,"area":null},{"id":"2204.08479","title":"Inductive Biases for Object-Centric Representations in the Presence of Complex Textures","created":"2022-04-18","cited_by_count":13,"area":null},{"id":"2405.00646","title":"Learning to Compose: Improving Object Centric Learning by Injecting Compositionality","created":"2024-05-01","cited_by_count":13,"area":"lr"},{"id":"2501.15878","title":"Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation","created":"2025-01-27","cited_by_count":13,"area":"diffusion"},{"id":"2402.07376","title":"Unsupervised Discovery of Object-Centric Neural Fields","created":"2024-02-12","cited_by_count":12,"area":null},{"id":"2405.18917","title":"Causal Action Influence Aware Counterfactual Data Augmentation","created":"2024-05-29","cited_by_count":12,"area":null},{"id":"2508.01345","title":"Predicting Video Slot Attention Queries from Random Slot-Feature Pairs","created":"2025-08-02","cited_by_count":12,"area":null},{"id":"2112.03568","title":"Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints","created":"2021-12-07","cited_by_count":11,"area":null},{"id":"2205.13271","title":"Unsupervised Multi-object Segmentation Using Attention and Soft-argmax","created":"2022-05-26","cited_by_count":11,"area":null},{"id":"2312.11463","title":"Appearance-Based Refinement for Object-Centric Motion Segmentation","created":"2023-12-18","cited_by_count":11,"area":null},{"id":"2411.06890","title":"SPARTAN: A Sparse Transformer World Model Attending to What Matters","created":"2024-11-11","cited_by_count":10,"area":"wm"},{"id":"2503.02143","title":"Four Principles for Physically Interpretable World Models","created":"2025-03-04","cited_by_count":10,"area":"wm"},{"id":"2402.01203","title":"Neural Language of Thought Models","created":"2024-02-02","cited_by_count":9,"area":"lr"},{"id":"2104.04275","title":"GATSBI: Generative Agent-centric Spatio-temporal Object Interaction","created":"2021-04-09","cited_by_count":8,"area":null},{"id":"2305.19550","title":"Spotlight Attention: Robust Object-Centric Learning With a Spatial Locality Prior","created":"2023-05-31","cited_by_count":8,"area":null},{"id":"2112.08001","title":"Autoencoder-based background reconstruction and foreground segmentation with background noise estimation","created":"2021-12-15","cited_by_count":7,"area":null},{"id":"2403.15245","title":"Reasoning-Enhanced Object-Centric Learning for Videos","created":"2024-03-22","cited_by_count":7,"area":"lr"},{"id":"2602.02722","title":"Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion","created":"2026-02-02","cited_by_count":7,"area":"deeprl"},{"id":"2104.03424","title":"Track, Check, Repeat: An EM Approach to Unsupervised Tracking","created":"2021-04-07","cited_by_count":6,"area":null},{"id":"2106.09051","title":"Unsupervised Video Prediction from a Single Frame by Estimating 3D Dynamic Scene Structure","created":"2021-06-16","cited_by_count":6,"area":null},{"id":"2210.07802","title":"Object-Category Aware Reinforcement Learning","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2311.09064","title":"Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models","created":"2023-11-15","cited_by_count":6,"area":"wm"},{"id":"2603.14401","title":"OCRA: Object-Centric Learning with 3D and Tactile Priors for Human-to-Robot Action Transfer","created":"2026-03-15","cited_by_count":6,"area":null},{"id":"2307.10846","title":"Goal-Conditioned Reinforcement Learning with Disentanglement-based Reachability Planning","created":"2023-07-20","cited_by_count":5,"area":null},{"id":"2506.10778","title":"SlotPi: Physics-informed Object-centric Reasoning Models","created":"2025-06-12","cited_by_count":5,"area":"lr"},{"id":"2306.07307","title":"Online Prototype Alignment for Few-shot Policy Transfer","created":"2023-06-12","cited_by_count":4,"area":null},{"id":"2310.10372","title":"Learning Object Permanence from Videos via Latent Imaginations","created":"2023-10-16","cited_by_count":4,"area":null},{"id":"2310.17178","title":"Relational Object-Centric Actor-Critic","created":"2023-10-26","cited_by_count":4,"area":"wm"},{"id":"2401.01922","title":"Unsupervised Object-Centric Learning from Multiple Unspecified Viewpoints","created":"2024-01-03","cited_by_count":4,"area":null},{"id":"2401.10148","title":"Explicitly Disentangled Representations in Object-Centric Learning","created":"2024-01-18","cited_by_count":4,"area":null},{"id":"2404.15109","title":"Compete and Compose: Learning Independent Mechanisms for Modular World Models","created":"2024-04-23","cited_by_count":4,"area":"wm"},{"id":"2411.00868","title":"Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2501.14174","title":"Dreamweaver: Learning Compositional World Models from Pixels","created":"2025-01-24","cited_by_count":4,"area":"wm"},{"id":"2509.02545","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","created":"2025-09-02","cited_by_count":4,"area":null},{"id":"2206.04003","title":"Patch-based Object-centric Transformers for Efficient Video Generation","created":"2022-06-08","cited_by_count":3,"area":null},{"id":"2209.09115","title":"Compositional Law Parsing with Latent Random Functions","created":"2022-09-15","cited_by_count":3,"area":null},{"id":"2211.06027","title":"Dance of SNN and ANN: Solving binding problem by combining spike timing and reconstructive attention","created":"2022-11-11","cited_by_count":3,"area":null},{"id":"2301.08951","title":"Time-Conditioned Generative Modeling of Object-Centric Representations for Video Decomposition and Prediction","created":"2023-01-21","cited_by_count":3,"area":null},{"id":"2311.02633","title":"The Background Also Matters: Background-Aware Motion-Guided Objects Discovery","created":"2023-11-05","cited_by_count":3,"area":null},{"id":"2603.22758","title":"Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2110.00547","title":"Self-Supervised Decomposition, Disentanglement and Prediction of Video Sequences while Interpreting Dynamics: A Koopman Perspective","created":"2021-10-01","cited_by_count":2,"area":null},{"id":"2206.03591","title":"ObPose: Leveraging Pose for Object-Centric Scene Inference and Generation in 3D","created":"2022-06-07","cited_by_count":2,"area":null},{"id":"2302.03288","title":"Object-Centric Scene Representations using Active Inference","created":"2023-02-07","cited_by_count":2,"area":null},{"id":"2401.11110","title":"VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE","created":"2024-01-20","cited_by_count":2,"area":null},{"id":"2402.17077","title":"Parallelized Spatiotemporal Binding","created":"2024-02-26","cited_by_count":2,"area":null},{"id":"2411.17438","title":"Object-centric proto-symbolic behavioural reasoning from pixels","created":"2024-11-26","cited_by_count":2,"area":null},{"id":"2606.12601","title":"Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learning","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2104.06645","title":"Jointly Learning Truth-Conditional Denotations and Groundings using Parallel Attention","created":"2021-04-14","cited_by_count":1,"area":null},{"id":"2112.07954","title":"Object Pursuit: Building a Space of Objects via Discriminative Weight Generation","created":"2021-12-15","cited_by_count":1,"area":null},{"id":"2209.10471","title":"Sample, Crop, Track: Self-Supervised Mobile 3D Object Detection for Urban Driving LiDAR","created":"2022-09-21","cited_by_count":1,"area":null},{"id":"2407.03216","title":"Learning Disentangled Representation in Object-Centric Models for Visual Dynamics Prediction via Transformers","created":"2024-07-03","cited_by_count":1,"area":null}],"next_cursor":"100"}