{"total":198,"rows":[{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381,"area":null},{"id":"2109.14279","title":"Localizing Objects with Self-Supervised Transformers and no Labels","created":"2021-09-29","cited_by_count":230,"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":"2103.02582","title":"D'ya like DAGs? A Survey on Structure Learning and Causal Discovery","created":"2021-03-03","cited_by_count":211,"area":null},{"id":"2205.07839","title":"Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization","created":"2022-05-16","cited_by_count":150,"area":null},{"id":"2104.07658","title":"Self-supervised Video Object Segmentation by Motion Grouping","created":"2021-04-15","cited_by_count":147,"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":"2104.00587","title":"NeRF-VAE: A Geometry Aware 3D Scene Generative Model","created":"2021-04-01","cited_by_count":112,"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":"2104.01148","title":"Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation","created":"2021-04-02","cited_by_count":88,"area":null},{"id":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81,"area":null},{"id":"2201.13100","title":"Adversarial Masking for Self-Supervised Learning","created":"2022-01-31","cited_by_count":78,"area":null},{"id":"2103.01937","title":"Neural Production Systems: Learning Rule-Governed Visual Dynamics","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2103.04174","title":"Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction","created":"2021-03-06","cited_by_count":75,"area":null},{"id":"2111.03042","title":"Unsupervised Learning of Compositional Energy Concepts","created":"2021-11-04","cited_by_count":71,"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":"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":"2203.07034","title":"Active Learning by Feature Mixing","created":"2022-03-14","cited_by_count":63,"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":"2307.02598","title":"Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation","created":"2023-07-05","cited_by_count":58,"area":null},{"id":"2111.06349","title":"Unsupervised Part Discovery from Contrastive Reconstruction","created":"2021-11-11","cited_by_count":57,"area":null},{"id":"2106.06650","title":"Large-Scale Unsupervised Object Discovery","created":"2021-06-12","cited_by_count":54,"area":null},{"id":"2206.06363","title":"Discovering Object Masks with Transformers for Unsupervised Semantic Segmentation","created":"2022-06-13","cited_by_count":54,"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":"2104.14575","title":"Unsupervised Layered Image Decomposition into Object Prototypes","created":"2021-04-29","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":"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":"2305.14229","title":"Provably Learning Object-Centric Representations","created":"2023-05-23","cited_by_count":45,"area":null},{"id":"2203.10159","title":"Discovering Objects that Can Move","created":"2022-03-18","cited_by_count":44,"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":"2312.15540","title":"Amodal Completion via Progressive Mixed Context Diffusion","created":"2023-12-24","cited_by_count":38,"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":"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":"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":"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":"2202.10432","title":"Reasoning with Scene Graphs for Robot Planning under Partial Observability","created":"2022-02-21","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":"2111.08960","title":"Compositional Transformers for Scene Generation","created":"2021-11-17","cited_by_count":24,"area":null},{"id":"2112.02290","title":"Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations","created":"2021-12-04","cited_by_count":24,"area":null},{"id":"2112.08949","title":"Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentation","created":"2021-12-16","cited_by_count":24,"area":null},{"id":"2207.10075","title":"Is an Object-Centric Video Representation Beneficial for Transfer?","created":"2022-07-20","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":"2210.00489","title":"Unsupervised Multi-View Object Segmentation Using Radiance Field Propagation","created":"2022-10-02","cited_by_count":22,"area":null},{"id":"2109.03351","title":"Capturing the objects of vision with neural networks","created":"2021-09-07","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":"2310.19054","title":"Object-centric architectures enable efficient causal representation learning","created":"2023-10-29","cited_by_count":21,"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":"2202.05839","title":"Abstraction for Deep Reinforcement Learning","created":"2022-02-10","cited_by_count":19,"area":null},{"id":"2205.15821","title":"Unsupervised Image Representation Learning with Deep Latent Particles","created":"2022-05-31","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":"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":"2207.02062","title":"Image Amodal Completion: A Survey","created":"2022-07-05","cited_by_count":18,"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":"2306.00503","title":"MEWL: Few-shot multimodal word learning with referential uncertainty","created":"2023-06-01","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":"2406.07706","title":"Object-level Scene Deocclusion","created":"2024-06-11","cited_by_count":17,"area":null},{"id":"2103.06796","title":"Unknown Object Segmentation from Stereo Images","created":"2021-03-11","cited_by_count":16,"area":null},{"id":"2110.09383","title":"Neuro-Symbolic Forward Reasoning","created":"2021-10-18","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":"2307.08027","title":"Multi-Object Discovery by Low-Dimensional Object Motion","created":"2023-07-16","cited_by_count":16,"area":null},{"id":"2106.05886","title":"Group Equivariant Subsampling","created":"2021-06-10","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":"2205.10093","title":"Visual Concepts Tokenization","created":"2022-05-20","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":"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":"2305.08810","title":"AutoRecon: Automated 3D Object Discovery and Reconstruction","created":"2023-05-15","cited_by_count":13,"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":"2503.21747","title":"CTRL-O: Language-Controllable Object-Centric Visual Representation Learning","created":"2025-03-27","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":"2203.05997","title":"Towards Self-Supervised Learning of Global and Object-Centric Representations","created":"2022-03-11","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":"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":"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":"2111.05393","title":"Object-Centric Representation Learning with Generative Spatial-Temporal Factorization","created":"2021-11-09","cited_by_count":10,"area":null}],"next_cursor":"100"}