{"list":"other","total":65,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1606.06650","title":"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","created":"2016-06-21","cited_by_count":1476},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"1601.06759","title":"Pixel Recurrent Neural Networks","created":"2016-01-25","cited_by_count":816},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484},{"id":"1609.02612","title":"Generating Videos with Scene Dynamics","created":"2016-09-08","cited_by_count":376},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"1609.08675","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","created":"2016-09-27","cited_by_count":324},{"id":"2205.09853","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","created":"2022-05-19","cited_by_count":309},{"id":"2112.14683","title":"StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2","created":"2021-12-29","cited_by_count":301},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244},{"id":"1611.06624","title":"Temporal Generative Adversarial Nets with Singular Value Clipping","created":"2016-11-21","cited_by_count":198},{"id":"1906.02634","title":"Scaling Autoregressive Video Models","created":"2019-06-06","cited_by_count":190},{"id":"2202.10571","title":"Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks","created":"2022-02-21","cited_by_count":186},{"id":"1905.09883","title":"Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit","created":"2019-05-23","cited_by_count":176},{"id":"2104.15069","title":"A Good Image Generator Is What You Need for High-Resolution Video Synthesis","created":"2021-04-30","cited_by_count":163},{"id":"2012.09988","title":"Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations","created":"2020-12-18","cited_by_count":155},{"id":"1710.05268","title":"Self-Supervised Visual Planning with Temporal Skip Connections","created":"2017-10-15","cited_by_count":139},{"id":"2206.07696","title":"Diffusion Models for Video Prediction and Infilling","created":"2022-06-15","cited_by_count":135},{"id":"1811.09245","title":"Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN","created":"2018-11-22","cited_by_count":120},{"id":"2206.11894","title":"MaskViT: Masked Visual Pre-Training for Video Prediction","created":"2022-06-23","cited_by_count":114},{"id":"2206.03429","title":"Generating Long Videos of Dynamic Scenes","created":"2022-06-07","cited_by_count":113},{"id":"2104.03310","title":"Regularizing Generative Adversarial Networks under Limited Data","created":"2021-04-07","cited_by_count":107},{"id":"2006.10704","title":"Latent Video Transformer","created":"2020-06-18","cited_by_count":106},{"id":"2012.15833","title":"Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade","created":"2020-12-31","cited_by_count":99},{"id":"2106.13195","title":"FitVid: Overfitting in Pixel-Level Video Prediction","created":"2021-06-24","cited_by_count":87},{"id":"2210.00990","title":"Visual Prompt Tuning for Generative Transfer Learning","created":"2022-10-03","cited_by_count":75},{"id":"2107.08037","title":"CCVS: Context-aware Controllable Video Synthesis","created":"2021-07-16","cited_by_count":69},{"id":"2112.05112","title":"BLT: Bidirectional Layout Transformer for Controllable Layout Generation","created":"2021-12-09","cited_by_count":69},{"id":"2003.04035","title":"Transformation-based Adversarial Video Prediction on Large-Scale Data","created":"2020-03-09","cited_by_count":66},{"id":"2209.04439","title":"Improved Masked Image Generation with Token-Critic","created":"2022-09-09","cited_by_count":64},{"id":"1912.08860","title":"Lower Dimensional Kernels for Video Discriminators","created":"2019-12-18","cited_by_count":37},{"id":"2203.02573","title":"Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning","created":"2022-03-04","cited_by_count":37},{"id":"2203.09494","title":"Transframer: Arbitrary Frame Prediction with Generative Models","created":"2022-03-17","cited_by_count":37},{"id":"1810.02419","title":"Towards High Resolution Video Generation with Progressive Growing of Sliced Wasserstein GANs","created":"2018-10-04","cited_by_count":36},{"id":"2105.14211","title":"M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformers","created":"2021-05-29","cited_by_count":36}],"next_cursor":null}