{"list":"other","total":52,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"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":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"1711.09020","title":"StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation","created":"2017-11-24","cited_by_count":1039},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2106.05735","title":"The Medical Segmentation Decathlon","created":"2021-06-10","cited_by_count":628},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484},{"id":"2211.07804","title":"Diffusion Models for Medical Image Analysis: A Comprehensive Survey","created":"2022-11-14","cited_by_count":273},{"id":"2104.14806","title":"GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions","created":"2021-04-30","cited_by_count":256},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253},{"id":"2207.08208","title":"Unsupervised Medical Image Translation with Adversarial Diffusion Models","created":"2022-07-17","cited_by_count":192},{"id":"2304.09790","title":"AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation","created":"2023-04-19","cited_by_count":180},{"id":"2205.12952","title":"Pretraining is All You Need for Image-to-Image Translation","created":"2022-05-25","cited_by_count":160},{"id":"2207.05876","title":"Adaptive Diffusion Priors for Accelerated MRI Reconstruction","created":"2022-07-12","cited_by_count":118},{"id":"2211.12737","title":"RoentGen: Vision-Language Foundation Model for Chest X-ray Generation","created":"2022-11-23","cited_by_count":89},{"id":"2209.12104","title":"Conversion Between CT and MRI Images Using Diffusion and Score-Matching Models","created":"2022-09-24","cited_by_count":69},{"id":"2402.05210","title":"Anatomically-Controllable Medical Image Generation with Segmentation-Guided Diffusion Models","created":"2024-02-07","cited_by_count":69},{"id":"2303.14081","title":"CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis","created":"2023-03-24","cited_by_count":65},{"id":"2305.16037","title":"GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes","created":"2023-05-25","cited_by_count":64},{"id":"2306.04542","title":"On the Design Fundamentals of Diffusion Models: A Survey","created":"2023-06-07","cited_by_count":60},{"id":"1907.13590","title":"Unsupervised Domain Adaptation via Disentangled Representations: Application to Cross-Modality Liver Segmentation","created":"2019-07-31","cited_by_count":50},{"id":"2307.10094","title":"Make-A-Volume: Leveraging Latent Diffusion Models for Cross-Modality 3D Brain MRI Synthesis","created":"2023-07-19","cited_by_count":43},{"id":"2310.03559","title":"MedSyn: Text-guided Anatomy-aware Synthesis of High-Fidelity 3D CT Images","created":"2023-10-05","cited_by_count":41},{"id":"2304.04106","title":"MedGen3D: A Deep Generative Framework for Paired 3D Image and Mask Generation","created":"2023-04-08","cited_by_count":34},{"id":"2310.14197","title":"Diffusion-based Data Augmentation for Nuclei Image Segmentation","created":"2023-10-22","cited_by_count":31},{"id":"2108.04016","title":"Deep Learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge","created":"2021-08-09","cited_by_count":28},{"id":"2306.14132","title":"DiffMix: Diffusion Model-based Data Synthesis for Nuclei Segmentation and Classification in Imbalanced Pathology Image Datasets","created":"2023-06-25","cited_by_count":28},{"id":"2505.06068","title":"Noise-Consistent Siamese-Diffusion for Medical Image Synthesis and Segmentation","created":"2025-05-09","cited_by_count":23},{"id":"2206.15134","title":"InsMix: Towards Realistic Generative Data Augmentation for Nuclei Instance Segmentation","created":"2022-06-30","cited_by_count":19},{"id":"2005.01969","title":"AlignShift: Bridging the Gap of Imaging Thickness in 3D Anisotropic Volumes","created":"2020-05-05","cited_by_count":13},{"id":"2402.14185","title":"HINT: High-quality INPainting Transformer with Mask-Aware Encoding and Enhanced Attention","created":"2024-02-22","cited_by_count":11},{"id":"2110.14709","title":"Sharp-GAN: Sharpness Loss Regularized GAN for Histopathology Image Synthesis","created":"2021-10-27","cited_by_count":10},{"id":"2501.19084","title":"Laser: Efficient Language-Guided Segmentation in Neural Radiance Fields","created":"2025-01-31","cited_by_count":10},{"id":"2306.12109","title":"DiffuseIR:Diffusion Models For Isotropic Reconstruction of 3D Microscopic Images","created":"2023-06-21","cited_by_count":9},{"id":"2502.14676","title":"BP-SGCN: Behavioral Pseudo-Label Informed Sparse Graph Convolution Network for Pedestrian and Heterogeneous Trajectory Prediction","created":"2025-02-20","cited_by_count":9},{"id":"2505.01888","title":"Rethinking Score Distilling Sampling for 3D Editing and Generation","created":"2025-05-03","cited_by_count":7},{"id":"2301.02069","title":"Deep Learning for Breast MRI Style Transfer with Limited Training Data","created":"2023-01-05","cited_by_count":6},{"id":"2210.05952","title":"3D Brain and Heart Volume Generative Models: A Survey","created":"2022-10-12","cited_by_count":4},{"id":"2403.09363","title":"Sentinel-Guided Zero-Shot Learning: A Collaborative Paradigm without Real Data Exposure","created":"2024-03-14","cited_by_count":4},{"id":"2505.14087","title":"Large-Scale Multi-Character Interaction Synthesis","created":"2025-05-20","cited_by_count":4},{"id":"2407.02675","title":"Depth-Aware Endoscopic Video Inpainting","created":"2024-07-02","cited_by_count":2},{"id":"2503.17530","title":"FMDConv: Fast Multi-Attention Dynamic Convolution via Speed-Accuracy Trade-off","created":"2025-03-21","cited_by_count":1}],"next_cursor":null}