{"list":"other","total":86,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"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":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"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":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"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":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2303.09535","title":"FateZero: Fusing Attentions for Zero-shot Text-based Video Editing","created":"2023-03-16","cited_by_count":466},{"id":"2211.11018","title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","created":"2022-11-20","cited_by_count":465},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"2304.08466","title":"Synthetic Data from Diffusion Models Improves ImageNet Classification","created":"2023-04-17","cited_by_count":327},{"id":"2305.13077","title":"ControlVideo: Training-free Controllable Text-to-Video Generation","created":"2023-05-22","cited_by_count":327},{"id":"2210.07574","title":"Is synthetic data from generative models ready for image recognition?","created":"2022-10-14","cited_by_count":320},{"id":"2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","created":"2023-02-20","cited_by_count":304},{"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":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"2305.10474","title":"Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models","created":"2023-05-17","cited_by_count":285},{"id":"2302.07944","title":"Effective Data Augmentation With Diffusion Models","created":"2023-02-07","cited_by_count":283},{"id":"2303.13744","title":"Conditional Image-to-Video Generation with Latent Flow Diffusion Models","created":"2023-03-24","cited_by_count":181},{"id":"2304.09790","title":"AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation","created":"2023-04-19","cited_by_count":180},{"id":"2212.08420","title":"Fake it till you make it: Learning transferable representations from synthetic ImageNet clones","created":"2022-12-16","cited_by_count":172},{"id":"2310.05922","title":"FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing","created":"2023-10-09","cited_by_count":167},{"id":"2004.03548","title":"Temporal Pyramid Network for Action Recognition","created":"2020-04-07","cited_by_count":163},{"id":"2408.00874","title":"Medical SAM 2: Segment medical images as video via Segment Anything Model 2","created":"2024-08-01","cited_by_count":154},{"id":"2402.04324","title":"ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation","created":"2024-02-06","cited_by_count":132},{"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":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116},{"id":"2402.01566","title":"Boximator: Generating Rich and Controllable Motions for Video Synthesis","created":"2024-02-02","cited_by_count":107},{"id":"2304.09218","title":"Generative models improve fairness of medical classifiers under distribution shifts","created":"2023-04-18","cited_by_count":90},{"id":"2305.18453","title":"Conditional Diffusion Models for Semantic 3D Brain MRI Synthesis","created":"2023-05-29","cited_by_count":86},{"id":"2312.00094","title":"Fast ODE-based Sampling for Diffusion Models in Around 5 Steps","created":"2023-11-30","cited_by_count":84},{"id":"2312.17681","title":"FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis","created":"2023-12-29","cited_by_count":79},{"id":"2312.16693","title":"I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models","created":"2023-12-27","cited_by_count":70},{"id":"2402.19470","title":"Towards Generalizable Tumor Synthesis","created":"2024-02-29","cited_by_count":65},{"id":"2310.15160","title":"FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models","created":"2023-10-23","cited_by_count":61},{"id":"2310.10769","title":"LAMP: Learn A Motion Pattern for Few-Shot-Based Video Generation","created":"2023-10-16","cited_by_count":59},{"id":"2403.12034","title":"VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models","created":"2024-03-18","cited_by_count":56},{"id":"2012.03457","title":"VideoMix: Rethinking Data Augmentation for Video Classification","created":"2020-12-07","cited_by_count":55},{"id":"2403.11050","title":"Endora: Video Generation Models as Endoscopy