{"total":118,"rows":[{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220,"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":"2206.06922","title":"Object Scene Representation Transformer","created":"2022-06-14","cited_by_count":90,"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":"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":"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":"2310.05327","title":"Provable Compositional Generalization for Object-Centric Learning","created":"2023-10-09","cited_by_count":41,"area":null},{"id":"2204.02075","title":"Complex-Valued Autoencoders for Object Discovery","created":"2022-04-05","cited_by_count":40,"area":null},{"id":"2410.13821","title":"Artificial Kuramoto Oscillatory Neurons","created":"2024-10-17","cited_by_count":38,"area":null},{"id":"2211.01177","title":"Neural Systematic Binder","created":"2022-11-02","cited_by_count":37,"area":null},{"id":"2406.19370","title":"Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space","created":"2024-06-27","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":"2306.08649","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","created":"2023-06-14","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":"2303.15555","title":"Object Discovery from Motion-Guided Tokens","created":"2023-03-27","cited_by_count":25,"area":null},{"id":"2308.15512","title":"Shatter and Gather: Learning Referring Image Segmentation with Text Supervision","created":"2023-08-29","cited_by_count":25,"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":"2411.07784","title":"Interaction Asymmetry: A General Principle for Learning Composable Abstractions","created":"2024-11-12","cited_by_count":20,"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":"2408.09162","title":"Zero-Shot Object-Centric Representation Learning","created":"2024-08-17","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":"2307.09437","title":"Grounded Object Centric Learning","created":"2023-07-18","cited_by_count":17,"area":null},{"id":"2309.00233","title":"Object-Centric Multiple Object Tracking","created":"2023-09-01","cited_by_count":15,"area":null},{"id":"2308.16316","title":"Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art","created":"2023-08-30","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":"2307.03376","title":"Weakly-supervised Contrastive Learning for Unsupervised Object Discovery","created":"2023-07-07","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":"2508.01345","title":"Predicting Video Slot Attention Queries from Random Slot-Feature Pairs","created":"2025-08-02","cited_by_count":12,"area":null},{"id":"2311.04640","title":"Object-Centric Learning with Slot Mixture Module","created":"2023-11-08","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":"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":"2406.07141","title":"Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention","created":"2024-06-11","cited_by_count":9,"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":"2306.00763","title":"Learning Disentangled Prompts for Compositional Image Synthesis","created":"2023-06-01","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":"2402.13088","title":"Slot-VLM: SlowFast Slots for Video-Language Modeling","created":"2024-02-20","cited_by_count":8,"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":"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":"2505.11563","title":"Object-Centric Representations Improve Policy Generalization in Robot Manipulation","created":"2025-05-16","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":"2402.05627","title":"Binding Dynamics in Rotating Features","created":"2024-02-08","cited_by_count":5,"area":null},{"id":"2410.15728","title":"Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2411.02299","title":"Grouped Discrete Representation for Object-Centric Learning","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2602.03390","title":"From Vicious to Virtuous Cycles: Synergistic Representation Learning for Unsupervised Video Object-Centric Learning","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2305.17262","title":"Im-Promptu: In-Context Composition from Image Prompts","created":"2023-05-26","cited_by_count":4,"area":null},{"id":"2312.04947","title":"Benchmarking and Analysis of Unsupervised Object Segmentation from Real-world Single Images","created":"2023-12-08","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":"2506.01778","title":"unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2306.02577","title":"Exploring the Role of the Bottleneck in Slot-Based Models Through Covariance Regularization","created":"2023-06-05","cited_by_count":3,"area":null},{"id":"2404.18423","title":"OCK: Unsupervised Dynamic Video Prediction with Object-Centric Kinematics","created":"2024-04-29","cited_by_count":3,"area":null},{"id":"2405.10598","title":"Top-Down Guidance for Learning Object-Centric Representations","created":"2024-05-17","cited_by_count":3,"area":null},{"id":"2410.18809","title":"Learning Global Object-Centric