{"list":"other","total":52,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"2201.09865","title":"RePaint: Inpainting using Denoising Diffusion Probabilistic Models","created":"2022-01-24","cited_by_count":1430},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"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":"2401.08740","title":"SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers","created":"2024-01-16","cited_by_count":737},{"id":"1711.09078","title":"Video Enhancement with Task-Oriented Flow","created":"2017-11-24","cited_by_count":619},{"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":"2003.03808","title":"PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models","created":"2020-03-08","cited_by_count":358},{"id":"1712.00080","title":"Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation","created":"2017-11-30","cited_by_count":326},{"id":"2406.07550","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","created":"2024-06-11","cited_by_count":302},{"id":"2210.04628","title":"Novel View Synthesis with Diffusion Models","created":"2022-10-06","cited_by_count":300},{"id":"2003.05534","title":"Softmax Splatting for Video Frame Interpolation","created":"2020-03-11","cited_by_count":279},{"id":"2309.15807","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","created":"2023-09-27","cited_by_count":279},{"id":"1904.00830","title":"Depth-Aware Video Frame Interpolation","created":"2019-04-01","cited_by_count":234},{"id":"2011.06294","title":"Real-Time Intermediate Flow Estimation for Video Frame Interpolation","created":"2020-11-12","cited_by_count":213},{"id":"1506.06825","title":"DeepStereo: Learning to Predict New Views from the World's Imagery","created":"2015-06-22","cited_by_count":185},{"id":"2304.09790","title":"AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation","created":"2023-04-19","cited_by_count":180},{"id":"1711.10703","title":"FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors","created":"2017-11-29","cited_by_count":170},{"id":"2202.04901","title":"FILM: Frame Interpolation for Large Motion","created":"2022-02-10","cited_by_count":153},{"id":"1804.06919","title":"Video Compression through Image Interpolation","created":"2018-04-18","cited_by_count":143},{"id":"2103.16206","title":"XVFI: eXtreme Video Frame Interpolation","created":"2021-03-30","cited_by_count":126},{"id":"2111.13817","title":"Video Frame Interpolation Transformer","created":"2021-11-27","cited_by_count":123},{"id":"2205.14620","title":"IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation","created":"2022-05-29","cited_by_count":109},{"id":"2206.04647","title":"VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution","created":"2022-06-09","cited_by_count":101},{"id":"2303.00440","title":"Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation","created":"2023-03-01","cited_by_count":98},{"id":"2104.02495","title":"Deep Animation Video Interpolation in the Wild","created":"2021-04-06","cited_by_count":65},{"id":"2302.07864","title":"Denoising Diffusion Probabilistic Models for Robust Image Super-Resolution in the Wild","created":"2023-02-15","cited_by_count":46},{"id":"1702.00783","title":"Pixel Recursive Super Resolution","created":"2017-02-02","cited_by_count":44},{"id":"1811.11745","title":"Learning to Synthesize Motion Blur","created":"2018-11-27","cited_by_count":37},{"id":"2207.08119","title":"FloLPIPS: A Bespoke Video Quality Metric for Frame Interpoation","created":"2022-07-17","cited_by_count":37},{"id":"2111.15483","title":"ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation","created":"2021-11-30","cited_by_count":35},{"id":"2212.00776","title":"ResFormer: Scaling ViTs with Multi-Resolution Training","created":"2022-12-01","cited_by_count":34},{"id":"2404.06913","title":"Sparse Global Matching for Video Frame Interpolation with Large Motion","created":"2024-04-10","cited_by_count":28},{"id":"2211.11423","title":"Blur Interpolation Transformer for Real-World Motion from Blur","created":"2022-11-21","cited_by_count":25},{"id":"2403.18361","title":"ViTAR: Vision Transformer with Any Resolution","created":"2024-03-27","cited_by_count":25},{"id":"2304.02225","title":"BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation","created":"2023-04-05","cited_by_count":23},{"id":"2407.02315","title":"VFIMamba: Video Frame Interpolation with State Space Models","created":"2024-07-02","cited_by_count":22},{"id":"2405.05953","title":"Frame Interpolation with Consecutive Brownian Bridge Diffusion","created":"2024-05-09","cited_by_count":19},{"id":"2207.06763","title":"Neighbor Correspondence Matching for Flow-based Video Frame Synthesis","created":"2022-07-14","cited_by_count":12},{"id":"2406.09754","title":"LAVIB: A Large-scale Video Interpolation Benchmark","created":"2024-06-14","cited_by_count":11},{"id":"2310.17294","title":"Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolution","created":"2023-10-26","cited_by_count":8}],"next_cursor":null}