{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"2106.10689","title":"NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction","created":"2021-06-20","cited_by_count":1712},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"2011.12948","title":"Nerfies: Deformable Neural Radiance Fields","created":"2020-11-25","cited_by_count":1198},{"id":"2106.12052","title":"Volume Rendering of Neural Implicit Surfaces","created":"2021-06-22","cited_by_count":996},{"id":"2111.11215","title":"Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction","created":"2021-11-22","cited_by_count":964},{"id":"2007.11571","title":"Neural Sparse Voxel Fields","created":"2020-07-22","cited_by_count":959},{"id":"1906.01618","title":"Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations","created":"2019-06-04","cited_by_count":864},{"id":"2011.12100","title":"GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields","created":"2020-11-24","cited_by_count":785},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2102.13090","title":"IBRNet: Learning Multi-View Image-Based Rendering","created":"2021-02-25","cited_by_count":703},{"id":"2007.02442","title":"GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis","created":"2020-07-05","cited_by_count":689},{"id":"2103.13744","title":"KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs","created":"2021-03-25","cited_by_count":673},{"id":"1905.00889","title":"Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines","created":"2019-05-02","cited_by_count":672},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"2103.10380","title":"FastNeRF: High-Fidelity Neural Rendering at 200FPS","created":"2021-03-18","cited_by_count":511},{"id":"2012.03065","title":"Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction","created":"2020-12-05","cited_by_count":467},{"id":"1812.01024","title":"DeepVoxels: Learning Persistent 3D Feature Embeddings","created":"2018-12-03","cited_by_count":405},{"id":"1912.08804","title":"SynSin: End-to-end View Synthesis from a Single Image","created":"2019-12-18","cited_by_count":364},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307},{"id":"1906.07316","title":"DeepView: View Synthesis with Learned Gradient Descent","created":"2019-06-18","cited_by_count":253},{"id":"2012.01714","title":"AutoInt: Automatic Integration for Fast Neural Volume Rendering","created":"2020-12-03","cited_by_count":204},{"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":"1704.06254","title":"Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency","created":"2017-04-20","cited_by_count":177},{"id":"1605.03557","title":"View Synthesis by Appearance Flow","created":"2016-05-11","cited_by_count":172},{"id":"1812.02725","title":"Visual Object Networks: Image Generation with Disentangled 3D Representation","created":"2018-12-06","cited_by_count":124},{"id":"2104.07652","title":"Geometry-Free View Synthesis: Transformers and no 3D Priors","created":"2021-04-15","cited_by_count":100},{"id":"2105.13677","title":"ResT: An Efficient Transformer for Visual Recognition","created":"2021-05-28","cited_by_count":79},{"id":"2203.10157","title":"ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers","created":"2022-03-18","cited_by_count":70},{"id":"2103.16552","title":"Unsupervised Learning of 3D Object Categories from Videos in the Wild","created":"2021-03-30","cited_by_count":67},{"id":"1905.08776","title":"Textured Neural Avatars","created":"2019-05-21","cited_by_count":65},{"id":"1806.06575","title":"RenderNet: A deep convolutional network for differentiable rendering from 3D shapes","created":"2018-06-18","cited_by_count":42},{"id":"2106.01401","title":"Container: Context Aggregation Network","created":"2021-06-02","cited_by_count":37},{"id":"2207.05518","title":"Tracking Objects as Pixel-wise Distributions","created":"2022-07-12","cited_by_count":37},{"id":"2005.11882","title":"Sentiment Analysis: Automatically Detecting Valence, Emotions, and Other Affectual States from Text","created":"2020-05-25","cited_by_count":26},{"id":"2110.00804","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","created":"2021-10-02","cited_by_count":21},{"id":"1812.01387","title":"Estimating 6D Pose From Localizing Designated Surface Keypoints","created":"2018-12-04","cited_by_count":9}],"next_cursor":null}