{"total":199,"rows":[{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381,"area":null},{"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":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147,"area":null},{"id":"2203.16437","title":"Weakly supervised causal representation learning","created":"2022-03-30","cited_by_count":140,"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":"2206.06922","title":"Object Scene Representation Transformer","created":"2022-06-14","cited_by_count":90,"area":null},{"id":"2203.08777","title":"Object discovery and representation networks","created":"2022-03-16","cited_by_count":80,"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":"2205.15288","title":"Self-Supervised Visual Representation Learning with Semantic Grouping","created":"2022-05-30","cited_by_count":70,"area":null},{"id":"2307.05596","title":"Compositional Generalization from First Principles","created":"2023-07-10","cited_by_count":64,"area":null},{"id":"2207.02206","title":"Segmenting Moving Objects via an Object-Centric Layered Representation","created":"2022-07-05","cited_by_count":63,"area":null},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60,"area":null},{"id":"2207.05027","title":"Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations","created":"2022-07-11","cited_by_count":54,"area":null},{"id":"2206.06169","title":"Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems","created":"2022-06-13","cited_by_count":51,"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":"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":"2312.00648","title":"SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers","created":"2023-12-01","cited_by_count":49,"area":null},{"id":"2207.00787","title":"Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation","created":"2022-07-02","cited_by_count":46,"area":null},{"id":"2305.14229","title":"Provably Learning Object-Centric Representations","created":"2023-05-23","cited_by_count":45,"area":null},{"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":"2204.02075","title":"Complex-Valued Autoencoders for Object Discovery","created":"2022-04-05","cited_by_count":40,"area":null},{"id":"2211.01177","title":"Neural Systematic Binder","created":"2022-11-02","cited_by_count":37,"area":null},{"id":"2308.11796","title":"Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations","created":"2023-08-22","cited_by_count":35,"area":null},{"id":"2406.09196","title":"Adaptive Slot Attention: Object Discovery with Dynamic Slot Number","created":"2024-06-13","cited_by_count":34,"area":null},{"id":"2412.14295","title":"Temporally Consistent Object-Centric Learning by Contrasting Slots","created":"2024-12-18","cited_by_count":31,"area":null},{"id":"2306.08649","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","created":"2023-06-14","cited_by_count":30,"area":null},{"id":"2412.15212","title":"Scaling 4D Representations","created":"2024-12-19","cited_by_count":30,"area":null},{"id":"2306.00600","title":"Rotating Features for Object Discovery","created":"2023-06-01","cited_by_count":29,"area":null},{"id":"2205.03923","title":"Unsupervised Discovery and Composition of Object Light Fields","created":"2022-05-08","cited_by_count":28,"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":"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":"2412.07770","title":"From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos","created":"2024-12-10","cited_by_count":23,"area":null},{"id":"2205.06333","title":"Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations","created":"2022-05-12","cited_by_count":21,"area":null},{"id":"2205.13349","title":"Learning What and Where: Disentangling Location and Identity Tracking Without Supervision","created":"2022-05-26","cited_by_count":21,"area":null},{"id":"2303.15904","title":"Mask-Free Video Instance Segmentation","created":"2023-03-28","cited_by_count":20,"area":null},{"id":"2306.06997","title":"Slot-VAE: Object-Centric Scene Generation with Slot Attention","created":"2023-06-12","cited_by_count":20,"area":null},{"id":"2308.09951","title":"Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos","created":"2023-08-19","cited_by_count":20,"area":null},{"id":"2201.13388","title":"Compositional Multi-Object Reinforcement Learning with Linear Relation Networks","created":"2022-01-31","cited_by_count":19,"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":"2510.24709","title":"Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?","created":"2025-10-28","cited_by_count":19,"area":null},{"id":"2207.11232","title":"Neural Groundplans: Persistent Neural Scene Representations from a Single Image","created":"2022-07-22","cited_by_count":17,"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":"2307.09437","title":"Grounded Object Centric Learning","created":"2023-07-18","cited_by_count":17,"area":null},{"id":"2312.05359","title":"Learning 3D Particle-based Simulators from RGB-D Videos","created":"2023-12-08","cited_by_count":17,"area":null},{"id":"2301.13197","title":"Unlocking Slot Attention by Changing Optimal Transport Costs","created":"2023-01-30","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":"2404.13474","title":"Composing Pre-Trained Object-Centric Representations for Robotics From \"What\" and \"Where\" Foundation Models","created":"2024-04-20","cited_by_count":16,"area":null},{"id":"2205.08515","title":"Unsupervised Segmentation in Real-World Images via Spelke Object Inference","created":"2022-05-17","cited_by_count":15,"area":null},{"id":"2210.05972","title":"Unsupervised Learning of Equivariant Structure from Sequences","created":"2022-10-12","cited_by_count":15,"area":null},{"id":"2308.02840","title":"Learning Unified Decompositional