{"total":55,"rows":[{"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":"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":"2410.13821","title":"Artificial Kuramoto Oscillatory Neurons","created":"2024-10-17","cited_by_count":38,"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":"2408.09162","title":"Zero-Shot Object-Centric Representation Learning","created":"2024-08-17","cited_by_count":19,"area":null},{"id":"2310.12904","title":"Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey","created":"2023-10-19","cited_by_count":16,"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":"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":"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":"2403.10830","title":"View-Centric Multi-Object Tracking with Homographic Matching in Moving UAV","created":"2024-03-16","cited_by_count":10,"area":null},{"id":"2410.01539","title":"Multi-Scale Fusion for Object Representation","created":"2024-10-02","cited_by_count":7,"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":"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":"2501.12477","title":"Slot-BERT: Self-supervised Object Discovery in Surgical Video","created":"2025-01-21","cited_by_count":4,"area":null},{"id":"2509.02545","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","created":"2025-09-02","cited_by_count":4,"area":null},{"id":"2506.02964","title":"FORLA: Federated Object-centric Representation Learning with Slot Attention","created":"2025-06-03","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":"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":"2507.01882","title":"Future Slot Prediction for Unsupervised Object Discovery in Surgical Video","created":"2025-07-02","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":"2606.12601","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":"2606.13714","title":"TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2606.15527","title":"Selective Synergistic Learning for Video Object-Centric Learning","created":"2026-06-14","cited_by_count":2,"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":"2602.07544","title":"MUFASA: A Multi-Layer Framework for Slot Attention","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2605.03650","title":"Rethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to Correspondence","created":"2026-05-05","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":"2407.09537","title":"ViPro: Enabling and Controlling Video Prediction for Complex Dynamical Scenarios using Procedural Knowledge","created":"2024-06-26","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":"2507.20855","title":"Compositional Video Synthesis by Temporal Object-Centric Learning","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2508.06335","title":"ViPro-2: Unsupervised State Estimation via Integrated Dynamics for Guiding Video Prediction","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2509.02032","title":"ContextFusion and Bootstrap: An Effective Approach to Improve Slot Attention-Based Object-Centric Learning","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2509.09298","title":"Learning Object-Centric Representations in SAR Images with Multi-Level Feature Fusion","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2512.02685","title":"Unsupervised Structural Scene Decomposition via Foreground-Aware Slot Attention with Pseudo-Mask Guidance","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2512.18192","title":"Multi-Part Object Representations via Graph Structures and Co-Part Discovery","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2601.04462","title":"Meta-probabilistic Modeling","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2601.12936","title":"QASA: Quality-Guided K-Adaptive Slot Attention for Unsupervised Object-Centric Learning","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2602.07532","title":"Evaluating Object-Centric Models beyond Object Discovery","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2603.11246","title":"When Slots Compete: Slot Merging in Object-Centric Learning","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.19480","title":"Deep Sprite-based Image Models: An Analysis","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.27696","title":"Structure over Pixels: Learning Variable-Length Visual Programs","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.30211","title":"Cycle Consistency in Video Object-Centric Learning","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.05325","title":"CenSynCMB: Centre Maps and Physics-Guided Synthesis for Microbleed Detection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.08249","title":"HSA: Hierarchical Slot Attention for Multi-granularity Scene-Decomposition","created":"2026-07-09","cited_by_count":0,"area":null}],"next_cursor":null}