{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"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":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"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":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"2310.00426","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","created":"2023-09-30","cited_by_count":864},{"id":"2004.07728","title":"Image Quality Assessment: Unifying Structure and Texture Similarity","created":"2020-04-16","cited_by_count":811},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"1905.02716","title":"EDVR: Video Restoration with Enhanced Deformable Convolutional Networks","created":"2019-05-07","cited_by_count":494},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"2205.04437","title":"Activating More Pixels in Image Super-Resolution Transformer","created":"2022-05-09","cited_by_count":438},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"2104.13371","title":"BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment","created":"2021-04-27","cited_by_count":342},{"id":"2211.04894","title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","created":"2022-11-09","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":"2405.08748","title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","created":"2024-05-14","cited_by_count":298},{"id":"2401.13627","title":"Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild","created":"2024-01-24","cited_by_count":286},{"id":"2206.11253","title":"Towards Robust Blind Face Restoration with Codebook Lookup Transformer","created":"2022-06-22","cited_by_count":231},{"id":"2307.06304","title":"Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution","created":"2023-07-12","cited_by_count":229},{"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":"2207.02595","title":"FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling","created":"2022-07-06","cited_by_count":179},{"id":"2206.02146","title":"Recurrent Video Restoration Transformer with Guided Deformable Attention","created":"2022-06-05","cited_by_count":170},{"id":"2407.21705","title":"Tora: Trajectory-oriented Diffusion Transformer for Video Generation","created":"2024-07-31","cited_by_count":164},{"id":"1801.04590","title":"Frame-Recurrent Video Super-Resolution","created":"2018-01-14","cited_by_count":160},{"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":"2008.00455","title":"Video Super-Resolution with Recurrent Structure-Detail Network","created":"2020-08-02","cited_by_count":116},{"id":"2312.02139","title":"DiffiT: Diffusion Vision Transformers for Image Generation","created":"2023-12-04","cited_by_count":106},{"id":"2405.20279","title":"CV-VAE: A Compatible Video VAE for Latent Generative Video Models","created":"2024-05-30","cited_by_count":70},{"id":"2206.10810","title":"A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift","created":"2022-06-22","cited_by_count":68},{"id":"2407.07667","title":"VEnhancer: Generative Space-Time Enhancement for Video Generation","created":"2024-07-10","cited_by_count":64},{"id":"2302.02412","title":"Mixture of Diffusers for scene composition and high resolution image generation","created":"2023-02-05","cited_by_count":56},{"id":"2407.13987","title":"RealViformer: Investigating Attention for Real-World Video Super-Resolution","created":"2024-07-19","cited_by_count":33},{"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":"2303.09735","title":"SRFormerV2: Taking a Closer Look at Permuted Self-Attention for Image Super-Resolution","created":"2023-03-17","cited_by_count":18},{"id":"2305.12689","title":"FIT: Far-reaching Interleaved Transformers","created":"2023-05-22","cited_by_count":16}],"next_cursor":null}