{"list":"other","total":57,"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":"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"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":"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":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"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":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"1711.09078","title":"Video Enhancement with Task-Oriented Flow","created":"2017-11-24","cited_by_count":619},{"id":"1711.06077","title":"The Perception-Distortion Tradeoff","created":"2017-11-16","cited_by_count":587},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"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":"1905.02716","title":"EDVR: Video Restoration with Enhanced Deformable Convolutional Networks","created":"2019-05-07","cited_by_count":494},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"2311.04145","title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","created":"2023-11-07","cited_by_count":350},{"id":"2104.13371","title":"BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment","created":"2021-04-27","cited_by_count":342},{"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":"2310.11440","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","created":"2023-10-17","cited_by_count":340},{"id":"2303.08320","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","created":"2023-03-15","cited_by_count":331},{"id":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322},{"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":"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":"1808.00449","title":"Learning Blind Video Temporal Consistency","created":"2018-08-01","cited_by_count":253},{"id":"2201.12288","title":"VRT: A Video Restoration Transformer","created":"2022-01-28","cited_by_count":220},{"id":"2206.02146","title":"Recurrent Video Restoration Transformer with Guided Deformable Attention","created":"2022-06-05","cited_by_count":170},{"id":"1801.04590","title":"Frame-Recurrent Video Super-Resolution","created":"2018-01-14","cited_by_count":160},{"id":"2405.04233","title":"Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models","created":"2024-05-07","cited_by_count":160},{"id":"1611.05250","title":"Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation","created":"2016-11-16","cited_by_count":156},{"id":"1903.10128","title":"Recurrent Back-Projection Network for Video Super-Resolution","created":"2019-03-25","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":"2403.06098","title":"VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models","created":"2024-03-10","cited_by_count":131},{"id":"2008.00455","title":"Video Super-Resolution with Recurrent Structure-Detail Network","created":"2020-08-02","cited_by_count":116},{"id":"2007.11803","title":"MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution","created":"2020-07-23","cited_by_count":89},{"id":"2311.16845","title":"Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration","created":"2023-11-28","cited_by_count":88},{"id":"2312.04557","title":"GenTron: Diffusion Transformers for Image and Video Generation","created":"2023-12-07","cited_by_count":82},{"id":"2207.08494","title":"Rethinking Alignment in Video Super-Resolution Transformers","created":"2022-07-18","cited_by_count":71},{"id":"1909.08080","title":"Efficient Video Super-Resolution through Recurrent Latent Space Propagation","created":"2019-09-17","cited_by_count":69},{"id":"2407.07667","title":"VEnhancer: Generative Space-Time Enhancement for Video Generation","created":"2024-07-10","cited_by_count":64},{"id":"2403.17870","title":"Boosting Diffusion Models with Moving Average Sampling in Frequency Domain","created":"2024-03-26","cited_by_count":55},{"id":"2104.10642","title":"Temporal Modulation Network for Controllable Space-Time Video Super-Resolution","created":"2021-04-21","cited_by_count":54},{"id":"2205.07514","title":"Residual Local Feature Network for Efficient Super-Resolution","created":"2022-05-16","cited_by_count":53},{"id":"2003.04716","title":"Deep Blind Video Super-resolution","created":"2020-03-10","cited_by_count":44},{"id":"2112.05561","title":"Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions","created":"2021-12-10","cited_by_count":39},{"id":"2407.13987","title":"RealViformer: Investigating Attention for Real-World Video Super-Resolution","created":"2024-07-19","cited_by_count":33},{"id":"2206.07038","title":"AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos","created":"2022-06-14","cited_by_count":23},{"id":"2411.17470","title":"Towards Precise Scaling Laws for Video Diffusion Transformers","created":"2024-11-25","cited_by_count":20},{"id":"2401.10404","title":"Inflation with Diffusion: Efficient Temporal Adaptation for Text-to-Video Super-Resolution","created":"2024-01-18","cited_by_count":9}],"next_cursor":null}