{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"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":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"1711.06077","title":"The Perception-Distortion Tradeoff","created":"2017-11-16","cited_by_count":587},{"id":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"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":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346},{"id":"1605.07157","title":"Unsupervised Learning for Physical Interaction through Video Prediction","created":"2016-05-23","cited_by_count":260},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"id":"1802.07687","title":"Stochastic Video Generation with a Learned Prior","created":"2018-02-21","cited_by_count":245},{"id":"1907.13052","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","created":"2019-07-30","cited_by_count":227},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"2001.02407","title":"SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition","created":"2020-01-08","cited_by_count":190},{"id":"2103.09504","title":"PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning","created":"2021-03-17","cited_by_count":182},{"id":"1804.01523","title":"Stochastic Adversarial Video Prediction","created":"2018-04-04","cited_by_count":173},{"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":"1509.06113","title":"Deep Spatial Autoencoders for Visuomotor Learning","created":"2015-09-21","cited_by_count":153},{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147},{"id":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147},{"id":"1710.05268","title":"Self-Supervised Visual Planning with Temporal Skip Connections","created":"2017-10-15","cited_by_count":139},{"id":"2205.14065","title":"Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos","created":"2022-05-27","cited_by_count":139},{"id":"1908.05656","title":"PHYRE: A New Benchmark for Physical Reasoning","created":"2019-08-15","cited_by_count":137},{"id":"1806.07823","title":"Unsupervised Learning of Object Landmarks through Conditional Image Generation","created":"2018-06-20","cited_by_count":114},{"id":"1910.12827","title":"Entity Abstraction in Visual Model-Based Reinforcement Learning","created":"2019-10-28","cited_by_count":110},{"id":"1906.11883","title":"Unsupervised Learning of Object Keypoints for Perception and Control","created":"2019-06-19","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":"1906.07889","title":"Unsupervised Learning of Object Structure and Dynamics from Videos","created":"2019-06-19","cited_by_count":92},{"id":"2206.06922","title":"Object Scene Representation Transformer","created":"2022-06-14","cited_by_count":90},{"id":"1604.01802","title":"Learning to Track at 100 FPS with Deep Regression Networks","created":"2016-04-06","cited_by_count":89},{"id":"1704.05831","title":"Learning to Generate Long-term Future via Hierarchical Prediction","created":"2017-04-19","cited_by_count":88},{"id":"1911.01655","title":"High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks","created":"2019-11-05","cited_by_count":88},{"id":"2007.00631","title":"Causal Discovery in Physical Systems from Videos","created":"2020-07-01","cited_by_count":77},{"id":"2103.04174","title":"Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction","created":"2021-03-06","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":"2106.03849","title":"SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition","created":"2021-06-07","cited_by_count":69},{"id":"2103.01950","title":"Predicting Video with VQVAE","created":"2021-03-02","cited_by_count":61},{"id":"2302.04419","title":"An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning","created":"2023-02-09","cited_by_count":49},{"id":"1910.02425","title":"Structured Object-Aware Physics Prediction for Video Modeling and Planning","created":"2019-10-06","cited_by_count":43},{"id":"2203.09494","title":"Transframer: Arbitrary Frame Prediction with Generative Models","created":"2022-03-17","cited_by_count":37},{"id":"1910.02027","title":"Unsupervised Keypoint Learning for Guiding Class-Conditional Video Prediction","created":"2019-10-04","cited_by_count":36},{"id":"2104.14553","title":"MarioNette: Self-Supervised Sprite Learning","created":"2021-04-29","cited_by_count":35},{"id":"2006.07034","title":"Benchmarking Unsupervised Object Representations for Video Sequences","created":"2020-06-12","cited_by_count":27},{"id":"2107.09240","title":"Generative Video Transformer: Can Objects be the Words?","created":"2021-07-20","cited_by_count":24},{"id":"2112.05121","title":"Self-Supervised Keypoint Discovery in Behavioral Videos","created":"2021-12-09","cited_by_count":23},{"id":"1910.05231","title":"R-SQAIR: Relational Sequential Attend, Infer, Repeat","created":"2019-10-11","cited_by_count":21},{"id":"1812.08985","title":"Non-Adversarial Image Synthesis with Generative Latent Nearest Neighbors","created":"2018-12-21","cited_by_count":19},{"id":"2205.15821","title":"Unsupervised Image Representation Learning with Deep Latent Particles","created":"2022-05-31","cited_by_count":19},{"id":"2302.11850","title":"Object-Centric Video Prediction via Decoupling of Object Dynamics and Interactions","created":"2023-02-23","cited_by_count":19},{"id":"2109.04150","title":"Self-supervised Reinforcement Learning with Independently Controllable Subgoals","created":"2021-09-09","cited_by_count":16},{"id":"2107.13170","title":"Accurate Grid Keypoint Learning for Efficient Video Prediction","created":"2021-07-28","cited_by_count":13}],"next_cursor":null}