{"total":209,"rows":[{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248,"area":"wm"},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220,"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":"2201.10700","title":"Deep Image Deblurring: A Survey","created":"2022-01-26","cited_by_count":94,"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":"2103.15619","title":"SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data","created":"2021-03-29","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":"2103.01937","title":"Neural Production Systems: Learning Rule-Governed Visual Dynamics","created":"2021-03-02","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":"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":"2104.03059","title":"Differentiable Patch Selection for Image Recognition","created":"2021-04-07","cited_by_count":68,"area":null},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60,"area":null},{"id":"2112.02236","title":"SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing","created":"2021-12-04","cited_by_count":58,"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":"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":"2108.12043","title":"Learning Disentangled Representations in the Imaging Domain","created":"2021-08-26","cited_by_count":46,"area":null},{"id":"2203.10159","title":"Discovering Objects that Can Move","created":"2022-03-18","cited_by_count":44,"area":null},{"id":"2204.02075","title":"Complex-Valued Autoencoders for Object Discovery","created":"2022-04-05","cited_by_count":40,"area":null},{"id":"2201.12382","title":"Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices","created":"2022-01-28","cited_by_count":37,"area":"lr"},{"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":"2104.14553","title":"MarioNette: Self-Supervised Sprite Learning","created":"2021-04-29","cited_by_count":35,"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":"2204.00746","title":"What to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactions","created":"2022-04-02","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":"2202.04178","title":"VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming","created":"2022-02-07","cited_by_count":31,"area":"lr"},{"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":"2110.15497","title":"Unsupervised Foreground Extraction via Deep Region Competition","created":"2021-10-29","cited_by_count":26,"area":"moe"},{"id":"2111.00312","title":"3DP3: 3D Scene Perception via Probabilistic Programming","created":"2021-10-30","cited_by_count":26,"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":"2103.06089","title":"Variable-rate discrete representation learning","created":"2021-03-10","cited_by_count":24,"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":"2311.02007","title":"Towards Unsupervised Object Detection From LiDAR Point Clouds","created":"2023-11-03","cited_by_count":23,"area":null},{"id":"2103.14610","title":"SKID RAW: Skill Discovery from Raw Trajectories","created":"2021-03-26","cited_by_count":22,"area":null},{"id":"2104.02726","title":"Creativity and Machine Learning: A Survey","created":"2021-04-06","cited_by_count":21,"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":"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":"2210.07920","title":"MOVE: Unsupervised Movable Object Segmentation and Detection","created":"2022-10-14","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":"2110.09140","title":"Learning Prototype-oriented Set Representations for Meta-Learning","created":"2021-10-18","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":"2408.09162","title":"Zero-Shot Object-Centric Representation Learning","created":"2024-08-17","cited_by_count":19,"area":null},{"id":"2102.10212","title":"Hard-Attention for Scalable Image Classification","created":"2021-02-20","cited_by_count":18,"area":null},{"id":"2105.03830","title":"Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior","created":"2021-05-09","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":"2406.12272","title":"Slot State Space Models","created":"2024-06-18","cited_by_count":17,"area":"ssm"},{"id":"2210.00314","title":"Learning Hierarchical Image Segmentation For Recognition and By Recognition","created":"2022-10-01","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":"2102.11344","title":"HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving","created":"2021-02-22","cited_by_count":15,"area":null},{"id":"2112.00976","title":"Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification","created":"2021-12-02","cited_by_count":15,"area":null},{"id":"2204.11167","title":"RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning","created":"2022-04-24","cited_by_count":15,"area":null},{"id":"2307.09205","title":"Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning","created":"2023-07-18","cited_by_count":15,"area":"wm"},{"id":"2309.00233","title":"Object-Centric Multiple Object Tracking","created":"2023-09-01","cited_by_count":15,"area":null},{"id":"2403.12033","title":"HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation","created":"2024-03-18","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":"2211.05039","title":"Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task","created":"2022-11-09","cited_by_count":13,"area":null},{"id":"2405.00646","title":"Learning to Compose: Improving Object Centric Learning by Injecting Compositionality","created":"2024-05-01","cited_by_count":13,"area":"lr"},{"id":"2501.15878","title":"Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation","created":"2025-01-27","cited_by_count":13,"area":"diffusion"},{"id":"2103.03987","title":"Selective Replay Enhances Learning in Online Continual Analogical Reasoning","created":"2021-03-06","cited_by_count":12,"area":null},{"id":"2111.07534","title":"A Probabilistic Hard Attention Model For Sequentially Observed Scenes","created":"2021-11-15","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":"2502.14113","title":"Object-centric Binding in Contrastive Language-Image Pretraining","created":"2025-02-19","cited_by_count":12,"area":"mllm"},{"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":"2205.13271","title":"Unsupervised Multi-object Segmentation Using Attention and Soft-argmax","created":"2022-05-26","cited_by_count":11,"area":null},{"id":"2211.03374","title":"Deep Causal Learning: Representation, Discovery and Inference","created":"2022-11-07","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":"2111.05393","title":"Object-Centric Representation Learning with Generative Spatial-Temporal Factorization","created":"2021-11-09","cited_by_count":10,"area":null},{"id":"2210.13461","title":"Active Predictive Coding: A Unified Neural Framework for Learning Hierarchical World Models for Perception and Planning","created":"2022-10-23","cited_by_count":10,"area":"wm"},{"id":"2302.01579","title":"Semantic 3D-aware Portrait Synthesis and Manipulation Based on Compositional Neural Radiance Field","created":"2023-02-03","cited_by_count":10,"area":null},{"id":"2304.00948","title":"VTAE: Variational Transformer Autoencoder with Manifolds Learning","created":"2023-04-03","cited_by_count":10,"area":null},{"id":"2505.24492","title":"Object Centric Concept Bottlenecks","created":"2025-05-30","cited_by_count":10,"area":null}],"next_cursor":"100"}