and Compositional NeRF for Editable Novel View Synthesis","created":"2023-08-05","cited_by_count":15,"area":null},{"id":"2309.00233","title":"Object-Centric Multiple Object Tracking","created":"2023-09-01","cited_by_count":15,"area":null},{"id":"2203.13573","title":"Unsupervised Learning of Temporal Abstractions with Slot-based Transformers","created":"2022-03-25","cited_by_count":14,"area":null},{"id":"2210.00221","title":"Motion-inductive Self-supervised Object Discovery in Videos","created":"2022-10-01","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":"2407.17929","title":"GLASS: Guided Latent Slot Diffusion for Object-Centric Learning","created":"2024-07-25","cited_by_count":14,"area":null},{"id":"2502.07600","title":"PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning","created":"2025-02-11","cited_by_count":14,"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":"2208.03374","title":"Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter","created":"2022-08-05","cited_by_count":13,"area":null},{"id":"2303.01526","title":"Semantic Attention Flow Fields for Monocular Dynamic Scene Decomposition","created":"2023-03-02","cited_by_count":13,"area":null},{"id":"2311.17948","title":"Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes","created":"2023-11-29","cited_by_count":12,"area":null},{"id":"2408.06697","title":"SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields","created":"2024-08-13","cited_by_count":12,"area":null},{"id":"2503.21747","title":"CTRL-O: Language-Controllable Object-Centric Visual Representation Learning","created":"2025-03-27","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":"2203.05997","title":"Towards Self-Supervised Learning of Global and Object-Centric Representations","created":"2022-03-11","cited_by_count":11,"area":null},{"id":"2212.06795","title":"GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation","created":"2022-12-13","cited_by_count":11,"area":null},{"id":"2311.04640","title":"Object-Centric Learning with Slot Mixture Module","created":"2023-11-08","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":"2411.05927","title":"Moving Off-the-Grid: Scene-Grounded Video Representations","created":"2024-11-08","cited_by_count":11,"area":null},{"id":"2502.20263","title":"Vector-Quantized Vision Foundation Models for Object-Centric Learning","created":"2025-02-27","cited_by_count":11,"area":null},{"id":"2504.07092","title":"Are We Done with Object-Centric Learning?","created":"2025-04-09","cited_by_count":11,"area":null},{"id":"2505.20772","title":"MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning","created":"2025-05-27","cited_by_count":11,"area":null},{"id":"2206.02664","title":"Learning with Capsules: A Survey","created":"2022-06-06","cited_by_count":10,"area":null},{"id":"2311.17893","title":"Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation","created":"2023-11-29","cited_by_count":10,"area":null},{"id":"2403.17410","title":"On permutation-invariant neural networks","created":"2024-03-26","cited_by_count":10,"area":null},{"id":"2406.07141","title":"Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention","created":"2024-06-11","cited_by_count":9,"area":null},{"id":"2502.09680","title":"Object-Centric Latent Action Learning","created":"2025-02-13","cited_by_count":9,"area":null},{"id":"2305.18890","title":"Sensitivity of Slot-Based Object-Centric Models to their Number of Slots","created":"2023-05-30","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":"2312.10728","title":"Benchmarks for Physical Reasoning AI","created":"2023-12-17","cited_by_count":8,"area":null},{"id":"2402.18277","title":"Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing","created":"2024-02-28","cited_by_count":8,"area":null},{"id":"2405.17283","title":"Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery","created":"2024-05-27","cited_by_count":8,"area":null},{"id":"2407.06871","title":"Rethinking Image-to-Video Adaptation: An Object-centric Perspective","created":"2024-07-09","cited_by_count":8,"area":null},{"id":"2210.05519","title":"Robust and Controllable Object-Centric Learning through Energy-based Models","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2301.04101","title":"Neural Radiance Field Codebooks","created":"2023-01-10","cited_by_count":7,"area":null},{"id":"2303.05323","title":"Controllable Video Generation by Learning the Underlying Dynamical System with Neural ODE","created":"2023-03-09","cited_by_count":7,"area":null},{"id":"2306.02204","title":"Cycle Consistency Driven Object Discovery","created":"2023-06-03","cited_by_count":7,"area":null},{"id":"2410.01539","title":"Multi-Scale Fusion for Object Representation","created":"2024-10-02","cited_by_count":7,"area":null},{"id":"2210.02159","title":"Differentiable Mathematical Programming for Object-Centric Representation Learning","created":"2022-10-05","cited_by_count":6,"area":null},{"id":"2303.11373","title":"Neural Constraint Satisfaction: Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement","created":"2023-03-20","cited_by_count":6,"area":null},{"id":"2308.14899","title":"RobustCLEVR: A Benchmark and Framework for Evaluating Robustness in Object-centric Learning","created":"2023-08-28","cited_by_count":6,"area":null},{"id":"2508.05417","title":"Smoothing Slot Attention Iterations and Recurrences","created":"2025-08-07","cited_by_count":6,"area":null},{"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":"2605.31033","title":"SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation","created":"2026-05-29","cited_by_count":6,"area":null},{"id":"2206.08460","title":"TUSK: Task-Agnostic Unsupervised Keypoints","created":"2022-06-16","cited_by_count":5,"area":null}],"next_cursor":"100"}