{"list":"other","total":53,"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"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":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"1707.02921","title":"Enhanced Deep Residual Networks for Single Image Super-Resolution","created":"2017-07-10","cited_by_count":1552},{"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":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"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":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"2310.04378","title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","created":"2023-10-06","cited_by_count":846},{"id":"2004.07728","title":"Image Quality Assessment: Unifying Structure and Texture Similarity","created":"2020-04-16","cited_by_count":811},{"id":"1611.01704","title":"End-to-end Optimized Image Compression","created":"2016-11-05","cited_by_count":696},{"id":"1711.06077","title":"The Perception-Distortion Tradeoff","created":"2017-11-16","cited_by_count":587},{"id":"2412.07772","title":"From Slow Bidirectional to Fast Autoregressive Video Diffusion Models","created":"2024-12-10","cited_by_count":433},{"id":"1804.02815","title":"Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform","created":"2018-04-09","cited_by_count":371},{"id":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341},{"id":"2006.09965","title":"High-Fidelity Generative Image Compression","created":"2020-06-17","cited_by_count":338},{"id":"1812.00101","title":"DVC: An End-to-end Deep Video Compression Framework","created":"2018-11-30","cited_by_count":332},{"id":"2006.10685","title":"Deep Learning Enabled Semantic Communication Systems","created":"2020-06-18","cited_by_count":292},{"id":"2109.15047","title":"Deep Contextual Video Compression","created":"2021-09-30","cited_by_count":221},{"id":"1804.02958","title":"Generative Adversarial Networks for Extreme Learned Image Compression","created":"2018-04-09","cited_by_count":219},{"id":"2105.09600","title":"FVC: A New Framework towards Deep Video Compression in Feature Space","created":"2021-05-20","cited_by_count":153},{"id":"1502.03143","title":"Benchmarking in Manipulation Research: The YCB Object and Model Set and Benchmarking Protocols","created":"2015-02-10","cited_by_count":99},{"id":"2502.20762","title":"Towards Practical Real-Time Neural Video Compression","created":"2025-02-28","cited_by_count":80},{"id":"2312.16693","title":"I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models","created":"2023-12-27","cited_by_count":70},{"id":"2109.03082","title":"Perceptual Learned Video Compression with Recurrent Conditional GAN","created":"2021-09-07","cited_by_count":41},{"id":"2208.04094","title":"Towards Semantic Communications: Deep Learning-Based Image Semantic Coding","created":"2022-08-08","cited_by_count":36},{"id":"1912.06348","title":"Learned Video Compression via Joint Spatial-Temporal Correlation Exploration","created":"2019-12-13","cited_by_count":28},{"id":"2505.16177","title":"Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression","created":"2025-05-22","cited_by_count":25},{"id":"2012.00346","title":"Ultra-low bitrate video conferencing using deep image animation","created":"2020-12-01","cited_by_count":24},{"id":"2512.20194","title":"Generative Latent Coding for Ultra-Low Bitrate Image Compression","created":"2025-12-23","cited_by_count":23},{"id":"2109.10849","title":"DVC-P: Deep Video Compression with Perceptual Optimizations","created":"2021-09-22","cited_by_count":13},{"id":"2508.07682","title":"DiffVC-OSD: One-Step Diffusion-based Perceptual Neural Video Compression Framework","created":"2025-08-11","cited_by_count":11},{"id":"2510.09987","title":"Generative Latent Video Compression","created":"2025-10-11","cited_by_count":11},{"id":"2411.15798","title":"M3-CVC: Controllable Video Compression with Multimodal Generative Models","created":"2024-11-24","cited_by_count":10},{"id":"2507.07633","title":"T-GVC: Trajectory-Guided Generative Video Coding at Ultra-Low Bitrates","created":"2025-07-10","cited_by_count":10},{"id":"2312.07126","title":"Deep Hierarchical Video Compression","created":"2023-12-12","cited_by_count":9},{"id":"2502.13838","title":"Generative Video Semantic Communication via Multimodal Semantic Fusion with Large Model","created":"2025-02-19","cited_by_count":9},{"id":"2412.13646","title":"Transmit What You Need: Task-Adaptive Semantic Communications for Visual Information","created":"2024-12-18","cited_by_count":4},{"id":"2506.16572","title":"Single-step Diffusion for Image Compression at Ultra-Low Bitrates","created":"2025-06-19","cited_by_count":4},{"id":"2509.06904","title":"BIR-Adapter: A parameter-efficient diffusion adapter for blind image restoration","created":"2025-09-08","cited_by_count":2}],"next_cursor":null}