{"list":"other","total":71,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"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":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"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":"1912.12180","title":"Axial Attention in Multidimensional Transformers","created":"2019-12-20","cited_by_count":358},{"id":"2308.01898","title":"UniSim: A Neural Closed-Loop Sensor Simulator","created":"2023-08-03","cited_by_count":297},{"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":"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":"2311.02077","title":"EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision","created":"2023-11-03","cited_by_count":217},{"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":"2206.07764","title":"SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos","created":"2022-06-15","cited_by_count":166},{"id":"2303.14536","title":"SUDS: Scalable Urban Dynamic Scenes","created":"2023-03-25","cited_by_count":151},{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147},{"id":"1803.04831","title":"Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN","created":"2018-03-13","cited_by_count":143},{"id":"2205.14065","title":"Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos","created":"2022-05-27","cited_by_count":139},{"id":"2205.15838","title":"D$^2$NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video","created":"2022-05-31","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":"1708.03498","title":"Neural Expectation Maximization","created":"2017-08-11","cited_by_count":123},{"id":"2306.04988","title":"StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Views","created":"2023-06-08","cited_by_count":120},{"id":"2104.00587","title":"NeRF-VAE: A Geometry Aware 3D Scene Generative Model","created":"2021-04-01","cited_by_count":112},{"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":"2107.07905","title":"Unsupervised Discovery of Object Radiance Fields","created":"2021-07-16","cited_by_count":101},{"id":"2206.06922","title":"Object Scene Representation Transformer","created":"2022-06-14","cited_by_count":90},{"id":"2303.10834","title":"Object-Centric Slot Diffusion","created":"2023-03-20","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":"2305.11281","title":"SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models","created":"2023-05-18","cited_by_count":85},{"id":"1710.02224","title":"Dilated Recurrent Neural Networks","created":"2017-10-05","cited_by_count":83},{"id":"2306.04829","title":"Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities","created":"2023-06-07","cited_by_count":78},{"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":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60},{"id":"1803.00144","title":"Learning Longer-term Dependencies in RNNs with Auxiliary Losses","created":"2018-03-01","cited_by_count":58},{"id":"1906.10264","title":"Sequential Neural Processes","created":"2019-06-24","cited_by_count":55},{"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":"2211.14306","title":"RUST: Latent Neural Scene Representations from Unposed Imagery","created":"2022-11-25","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":"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":"2306.00600","title":"Rotating Features for Object Discovery","created":"2023-06-01","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":"2211.08458","title":"Latent Bottlenecked Attentive Neural Processes","created":"2022-11-15","cited_by_count":26},{"id":"2004.00642","title":"Object-Centric Image Generation with Factored Depths, Locations, and Appearances","created":"2020-04-01","cited_by_count":20},{"id":"2305.15001","title":"Contrastive Training of Complex-Valued Autoencoders for Object Discovery","created":"2023-05-24","cited_by_count":16},{"id":"2306.08068","title":"DORSal: Diffusion for Object-centric Representations of Scenes et al","created":"2023-06-13","cited_by_count":16},{"id":"2006.15987","title":"Robustifying Sequential Neural Processes","created":"2020-06-29","cited_by_count":15},{"id":"2203.13573","title":"Unsupervised Learning of Temporal Abstractions with Slot-based Transformers","created":"2022-03-25","cited_by_count":14},{"id":"2310.06020","title":"DyST: Towards Dynamic Neural Scene Representations on Real-World Videos","created":"2023-10-09","cited_by_count":11},{"id":"2111.05393","title":"Object-Centric Representation Learning with Generative Spatial-Temporal Factorization","created":"2021-11-09","cited_by_count":10},{"id":"2210.05519","title":"Robust and Controllable Object-Centric Learning through Energy-based Models","created":"2022-10-11","cited_by_count":7},{"id":"2101.04041","title":"Evaluating Disentanglement of Structured Representations","created":"2021-01-11","cited_by_count":3}],"next_cursor":null}