{"list":"other","total":75,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1811.12359","title":"Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations","created":"2018-11-29","cited_by_count":941},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"1802.05983","title":"Disentangling by Factorising","created":"2018-02-16","cited_by_count":616},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"id":"1711.00848","title":"Variational Inference of Disentangled Latent Concepts from Unlabeled Observations","created":"2017-11-02","cited_by_count":241},{"id":"2012.05208","title":"On the Binding Problem in Artificial Neural Networks","created":"2020-12-09","cited_by_count":233},{"id":"1907.13052","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","created":"2019-07-30","cited_by_count":227},{"id":"1909.10893","title":"Recurrent Independent Mechanisms","created":"2019-09-24","cited_by_count":219},{"id":"1603.08575","title":"Attend, Infer, Repeat: Fast Scene Understanding with Generative Models","created":"2016-03-28","cited_by_count":209},{"id":"2001.02407","title":"SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition","created":"2020-01-08","cited_by_count":190},{"id":"2202.11539","title":"Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut","created":"2022-02-23","cited_by_count":167},{"id":"2206.07764","title":"SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos","created":"2022-06-15","cited_by_count":166},{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147},{"id":"2205.14065","title":"Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos","created":"2022-05-27","cited_by_count":139},{"id":"1806.01794","title":"Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects","created":"2018-06-05","cited_by_count":128},{"id":"1708.03498","title":"Neural Expectation Maximization","created":"2017-08-11","cited_by_count":123},{"id":"1901.07017","title":"Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs","created":"2019-01-21","cited_by_count":117},{"id":"1910.12827","title":"Entity Abstraction in Visual Model-Based Reinforcement Learning","created":"2019-10-28","cited_by_count":110},{"id":"2104.09958","title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","created":"2021-04-20","cited_by_count":109},{"id":"1910.02384","title":"SCALOR: Generative World Models with Scalable Object Representations","created":"2019-10-06","cited_by_count":108},{"id":"1802.05312","title":"Learning Deep Disentangled Embeddings with the F-Statistic Loss","created":"2018-02-14","cited_by_count":101},{"id":"1802.10353","title":"Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions","created":"2018-02-28","cited_by_count":100},{"id":"2111.10265","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","created":"2021-11-19","cited_by_count":93},{"id":"2206.06922","title":"Object Scene Representation Transformer","created":"2022-06-14","cited_by_count":90},{"id":"2104.01148","title":"Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation","created":"2021-04-02","cited_by_count":88},{"id":"1902.07181","title":"Measuring Compositionality in Representation Learning","created":"2019-02-19","cited_by_count":84},{"id":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81},{"id":"2203.08777","title":"Object discovery and representation networks","created":"2022-03-16","cited_by_count":80},{"id":"2103.01937","title":"Neural Production Systems: Learning Rule-Governed Visual Dynamics","created":"2021-03-02","cited_by_count":75},{"id":"2010.02054","title":"Improving Generative Imagination in Object-Centric World Models","created":"2020-10-05","cited_by_count":71},{"id":"2111.03042","title":"Unsupervised Learning of Compositional Energy Concepts","created":"2021-11-04","cited_by_count":71},{"id":"2205.15288","title":"Self-Supervised Visual Representation Learning with Semantic Grouping","created":"2022-05-30","cited_by_count":70},{"id":"1606.06724","title":"Tagger: Deep Unsupervised Perceptual Grouping","created":"2016-06-21","cited_by_count":69},{"id":"2106.03849","title":"SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition","created":"2021-06-07","cited_by_count":69},{"id":"2007.11341","title":"Unsupervised Shape and Pose Disentanglement for 3D Meshes","created":"2020-07-22","cited_by_count":61},{"id":"1905.09275","title":"COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration","created":"2019-05-22","cited_by_count":57},{"id":"2010.12152","title":"Generative Neurosymbolic Machines","created":"2020-10-23","cited_by_count":57},{"id":"2006.16225","title":"Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems","created":"2020-06-29","cited_by_count":48},{"id":"2207.00787","title":"Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation","created":"2022-07-02","cited_by_count":46},{"id":"1911.09033","title":"Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking","created":"2019-11-20","cited_by_count":40},{"id":"2006.06130","title":"ROOTS: Object-Centric Representation and Rendering of 3D Scenes","created":"2020-06-11","cited_by_count":40},{"id":"2204.02075","title":"Complex-Valued Autoencoders for Object Discovery","created":"2022-04-05","cited_by_count":40},{"id":"2107.02367","title":"Discrete-Valued Neural Communication","created":"2021-07-06","cited_by_count":39},{"id":"2004.12906","title":"Towards causal generative scene models via competition of experts","created":"2020-04-27","cited_by_count":37},{"id":"2111.07117","title":"Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views","created":"2021-11-13","cited_by_count":37},{"id":"2007.06705","title":"Unsupervised object-centric video generation and decomposition in 3D","created":"2020-07-07","cited_by_count":31},{"id":"2007.12348","title":"Unsupervised Discovery of 3D Physical Objects from Video","created":"2020-07-24","cited_by_count":27},{"id":"2110.15497","title":"Unsupervised Foreground Extraction via Deep Region Competition","created":"2021-10-29","cited_by_count":26},{"id":"2107.09240","title":"Generative Video Transformer: Can Objects be the Words?","created":"2021-07-20","cited_by_count":24},{"id":"2112.02290","title":"Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations","created":"2021-12-04","cited_by_count":24},{"id":"1809.03137","title":"Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers","created":"2018-09-10","cited_by_count":22},{"id":"1910.05231","title":"R-SQAIR: Relational Sequential Attend, Infer, Repeat","created":"2019-10-11","cited_by_count":21},{"id":"2107.08577","title":"Structured World Belief for Reinforcement Learning in POMDP","created":"2021-07-19","cited_by_count":21},{"id":"2004.00642","title":"Object-Centric Image Generation with Factored Depths, Locations, and Appearances","created":"2020-04-01","cited_by_count":20},{"id":"2103.04693","title":"Unsupervised Object-Based Transition Models for 3D Partially Observable Environments","created":"2021-03-08","cited_by_count":20},{"id":"2011.10287","title":"Learning Object-Centric Video Models by Contrasting Sets","created":"2020-11-20","cited_by_count":19},{"id":"2103.00336","title":"Transformers with Competitive Ensembles of Independent Mechanisms","created":"2021-02-27","cited_by_count":19},{"id":"2011.03367","title":"Disentangling 3D Prototypical Networks For Few-Shot Concept Learning","created":"2020-11-06","cited_by_count":15},{"id":"2203.05997","title":"Towards Self-Supervised Learning of Global and Object-Centric Representations","created":"2022-03-11","cited_by_count":11},{"id":"2007.09294","title":"Slot Contrastive Networks: A Contrastive Approach for Representing Objects","created":"2020-07-18","cited_by_count":9},{"id":"2007.08973","title":"AlignNet: Unsupervised Entity Alignment","created":"2020-07-17","cited_by_count":6},{"id":"2103.05669","title":"Self-Supervision by Prediction for Object Discovery in Videos","created":"2021-03-09","cited_by_count":6},{"id":"2101.04041","title":"Evaluating Disentanglement of Structured Representations","created":"2021-01-11","cited_by_count":3},{"id":"2208.03167","title":"Disentangling 3D Attributes from a Single 2D Image: Human Pose, Shape and Garment","created":"2022-08-05","cited_by_count":2}],"next_cursor":null}