{"list":"other","total":60,"rows":[{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"2008.02268","title":"NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections","created":"2020-08-05","cited_by_count":1232},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2202.05263","title":"Block-NeRF: Scalable Large Scene Neural View Synthesis","created":"2022-02-10","cited_by_count":724},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"1804.07723","title":"Image Inpainting for Irregular Holes Using Partial Convolutions","created":"2018-04-20","cited_by_count":505},{"id":"1710.02410","title":"End-to-end Driving via Conditional Imitation Learning","created":"2017-10-06","cited_by_count":485},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2104.00677","title":"Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis","created":"2021-04-01","cited_by_count":464},{"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":"1912.08804","title":"SynSin: End-to-end View Synthesis from a Single Image","created":"2019-12-18","cited_by_count":364},{"id":"2011.13922","title":"A Recurrent Vision-and-Language BERT for Navigation","created":"2020-11-26","cited_by_count":302},{"id":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"id":"1711.04340","title":"Data Augmentation Generative Adversarial Networks","created":"2017-11-12","cited_by_count":278},{"id":"2110.13309","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","created":"2021-10-25","cited_by_count":271},{"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":"1802.07687","title":"Stochastic Video Generation with a Learned Prior","created":"2018-02-21","cited_by_count":245},{"id":"1904.04195","title":"Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout","created":"2019-04-08","cited_by_count":244},{"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":"1705.02894","title":"Geometric GAN","created":"2017-05-08","cited_by_count":233},{"id":"2002.10638","title":"Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training","created":"2020-02-25","cited_by_count":231},{"id":"1805.09817","title":"Stereo Magnification: Learning View Synthesis using Multiplane Images","created":"2018-05-24","cited_by_count":211},{"id":"2004.04727","title":"3D Photography using Context-aware Layered Depth Inpainting","created":"2020-04-09","cited_by_count":206},{"id":"1708.05375","title":"Learning a Multi-View Stereo Machine","created":"2017-08-17","cited_by_count":194},{"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":"2105.08756","title":"Pathdreamer: A World Model for Indoor Navigation","created":"2021-05-18","cited_by_count":118},{"id":"2010.09304","title":"Language and Visual Entity Relationship Graph for Agent Navigation","created":"2020-10-19","cited_by_count":100},{"id":"2104.07652","title":"Geometry-Free View Synthesis: Transformers and no 3D Priors","created":"2021-04-15","cited_by_count":100},{"id":"2108.05892","title":"PixelSynth: Generating a 3D-Consistent Experience from a Single Image","created":"2021-08-12","cited_by_count":82},{"id":"1903.02547","title":"Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation","created":"2019-03-06","cited_by_count":81},{"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":"2007.08509","title":"World-Consistent Video-to-Video Synthesis","created":"2020-07-16","cited_by_count":69},{"id":"1806.01054","title":"RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation","created":"2018-06-04","cited_by_count":66},{"id":"2203.09457","title":"Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Image","created":"2022-03-17","cited_by_count":55},{"id":"2109.05125","title":"MURAL: Multimodal, Multitask Retrieval Across Languages","created":"2021-09-10","cited_by_count":44},{"id":"2005.03086","title":"Diagnosing the Environment Bias in Vision-and-Language Navigation","created":"2020-05-06","cited_by_count":41},{"id":"2011.03775","title":"Text-to-Image Generation Grounded by Fine-Grained User Attention","created":"2020-11-07","cited_by_count":36},{"id":"1807.08776","title":"Peeking Behind Objects: Layered Depth Prediction from a Single Image","created":"2018-07-23","cited_by_count":23},{"id":"2106.13974","title":"Semantics-aware Multi-modal Domain Translation:From LiDAR Point Clouds to Panoramic Color Images","created":"2021-06-26","cited_by_count":6},{"id":"1904.10795","title":"3D Dynamic Point Cloud Inpainting via Temporal Consistency on Graphs","created":"2019-04-23","cited_by_count":2}],"next_cursor":null}