{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"1812.02713","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","created":"2018-12-06","cited_by_count":526},{"id":"1803.00676","title":"Meta-Learning for Semi-Supervised Few-Shot Classification","created":"2018-03-02","cited_by_count":456},{"id":"2103.15875","title":"In-Place Scene Labelling and Understanding with Implicit Scene Representation","created":"2021-03-29","cited_by_count":415},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329},{"id":"1904.06447","title":"Learning Shape Templates with Structured Implicit Functions","created":"2019-04-12","cited_by_count":242},{"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":"2111.13152","title":"Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations","created":"2021-11-25","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":"1911.06971","title":"BSP-Net: Generating Compact Meshes via Binary Space Partitioning","created":"2019-11-16","cited_by_count":206},{"id":"1906.03950","title":"Domain-Specific Batch Normalization for Unsupervised Domain Adaptation","created":"2019-05-27","cited_by_count":197},{"id":"2111.13539","title":"GeoNeRF: Generalizing NeRF with Geometry Priors","created":"2021-11-26","cited_by_count":196},{"id":"1612.00404","title":"Learning Shape Abstractions by Assembling Volumetric Primitives","created":"2016-12-01","cited_by_count":181},{"id":"1909.05736","title":"CvxNet: Learnable Convex Decomposition","created":"2019-09-12","cited_by_count":174},{"id":"1607.03516","title":"Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation","created":"2016-07-12","cited_by_count":163},{"id":"2006.08381","title":"DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning","created":"2020-06-15","cited_by_count":161},{"id":"1806.01794","title":"Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects","created":"2018-06-05","cited_by_count":128},{"id":"1904.09970","title":"Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids","created":"2019-04-22","cited_by_count":124},{"id":"1911.10949","title":"PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes","created":"2019-11-25","cited_by_count":119},{"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":"1908.04520","title":"SDM-NET: Deep Generative Network for Structured Deformable Mesh","created":"2019-08-13","cited_by_count":113},{"id":"2103.10429","title":"Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks","created":"2021-03-18","cited_by_count":103},{"id":"1802.10353","title":"Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions","created":"2018-02-28","cited_by_count":100},{"id":"1908.04725","title":"Learning elementary structures for 3D shape generation and matching","created":"2019-08-13","cited_by_count":98},{"id":"2111.10265","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","created":"2021-11-19","cited_by_count":93},{"id":"1903.11228","title":"BAE-NET: Branched Autoencoder for Shape Co-Segmentation","created":"2019-03-27","cited_by_count":89},{"id":"1906.06818","title":"Stacked Capsule Autoencoders","created":"2019-06-17","cited_by_count":82},{"id":"2004.01176","title":"Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image","created":"2020-04-02","cited_by_count":72},{"id":"1606.06724","title":"Tagger: Deep Unsupervised Perceptual Grouping","created":"2016-06-21","cited_by_count":69},{"id":"1901.02875","title":"Learning to Infer and Execute 3D Shape Programs","created":"2019-01-09","cited_by_count":68},{"id":"2103.16201","title":"MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption","created":"2021-03-30","cited_by_count":65},{"id":"2112.02355","title":"SITA: Single Image Test-time Adaptation","created":"2021-12-04","cited_by_count":59},{"id":"1804.05469","title":"Im2Struct: Recovering 3D Shape Structure from a Single RGB Image","created":"2018-04-16","cited_by_count":55},{"id":"2107.00848","title":"Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning","created":"2021-07-02","cited_by_count":53},{"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":"1811.10719","title":"Learning View Priors for Single-view 3D Reconstruction","created":"2018-11-26","cited_by_count":35},{"id":"2112.06745","title":"A Survey of Unsupervised Domain Adaptation for Visual Recognition","created":"2021-12-13","cited_by_count":31},{"id":"2002.06478","title":"Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories","created":"2020-02-16","cited_by_count":30},{"id":"2007.12348","title":"Unsupervised Discovery of 3D Physical Objects from Video","created":"2020-07-24","cited_by_count":27},{"id":"2104.03851","title":"CoCoNets: Continuous Contrastive 3D Scene Representations","created":"2021-04-08","cited_by_count":19},{"id":"2007.06245","title":"Reconstruction Bottlenecks in Object-Centric Generative Models","created":"2020-07-13","cited_by_count":17},{"id":"2007.14878","title":"MessyTable: Instance Association in Multiple Camera Views","created":"2020-07-29","cited_by_count":13},{"id":"2107.13629","title":"Discovering 3D Parts from Image Collections","created":"2021-07-28","cited_by_count":13},{"id":"2006.14727","title":"Unsupervised Video Decomposition using Spatio-temporal Iterative Inference","created":"2020-06-25","cited_by_count":12},{"id":"2007.06533","title":"S2RMs: Spatially Structured Recurrent Modules","created":"2020-07-13","cited_by_count":10},{"id":"2011.10007","title":"Multi-Plane Program Induction with 3D Box Priors","created":"2020-11-19","cited_by_count":10}],"next_cursor":null}