{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"1701.05517","title":"PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications","created":"2017-01-19","cited_by_count":417},{"id":"1603.04992","title":"Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue","created":"2016-03-16","cited_by_count":368},{"id":"1912.08804","title":"SynSin: End-to-end View Synthesis from a Single Image","created":"2019-12-18","cited_by_count":364},{"id":"1906.08240","title":"Neural Point-Based Graphics","created":"2019-06-19","cited_by_count":327},{"id":"1511.01844","title":"A note on the evaluation of generative models","created":"2015-11-05","cited_by_count":292},{"id":"2003.05534","title":"Softmax Splatting for Video Frame Interpolation","created":"2020-03-11","cited_by_count":279},{"id":"2004.11364","title":"Single-View View Synthesis with Multiplane Images","created":"2020-04-23","cited_by_count":263},{"id":"1906.07316","title":"DeepView: View Synthesis with Learned Gradient Descent","created":"2019-06-18","cited_by_count":253},{"id":"2012.09855","title":"Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image","created":"2020-12-17","cited_by_count":243},{"id":"2008.05511","title":"Free View Synthesis","created":"2020-08-12","cited_by_count":231},{"id":"1606.01933","title":"A Decomposable Attention Model for Natural Language Inference","created":"2016-06-06","cited_by_count":215},{"id":"2004.04727","title":"3D Photography using Context-aware Layered Depth Inpainting","created":"2020-04-09","cited_by_count":206},{"id":"1903.05789","title":"Diagnosing and Enhancing VAE Models","created":"2019-03-14","cited_by_count":193},{"id":"1905.00413","title":"Pushing the Boundaries of View Extrapolation with Multiplane Images","created":"2019-05-01","cited_by_count":191},{"id":"1506.06825","title":"DeepStereo: Learning to Predict New Views from the World's Imagery","created":"2015-06-22","cited_by_count":185},{"id":"1611.02731","title":"Variational Lossy Autoencoder","created":"2016-11-08","cited_by_count":176},{"id":"1605.03557","title":"View Synthesis by Appearance Flow","created":"2016-05-11","cited_by_count":172},{"id":"2011.07233","title":"Stable View Synthesis","created":"2020-11-14","cited_by_count":165},{"id":"1609.02974","title":"Learning-Based View Synthesis for Light Field Cameras","created":"2016-09-09","cited_by_count":145},{"id":"1909.05483","title":"3D Ken Burns Effect from a Single Image","created":"2019-09-12","cited_by_count":128},{"id":"1503.03167","title":"Deep Convolutional Inverse Graphics Network","created":"2015-03-11","cited_by_count":121},{"id":"1904.04290","title":"Neural Rerendering in the Wild","created":"2019-04-08","cited_by_count":121},{"id":"1812.04777","title":"Extreme View Synthesis","created":"2018-12-12","cited_by_count":94},{"id":"2012.09854","title":"Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis from a Single Image","created":"2020-12-17","cited_by_count":77},{"id":"1604.03650","title":"Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks","created":"2016-04-13","cited_by_count":73},{"id":"2007.15194","title":"Crowdsampling the Plenoptic Function","created":"2020-07-30","cited_by_count":62},{"id":"1708.03292","title":"Learning to Synthesize a 4D RGBD Light Field from a Single Image","created":"2017-08-10","cited_by_count":60},{"id":"1703.02921","title":"Transformation-Grounded Image Generation Network for Novel 3D View Synthesis","created":"2017-03-08","cited_by_count":59},{"id":"1511.06702","title":"Multi-view 3D Models from Single Images with a Convolutional Network","created":"2015-11-20","cited_by_count":58},{"id":"2004.13166","title":"A Disentangling Invertible Interpretation Network for Explaining Latent Representations","created":"2020-04-27","cited_by_count":57},{"id":"2008.12298","title":"One Shot 3D Photography","created":"2020-08-27","cited_by_count":45},{"id":"1411.5928","title":"Learning to Generate Chairs, Tables and Cars with Convolutional Networks","created":"2014-11-21","cited_by_count":26},{"id":"1601.00706","title":"Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis","created":"2016-01-05","cited_by_count":24},{"id":"1807.08776","title":"Peeking Behind Objects: Layered Depth Prediction from a Single Image","created":"2018-07-23","cited_by_count":23},{"id":"1804.06008","title":"Geometry-aware Deep Network for Single-Image Novel View Synthesis","created":"2018-04-17","cited_by_count":19}],"next_cursor":null}