Representations via Disentangled Slot Attention","created":"2024-10-24","cited_by_count":3,"area":null},{"id":"2504.04490","title":"Learning Conditionally Independent Transformations using Normal Subgroups in Group Theory","created":"2025-04-06","cited_by_count":3,"area":null},{"id":"2506.19408","title":"Is an object-centric representation beneficial for robotic manipulation ?","created":"2025-06-24","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":"2306.09682","title":"OCTScenes: A Versatile Real-World Dataset of Tabletop Scenes for Object-Centric Learning","created":"2023-06-16","cited_by_count":2,"area":null},{"id":"2310.08929","title":"Leveraging Image Augmentation for Object Manipulation: Towards Interpretable Controllability in Object-Centric Learning","created":"2023-10-13","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":"2403.07887","title":"Neural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations","created":"2024-02-02","cited_by_count":2,"area":null},{"id":"2407.01726","title":"Grouped Discrete Representation Guides Object-Centric Learning","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2407.02386","title":"OpenSlot: Mixed Open-Set Recognition with Object-Centric Learning","created":"2024-07-02","cited_by_count":2,"area":null},{"id":"2407.04170","title":"Attention Normalization Impacts Cardinality Generalization in Slot Attention","created":"2024-07-04","cited_by_count":2,"area":null},{"id":"2412.18743","title":"Successes and Limitations of Object-centric Models at Compositional Generalisation","created":"2024-12-25","cited_by_count":2,"area":null},{"id":"2412.19847","title":"Symbolic Disentangled Representations for Images","created":"2024-12-25","cited_by_count":2,"area":null},{"id":"2503.09679","title":"DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2506.03798","title":"CoLa: Chinese Character Decomposition with Compositional Latent Components","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2510.23956","title":"Neural USD: An object-centric framework for iterative editing and control","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2606.23436","title":"Rethinking Object-Centric Representations for Video Dynamics Modeling","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2206.01370","title":"Towards Improving the Generation Quality of Autoregressive Slot VAEs","created":"2022-06-03","cited_by_count":1,"area":null},{"id":"2210.14139","title":"Learning Explicit Object-Centric Representations with Vision Transformers","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2304.01430","title":"Divided Attention: Unsupervised Multi-Object Discovery with Contextually Separated Slots","created":"2023-04-04","cited_by_count":1,"area":null},{"id":"2403.17664","title":"DiffFAE: Advancing High-fidelity One-shot Facial Appearance Editing with Space-sensitive Customization and Semantic Preservation","created":"2024-03-26","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},{"id":"2409.03553","title":"Organized Grouped Discrete Representation for Object-Centric Learning","created":"2024-09-05","cited_by_count":1,"area":null},{"id":"2411.00402","title":"Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2504.12197","title":"Beyond Patches: Mining Interpretable Part-Prototypes for Explainable AI","created":"2025-04-16","cited_by_count":1,"area":null},{"id":"2505.02071","title":"Hierarchical Compact Clustering Attention (COCA) for Unsupervised Object-Centric Learning","created":"2025-05-04","cited_by_count":1,"area":null},{"id":"2510.21402","title":"Disentangled Representation Learning via Modular Compositional Bias","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2602.07544","title":"MUFASA: A Multi-Layer Framework for Slot Attention","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2603.14022","title":"A Hyperbolic Perspective on Hierarchical Structure in Object-Centric Scene Representations","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2606.19451","title":"3D-DLP: Self-Supervised 3D Object-Centric Scene Representation Learning","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2608.01103","title":"SSR: Similarity-Shift Refinement for Training-Free Object-Centric Masks","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2209.15404","title":"Entropy-driven Unsupervised Keypoint Representation Learning in Videos","created":"2022-09-30","cited_by_count":0,"area":null},{"id":"2503.09867","title":"Oh-A-DINO: Understanding and Enhancing Attribute-Level Information in Self-Supervised Object-Centric Representations","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2505.09716","title":"Disassociating performance from compositional feature learning","created":"2025-05-14","cited_by_count":0,"area":null},{"id":"2506.07806","title":"Identifiable Object Representations under Spatial Ambiguities","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2507.20855","title":"Compositional Video Synthesis by Temporal Object-Centric Learning","created":"2025-07-28","cited_by_count":0,"area":null}],"next_cursor":"100"}