{"list":"other","total":79,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"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":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"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":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"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":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"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":"2111.09881","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","created":"2021-11-18","cited_by_count":1627},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2107.10833","title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","created":"2021-07-22","cited_by_count":970},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"1511.04587","title":"Accurate Image Super-Resolution Using Very Deep Convolutional Networks","created":"2015-11-14","cited_by_count":903},{"id":"1802.08797","title":"Residual Dense Network for Image Super-Resolution","created":"2018-02-24","cited_by_count":799},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"2108.02938","title":"ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models","created":"2021-08-06","cited_by_count":635},{"id":"1711.09078","title":"Video Enhancement with Task-Oriented Flow","created":"2017-11-24","cited_by_count":619},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"2103.14006","title":"Designing a Practical Degradation Model for Deep Blind Image Super-Resolution","created":"2021-03-25","cited_by_count":529},{"id":"1511.08458","title":"An Introduction to Convolutional Neural Networks","created":"2015-11-26","cited_by_count":514},{"id":"1905.02716","title":"EDVR: Video Restoration with Enhanced Deformable Convolutional Networks","created":"2019-05-07","cited_by_count":494},{"id":"2303.09535","title":"FateZero: Fusing Attentions for Zero-shot Text-based Video Editing","created":"2023-03-16","cited_by_count":466},{"id":"2307.10373","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","created":"2023-07-19","cited_by_count":442},{"id":"2104.13371","title":"BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment","created":"2021-04-27","cited_by_count":342},{"id":"2303.08320","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","created":"2023-03-15","cited_by_count":331},{"id":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327},{"id":"2312.02145","title":"Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation","created":"2023-12-04","cited_by_count":327},{"id":"2303.12688","title":"Pix2Video: Video Editing using Image Diffusion","created":"2023-03-22","cited_by_count":320},{"id":"2012.02181","title":"BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond","created":"2020-12-03","cited_by_count":304},{"id":"2203.16194","title":"FlowFormer: A Transformer Architecture for Optical Flow","created":"2022-03-30","cited_by_count":275},{"id":"1807.04686","title":"Toward Convolutional Blind Denoising of Real Photographs","created":"2018-07-12","cited_by_count":274},{"id":"2306.07954","title":"Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation","created":"2023-06-13","cited_by_count":253},{"id":"1812.02898","title":"TDAN: Temporally Deformable Alignment Network for Video Super-Resolution","created":"2018-12-07","cited_by_count":226},{"id":"2201.12288","title":"VRT: A Video Restoration Transformer","created":"2022-01-28","cited_by_count":220},{"id":"2302.12228","title":"Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models","created":"2023-02-23","cited_by_count":203},{"id":"2206.02146","title":"Recurrent Video Restoration Transformer with Guided Deformable Attention","created":"2022-06-05","cited_by_count":170},{"id":"2310.05922","title":"FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing","created":"2023-10-09","cited_by_count":167},{"id":"2211.12250","title":"Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring","created":"2022-11-22","cited_by_count":165},{"id":"1404.2188","title":"A Convolutional Neural Network for Modelling Sentences","created":"2014-04-08","cited_by_count":163},{"id":"1704.02738","title":"Detail-revealing Deep Video Super-resolution","created":"2017-04-10","cited_by_count":148},{"id":"2111.12704","title":"Investigating Tradeoffs in Real-World Video Super-Resolution","created":"2021-11-24","cited_by_count":134},{"id":"1907.01361","title":"FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation","created":"2019-07-01","cited_by_count":128},{"id":"2106.06847","title":"Video Super-Resolution Transformer","created":"2021-06-12","cited_by_count":121},{"id":"2008.00455","title":"Video Super-Resolution with Recurrent Structure-Detail Network","created":"2020-08-02","cited_by_count":116},{"id":"2303.01237","title":"FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation","created":"2023-03-02","cited_by_count":114},{"id":"2312.04524","title":"RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models","created":"2023-12-07","cited_by_count":114},{"id":"2312.10656","title":"VidToMe: Video Token Merging for Zero-Shot Video Editing","created":"2023-12-17","cited_by_count":113},{"id":"2202.13142","title":"Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors","created":"2022-02-26","cited_by_count":100},{"id":"2007.11803","title":"MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution","created":"2020-07-23","cited_by_count":89},{"id":"1801.09392","title":"Shift-Net: Image Inpainting via Deep Feature Rearrangement","created":"2018-01-29","cited_by_count":87},{"id":"2004.02501","title":"Cascaded Deep Video Deblurring Using Temporal Sharpness Prior","created":"2020-04-06","cited_by_count":85},{"id":"2303.08340","title":"VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation","created":"2023-03-15","cited_by_count":82},{"id":"2009.07265","title":"Understanding Deformable Alignment in Video Super-Resolution","created":"2020-09-15","cited_by_count":78},{"id":"2212.00235","title":"VIDM: Video Implicit Diffusion Models","created":"2022-12-01","cited_by_count":78},{"id":"2206.10810","title":"A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift","created":"2022-06-22","cited_by_count":68},{"id":"1906.11890","title":"DVDnet: A Fast Network for Deep Video Denoising","created":"2019-06-04","cited_by_count":60},{"id":"2403.12962","title":"FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation","created":"2024-03-19","cited_by_count":49},{"id":"2212.07339","title":"Mitigating Artifacts in Real-World Video Super-Resolution Models","created":"2022-12-14","cited_by_count":29},{"id":"2401.03707","title":"FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring","created":"2024-01-08","cited_by_count":28},{"id":"2102.06205","title":"Hybrid Neural Fusion for Full-frame Video Stabilization","created":"2021-02-11","cited_by_count":21},{"id":"2308.10079","title":"MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance","created":"2023-08-19","cited_by_count":17},{"id":"2404.19500","title":"Towards Real-world Video Face Restoration: A New Benchmark","created":"2024-04-30","cited_by_count":6}],"next_cursor":null}