{"total":123,"rows":[{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248,"area":"wm"},{"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":"2205.14065","title":"Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos","created":"2022-05-27","cited_by_count":139,"area":null},{"id":"2103.01209","title":"Generative Adversarial Transformers","created":"2021-03-01","cited_by_count":120,"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":"2107.07905","title":"Unsupervised Discovery of Object Radiance Fields","created":"2021-07-16","cited_by_count":101,"area":null},{"id":"2111.10265","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","created":"2021-11-19","cited_by_count":93,"area":null},{"id":"2303.10834","title":"Object-Centric Slot Diffusion","created":"2023-03-20","cited_by_count":90,"area":"diffusion"},{"id":"2104.01148","title":"Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation","created":"2021-04-02","cited_by_count":88,"area":null},{"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":"2109.04553","title":"Is Attention Better Than Matrix Decomposition?","created":"2021-09-09","cited_by_count":77,"area":null},{"id":"2111.03042","title":"Unsupervised Learning of Compositional Energy Concepts","created":"2021-11-04","cited_by_count":71,"area":null},{"id":"2108.09274","title":"MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction","created":"2021-08-20","cited_by_count":61,"area":null},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60,"area":null},{"id":"2307.02598","title":"Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation","created":"2023-07-05","cited_by_count":58,"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":"2104.14575","title":"Unsupervised Layered Image Decomposition into Object Prototypes","created":"2021-04-29","cited_by_count":50,"area":null},{"id":"2310.06907","title":"Self-supervised Object-Centric Learning for Videos","created":"2023-10-10","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":"2204.02075","title":"Complex-Valued Autoencoders for Object Discovery","created":"2022-04-05","cited_by_count":40,"area":null},{"id":"2111.07117","title":"Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views","created":"2021-11-13","cited_by_count":37,"area":null},{"id":"2211.01177","title":"Neural Systematic Binder","created":"2022-11-02","cited_by_count":37,"area":null},{"id":"2106.03630","title":"Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations","created":"2021-06-07","cited_by_count":36,"area":null},{"id":"2202.13519","title":"PartAfford: Part-level Affordance Discovery from 3D Objects","created":"2022-02-28","cited_by_count":36,"area":null},{"id":"2104.06456","title":"Single Image Depth Estimation: An Overview","created":"2021-04-13","cited_by_count":35,"area":null},{"id":"2201.02074","title":"EM-driven unsupervised learning for efficient motion segmentation","created":"2022-01-06","cited_by_count":33,"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":"2110.06562","title":"Unsupervised Object Learning via Common Fate","created":"2021-10-13","cited_by_count":29,"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":"2110.15497","title":"Unsupervised Foreground Extraction via Deep Region Competition","created":"2021-10-29","cited_by_count":26,"area":"moe"},{"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":"2202.00961","title":"Modularity-Aware Graph Autoencoders for Joint Community Detection and Link Prediction","created":"2022-02-02","cited_by_count":22,"area":null},{"id":"2301.05169","title":"Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning","created":"2023-01-12","cited_by_count":22,"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":"2207.11232","title":"Neural Groundplans: Persistent Neural Scene Representations from a Single Image","created":"2022-07-22","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":"2210.02324","title":"Promising or Elusive? Unsupervised Object Segmentation from Real-world Single Images","created":"2022-10-05","cited_by_count":16,"area":null},{"id":"2305.15001","title":"Contrastive Training of Complex-Valued Autoencoders for Object Discovery","created":"2023-05-24","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":"2203.13573","title":"Unsupervised Learning of Temporal Abstractions with Slot-based Transformers","created":"2022-03-25","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":"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":"2106.05897","title":"Unsupervised Co-part Segmentation through Assembly","created":"2021-06-10","cited_by_count":12,"area":null},{"id":"2402.07376","title":"Unsupervised Discovery