{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"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":"2011.12100","title":"GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields","created":"2020-11-24","cited_by_count":785},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"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":"1605.09782","title":"Adversarial Feature Learning","created":"2016-05-31","cited_by_count":350},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"1711.00848","title":"Variational Inference of Disentangled Latent Concepts from Unlabeled Observations","created":"2017-11-02","cited_by_count":241},{"id":"1907.02544","title":"Large Scale Adversarial Representation Learning","created":"2019-07-04","cited_by_count":239},{"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":"2002.08988","title":"BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images","created":"2020-02-20","cited_by_count":166},{"id":"2104.07658","title":"Self-supervised Video Object Segmentation by Motion Grouping","created":"2021-04-15","cited_by_count":147},{"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":"2102.12627","title":"How to represent part-whole hierarchies in a neural network","created":"2021-02-25","cited_by_count":123},{"id":"1503.03167","title":"Deep Convolutional Inverse Graphics Network","created":"2015-03-11","cited_by_count":121},{"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":"1902.10740","title":"Object-driven Text-to-Image Synthesis via Adversarial Training","created":"2019-02-27","cited_by_count":117},{"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":"1610.02454","title":"Learning What and Where to Draw","created":"2016-10-08","cited_by_count":105},{"id":"1912.05237","title":"Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis","created":"2019-12-11","cited_by_count":104},{"id":"1512.00570","title":"Attribute2Image: Conditional Image Generation from Visual Attributes","created":"2015-12-02","cited_by_count":93},{"id":"1909.05379","title":"Specifying Object Attributes and Relations in Interactive Scene Generation","created":"2019-09-11","cited_by_count":76},{"id":"1905.13539","title":"Unsupervised Object Segmentation by Redrawing","created":"2019-05-27","cited_by_count":74},{"id":"2010.02054","title":"Improving Generative Imagination in Object-Centric World Models","created":"2020-10-05","cited_by_count":71},{"id":"2106.03849","title":"SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition","created":"2021-06-07","cited_by_count":69},{"id":"1912.07414","title":"Learning Canonical Representations for Scene Graph to Image Generation","created":"2019-12-16","cited_by_count":60},{"id":"1905.12663","title":"Emergence of Object Segmentation in Perturbed Generative Models","created":"2019-05-29","cited_by_count":57},{"id":"2010.12152","title":"Generative Neurosymbolic Machines","created":"2020-10-23","cited_by_count":57},{"id":"1804.08018","title":"ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking","created":"2018-04-21","cited_by_count":55},{"id":"2103.10426","title":"Using latent space regression to analyze and leverage compositionality in GANs","created":"2021-03-18","cited_by_count":55},{"id":"1511.06406","title":"Denoising Criterion for Variational Auto-Encoding Framework","created":"2015-11-19","cited_by_count":43},{"id":"1901.00686","title":"Generating Multiple Objects at Spatially Distinct Locations","created":"2019-01-03","cited_by_count":41},{"id":"1911.09033","title":"Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking","created":"2019-11-20","cited_by_count":40},{"id":"2004.12906","title":"Towards causal generative scene models via competition of experts","created":"2020-04-27","cited_by_count":37},{"id":"2006.15327","title":"Compositional Video Synthesis with Action Graphs","created":"2020-06-27","cited_by_count":34},{"id":"2007.01272","title":"RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces","created":"2020-07-02","cited_by_count":32},{"id":"2107.09240","title":"Generative Video Transformer: Can Objects be the Words?","created":"2021-07-20","cited_by_count":24},{"id":"2004.05495","title":"Learning to Manipulate Individual Objects in an Image","created":"2020-04-11","cited_by_count":22},{"id":"2012.07287","title":"Information-Theoretic Segmentation by Inpainting Error Maximization","created":"2020-12-14","cited_by_count":22},{"id":"2004.00642","title":"Object-Centric Image Generation with Factored Depths, Locations, and Appearances","created":"2020-04-01","cited_by_count":20},{"id":"2103.00336","title":"Transformers with Competitive Ensembles of Independent Mechanisms","created":"2021-02-27","cited_by_count":19},{"id":"1412.5721","title":"An Algorithm for Online K-Means Clustering","created":"2014-12-18","cited_by_count":12},{"id":"1607.05387","title":"Generating Images Part by Part with Composite Generative Adversarial Networks","created":"2016-07-19","cited_by_count":6}],"next_cursor":null}