Simulators","created":"2024-03-17","cited_by_count":55},{"id":"2007.09507","title":"Backpropagated Gradient Representations for Anomaly Detection","created":"2020-07-18","cited_by_count":54},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52},{"id":"2204.06929","title":"Sketch guided and progressive growing GAN for realistic and editable ultrasound image synthesis","created":"2022-04-14","cited_by_count":42},{"id":"2401.01827","title":"Moonshot: Towards Controllable Video Generation and Editing with Multimodal Conditions","created":"2024-01-03","cited_by_count":42},{"id":"2405.20469","title":"Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images","created":"2024-05-30","cited_by_count":41},{"id":"2304.14660","title":"Segment Anything Model for Medical Images?","created":"2023-04-28","cited_by_count":39},{"id":"2103.10292","title":"How I failed machine learning in medical imaging -- shortcomings and recommendations","created":"2021-03-18","cited_by_count":37},{"id":"2303.12644","title":"Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis","created":"2023-03-22","cited_by_count":32},{"id":"2402.05937","title":"InstaGen: Enhancing Object Detection by Training on Synthetic Dataset","created":"2024-02-08","cited_by_count":26},{"id":"2403.12448","title":"Do Generated Data Always Help Contrastive Learning?","created":"2024-03-19","cited_by_count":25},{"id":"2310.12868","title":"DiffBoost: Enhancing Medical Image Segmentation via Text-Guided Diffusion Model","created":"2023-10-19","cited_by_count":23},{"id":"2305.17098","title":"ControlVideo: Conditional Control for One-shot Text-driven Video Editing and Beyond","created":"2023-05-26","cited_by_count":22},{"id":"2308.12453","title":"Augmenting medical image classifiers with synthetic data from latent diffusion models","created":"2023-08-23","cited_by_count":22},{"id":"2311.09402","title":"Synthetically Enhanced: Unveiling Synthetic Data's Potential in Medical Imaging Research","created":"2023-11-15","cited_by_count":18},{"id":"2401.05159","title":"Derm-T2IM: Harnessing Synthetic Skin Lesion Data via Stable Diffusion Models for Enhanced Skin Disease Classification using ViT and CNN","created":"2024-01-10","cited_by_count":15},{"id":"2407.06250","title":"FairDiff: Fair Segmentation with Point-Image Diffusion","created":"2024-07-08","cited_by_count":15},{"id":"2306.02544","title":"Fourier Test-time Adaptation with Multi-level Consistency for Robust Classification","created":"2023-06-05","cited_by_count":12},{"id":"2207.00476","title":"Online Reflective Learning for Robust Medical Image Segmentation","created":"2022-07-01","cited_by_count":8},{"id":"2402.04031","title":"Polyp-DDPM: Diffusion-Based Semantic Polyp Synthesis for Enhanced Segmentation","created":"2024-02-06","cited_by_count":8},{"id":"2310.07131","title":"Echocardiography video synthesis from end diastolic semantic map via diffusion model","created":"2023-10-11","cited_by_count":7},{"id":"2406.05421","title":"3D MRI Synthesis with Slice-Based Latent Diffusion Models: Improving Tumor Segmentation Tasks in Data-Scarce Regimes","created":"2024-06-08","cited_by_count":6},{"id":"2408.03035","title":"Training-Free Condition Video Diffusion Models for single frame Spatial-Semantic Echocardiogram Synthesis","created":"2024-08-06","cited_by_count":6},{"id":"2408.05985","title":"Diffuse-UDA: Addressing Unsupervised Domain Adaptation in Medical Image Segmentation with Appearance and Structure Aligned Diffusion Models","created":"2024-08-12","cited_by_count":6},{"id":"2403.17770","title":"CT Synthesis with Conditional Diffusion Models for Abdominal Lymph Node Segmentation","created":"2024-03-26","cited_by_count":5},{"id":"2405.16516","title":"Memory-efficient High-resolution OCT Volume Synthesis with Cascaded Amortized Latent Diffusion Models","created":"2024-05-26","cited_by_count":5},{"id":"2306.02548","title":"Inflated 3D Convolution-Transformer for Weakly-supervised Carotid Stenosis Grading with Ultrasound Videos","created":"2023-06-05","cited_by_count":3},{"id":"2407.19284","title":"Optimizing Synthetic Data for Enhanced Pancreatic Tumor Segmentation","created":"2024-07-27","cited_by_count":3},{"id":"2407.16634","title":"Knowledge-driven AI-generated data for accurate and interpretable breast ultrasound diagnoses","created":"2024-07-23","cited_by_count":2}],"next_cursor":null}