{"list":"other","total":72,"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":"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"2206.00927","title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","created":"2022-06-02","cited_by_count":1979},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1606.06650","title":"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","created":"2016-06-21","cited_by_count":1476},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"1603.06560","title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","created":"2016-03-21","cited_by_count":699},{"id":"2204.04799","title":"DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning","created":"2022-04-10","cited_by_count":642},{"id":"2206.01714","title":"Compositional Visual Generation with Composable Diffusion Models","created":"2022-06-03","cited_by_count":624},{"id":"2111.15640","title":"Diffusion Autoencoders: Toward a Meaningful and Decodable Representation","created":"2021-11-30","cited_by_count":449},{"id":"1808.06601","title":"Video-to-Video Synthesis","created":"2018-08-20","cited_by_count":390},{"id":"1808.07371","title":"Everybody Dance Now","created":"2018-08-22","cited_by_count":315},{"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":"2104.14806","title":"GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions","created":"2021-04-30","cited_by_count":256},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255},{"id":"1710.11252","title":"Stochastic Variational Video Prediction","created":"2017-10-30","cited_by_count":234},{"id":"1910.12713","title":"Few-shot Video-to-Video Synthesis","created":"2019-10-28","cited_by_count":197},{"id":"1807.10550","title":"X2Face: A network for controlling face generation by using images, audio, and pose codes","created":"2018-07-27","cited_by_count":189},{"id":"2202.10571","title":"Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks","created":"2022-02-21","cited_by_count":186},{"id":"2203.09043","title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","created":"2022-03-17","cited_by_count":175},{"id":"2106.00132","title":"On Fast Sampling of Diffusion Probabilistic Models","created":"2021-05-31","cited_by_count":170},{"id":"1710.00421","title":"Video Generation From Text","created":"2017-10-01","cited_by_count":154},{"id":"1803.09179","title":"FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces","created":"2018-03-24","cited_by_count":119},{"id":"1709.07592","title":"Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks","created":"2017-09-22","cited_by_count":89},{"id":"2112.02815","title":"Make It Move: Controllable Image-to-Video Generation with Text Descriptions","created":"2021-12-06","cited_by_count":88},{"id":"1804.08264","title":"To Create What You Tell: Generating Videos from Captions","created":"2018-04-23","cited_by_count":84},{"id":"2007.08509","title":"World-Consistent Video-to-Video Synthesis","created":"2020-07-16","cited_by_count":69},{"id":"1807.11152","title":"Pose Guided Human Video Generation","created":"2018-07-30","cited_by_count":67},{"id":"1807.09755","title":"Flow-Grounded Spatial-Temporal Video Prediction from Still Images","created":"2018-07-25","cited_by_count":55},{"id":"2011.15128","title":"Animating Pictures with Eulerian Motion Fields","created":"2020-11-30","cited_by_count":55},{"id":"2012.04324","title":"Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning","created":"2020-12-08","cited_by_count":55},{"id":"1903.04480","title":"Video Generation from Single Semantic Label Map","created":"2019-03-11","cited_by_count":54},{"id":"2105.04551","title":"Stochastic Image-to-Video Synthesis using cINNs","created":"2021-05-10","cited_by_count":49},{"id":"2112.03051","title":"Controllable Animation of Fluid Elements in Still Images","created":"2021-12-06","cited_by_count":45},{"id":"1611.10314","title":"Sync-DRAW: Automatic Video Generation using Deep Recurrent Attentive Architectures","created":"2016-11-30","cited_by_count":44},{"id":"2107.02790","title":"iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis","created":"2021-07-06","cited_by_count":42},{"id":"2106.11303","title":"Understanding Object Dynamics for Interactive Image-to-Video Synthesis","created":"2021-06-21","cited_by_count":38},{"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":"1910.02027","title":"Unsupervised Keypoint Learning for Guiding Class-Conditional Video Prediction","created":"2019-10-04","cited_by_count":36},{"id":"2203.15799","title":"StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis","created":"2022-03-29","cited_by_count":33},{"id":"2205.15996","title":"Text2Human: Text-Driven Controllable Human Image Generation","created":"2022-05-31","cited_by_count":31},{"id":"1708.05980","title":"Attentive Semantic Video Generation using Captions","created":"2017-08-20","cited_by_count":28},{"id":"1803.08085","title":"Probabilistic Video Generation using Holistic Attribute Control","created":"2018-03-21","cited_by_count":24},{"id":"2004.12361","title":"Evaluation Metrics for Conditional Image Generation","created":"2020-04-26","cited_by_count":19},{"id":"2210.01559","title":"Cross-identity Video Motion Retargeting with Joint Transformation and Synthesis","created":"2022-10-02","cited_by_count":10},{"id":"2107.04240","title":"Deep Image Synthesis from Intuitive User Input: A Review and Perspectives","created":"2021-07-09","cited_by_count":8}],"next_cursor":null}