{"list":"other","total":73,"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":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1904.00607","title":"Video Object Segmentation using Space-Time Memory Networks","created":"2019-04-01","cited_by_count":438},{"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":"1903.07593","title":"Learning Correspondence from the Cycle-Consistency of Time","created":"2019-03-18","cited_by_count":269},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"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":"1603.08575","title":"Attend, Infer, Repeat: Fast Scene Understanding with Generative Models","created":"2016-03-28","cited_by_count":209},{"id":"1911.12247","title":"Contrastive Learning of Structured World Models","created":"2019-11-27","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":"1806.09594","title":"Tracking Emerges by Colorizing Videos","created":"2018-06-25","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":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147},{"id":"1910.04744","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","created":"2019-10-10","cited_by_count":137},{"id":"1806.01794","title":"Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects","created":"2018-06-05","cited_by_count":128},{"id":"2006.04902","title":"What Matters in Unsupervised Optical Flow","created":"2020-06-08","cited_by_count":124},{"id":"1708.03498","title":"Neural Expectation Maximization","created":"2017-08-11","cited_by_count":123},{"id":"1910.12827","title":"Entity Abstraction in Visual Model-Based Reinforcement Learning","created":"2019-10-28","cited_by_count":110},{"id":"2002.07793","title":"MAST: A Memory-Augmented Self-supervised Tracker","created":"2020-02-18","cited_by_count":109},{"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":"1711.05890","title":"Occlusion Aware Unsupervised Learning of Optical Flow","created":"2017-11-16","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":"2104.01148","title":"Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation","created":"2021-04-02","cited_by_count":88},{"id":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81},{"id":"1904.01828","title":"Unsupervised Deep Tracking","created":"2019-04-03","cited_by_count":74},{"id":"2105.07014","title":"SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping","created":"2021-05-14","cited_by_count":74},{"id":"1901.03360","title":"Unsupervised Moving Object Detection via Contextual Information Separation","created":"2019-01-10","cited_by_count":72},{"id":"1604.00136","title":"It's Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera Videos","created":"2016-04-01","cited_by_count":71},{"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":"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":"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":"1904.03177","title":"Structured agents for physical construction","created":"2019-04-05","cited_by_count":50},{"id":"2203.10159","title":"Discovering Objects that Can Move","created":"2022-03-18","cited_by_count":44},{"id":"1910.02425","title":"Structured Object-Aware Physics Prediction for Video Modeling and Planning","created":"2019-10-06","cited_by_count":43},{"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":"2004.12906","title":"Towards causal generative scene models via competition of experts","created":"2020-04-27","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":"2110.06562","title":"Unsupervised Object Learning via Common Fate","created":"2021-10-13","cited_by_count":29},{"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":"1809.03137","title":"Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers","created":"2018-09-10","cited_by_count":22},{"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":"2203.13733","title":"Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning","created":"2022-03-15","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":"2201.13388","title":"Compositional Multi-Object Reinforcement Learning with Linear Relation Networks","created":"2022-01-31","cited_by_count":19},{"id":"2103.10574","title":"Hopper: Multi-hop Transformer for Spatiotemporal Reasoning","created":"2021-03-19","cited_by_count":12},{"id":"2010.15195","title":"Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in a First-person Simulated 3D Environment","created":"2020-10-28","cited_by_count":8},{"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":"2006.12480","title":"Self-supervised Video Object Segmentation","created":"2020-06-22","cited_by_count":5}],"next_cursor":null}