of Object-Centric Neural Fields","created":"2024-02-12","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":"2112.03568","title":"Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints","created":"2021-12-07","cited_by_count":11,"area":null},{"id":"2305.16543","title":"Revisiting Structured Variational Autoencoders","created":"2023-05-25","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":"2111.05393","title":"Object-Centric Representation Learning with Generative Spatial-Temporal Factorization","created":"2021-11-09","cited_by_count":10,"area":null},{"id":"2206.02664","title":"Learning with Capsules: A Survey","created":"2022-06-06","cited_by_count":10,"area":null},{"id":"2402.01203","title":"Neural Language of Thought Models","created":"2024-02-02","cited_by_count":9,"area":"lr"},{"id":"2410.19923","title":"Language Agents Meet Causality -- Bridging LLMs and Causal World Models","created":"2024-10-25","cited_by_count":9,"area":"wm"},{"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":"2405.17283","title":"Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery","created":"2024-05-27","cited_by_count":8,"area":null},{"id":"2107.06991","title":"Physics-informed generative neural network: an application to troposphere temperature prediction","created":"2021-07-08","cited_by_count":7,"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":"2306.02204","title":"Cycle Consistency Driven Object Discovery","created":"2023-06-03","cited_by_count":7,"area":null},{"id":"2103.05669","title":"Self-Supervision by Prediction for Object Discovery in Videos","created":"2021-03-09","cited_by_count":6,"area":null},{"id":"2103.10611","title":"Knowledge-Guided Object Discovery with Acquired Deep Impressions","created":"2021-03-19","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":"2402.05627","title":"Binding Dynamics in Rotating Features","created":"2024-02-08","cited_by_count":5,"area":null},{"id":"2109.05675","title":"Online Unsupervised Learning of Visual Representations and Categories","created":"2021-09-13","cited_by_count":4,"area":null},{"id":"2201.03624","title":"Competing Mutual Information Constraints with Stochastic Competition-based Activations for Learning Diversified Representations","created":"2022-01-10","cited_by_count":4,"area":null},{"id":"2302.10503","title":"Reusable Slotwise Mechanisms","created":"2023-02-21","cited_by_count":4,"area":null},{"id":"2303.14889","title":"Model-Based Reinforcement Learning with Isolated Imaginations","created":"2023-03-27","cited_by_count":4,"area":"wm"},{"id":"2306.07235","title":"Deep Gaussian Mixture Ensembles","created":"2023-06-12","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":"2401.01922","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":"2410.14371","title":"Interpretable end-to-end Neurosymbolic Reinforcement Learning agents","created":"2024-10-18","cited_by_count":4,"area":"deeprl"},{"id":"2410.20922","title":"FACTS: A Factored State-Space Framework For World Modelling","created":"2024-10-28","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":"2506.01778","title":"unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2101.04041","title":"Evaluating Disentanglement of Structured Representations","created":"2021-01-11","cited_by_count":3,"area":null},{"id":"2106.01722","title":"GMAIR: Unsupervised Object Detection Based on Spatial Attention and Gaussian Mixture","created":"2021-06-03","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":"2302.01660","title":"The Learnable Typewriter: A Generative Approach to Text Analysis","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2102.01223","title":"Inducing Meaningful Units from Character Sequences with Dynamic Capacity Slot Attention","created":"2021-02-01","cited_by_count":2,"area":null},{"id":"2106.05607","title":"Spatially Invariant Unsupervised 3D Object-Centric Learning and Scene Decomposition","created":"2021-06-10","cited_by_count":2,"area":null},{"id":"2107.02453","title":"Neural Mixture Models with Expectation-Maximization for End-to-end Deep Clustering","created":"2021-07-06","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":"2210.14808","title":"Search for Concepts: Discovering Visual Concepts Using Direct Optimization","created":"2022-10-25","cited_by_count":2,"area":"lr"},{"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":"2311.07534","title":"Unsupervised Musical Object Discovery from Audio","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2402.17077","title":"Parallelized Spatiotemporal Binding","created":"2024-02-26","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}],"next_cursor":"100"}