{"list":"other","total":68,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"1806.03589","title":"Free-Form Image Inpainting with Gated Convolution","created":"2018-06-10","cited_by_count":594},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"1804.07723","title":"Image Inpainting for Irregular Holes Using Partial Convolutions","created":"2018-04-20","cited_by_count":505},{"id":"1611.00850","title":"Optical Flow Estimation using a Spatial Pyramid Network","created":"2016-11-03","cited_by_count":424},{"id":"1808.06601","title":"Video-to-Video Synthesis","created":"2018-08-20","cited_by_count":390},{"id":"1912.12180","title":"Axial Attention in Multidimensional Transformers","created":"2019-12-20","cited_by_count":358},{"id":"2104.13371","title":"BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment","created":"2021-04-27","cited_by_count":342},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307},{"id":"1808.00449","title":"Learning Blind Video Temporal Consistency","created":"2018-08-01","cited_by_count":253},{"id":"1809.00461","title":"YouTube-VOS: Sequence-to-Sequence Video Object Segmentation","created":"2018-09-03","cited_by_count":232},{"id":"2201.12288","title":"VRT: A Video Restoration Transformer","created":"2022-01-28","cited_by_count":220},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189},{"id":"2007.10247","title":"Learning Joint Spatial-Temporal Transformations for Video Inpainting","created":"2020-07-20","cited_by_count":163},{"id":"1907.10244","title":"AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation","created":"2019-07-24","cited_by_count":134},{"id":"2005.09704","title":"Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting","created":"2020-05-19","cited_by_count":124},{"id":"2003.10955","title":"MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask","created":"2020-03-24","cited_by_count":117},{"id":"1905.02884","title":"Deep Flow-Guided Video Inpainting","created":"2019-05-08","cited_by_count":116},{"id":"2206.11894","title":"MaskViT: Masked Visual Pre-Training for Video Prediction","created":"2022-06-23","cited_by_count":114},{"id":"2204.02663","title":"Towards An End-to-End Framework for Flow-Guided Video Inpainting","created":"2022-04-06","cited_by_count":113},{"id":"1905.01639","title":"Deep Video Inpainting","created":"2019-05-05","cited_by_count":109},{"id":"2009.01835","title":"Flow-edge Guided Video Completion","created":"2020-09-03","cited_by_count":104},{"id":"1807.09620","title":"OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas","created":"2018-07-25","cited_by_count":99},{"id":"2109.02974","title":"FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting","created":"2021-09-07","cited_by_count":95},{"id":"1904.10247","title":"Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN","created":"2019-04-23","cited_by_count":87},{"id":"2106.13195","title":"FitVid: Overfitting in Pixel-Level Video Prediction","created":"2021-06-24","cited_by_count":87},{"id":"2207.08494","title":"Rethinking Alignment in Video Super-Resolution Transformers","created":"2022-07-18","cited_by_count":71},{"id":"1908.07007","title":"Boundless: Generative Adversarial Networks for Image Extension","created":"2019-08-19","cited_by_count":62},{"id":"2208.06768","title":"Flow-Guided Transformer for Video Inpainting","created":"2022-08-14","cited_by_count":59},{"id":"1806.08482","title":"Video Inpainting by Jointly Learning Temporal Structure and Spatial Details","created":"2018-06-22","cited_by_count":58},{"id":"1908.11587","title":"Copy-and-Paste Networks for Deep Video Inpainting","created":"2019-08-30","cited_by_count":58},{"id":"2103.10559","title":"CDFI: Compression-Driven Network Design for Frame Interpolation","created":"2021-03-18","cited_by_count":56},{"id":"2104.00675","title":"In&Out : Diverse Image Outpainting via GAN Inversion","created":"2021-04-01","cited_by_count":55},{"id":"2205.05570","title":"Review on Panoramic Imaging and Its Applications in Scene Understanding","created":"2022-05-11","cited_by_count":43},{"id":"1503.05528","title":"Video Inpainting of Complex Scenes","created":"2015-03-18","cited_by_count":41},{"id":"2205.05076","title":"Reduce Information Loss in Transformers for Pluralistic Image Inpainting","created":"2022-05-10","cited_by_count":36},{"id":"2203.06304","title":"MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting","created":"2022-03-12","cited_by_count":35},{"id":"2110.11062","title":"Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation","created":"2021-10-21","cited_by_count":34},{"id":"2205.13281","title":"Surround-view Fisheye Camera Perception for Automated Driving: Overview, Survey and Challenges","created":"2022-05-26","cited_by_count":34},{"id":"1808.08483","title":"Painting Outside the Box: Image Outpainting with GANs","created":"2018-08-25","cited_by_count":30},{"id":"2202.13388","title":"PanoFlow: Learning 360{\\deg} Optical Flow for Surrounding Temporal Understanding","created":"2022-02-27","cited_by_count":26},{"id":"1712.04569","title":"Im2Pano3D: Extrapolating 360 Structure and Semantics Beyond the Field of View","created":"2017-12-12","cited_by_count":25},{"id":"2207.10391","title":"Error Compensation Framework for Flow-Guided Video Inpainting","created":"2022-07-21","cited_by_count":20},{"id":"2105.05640","title":"FDAN: Flow-guided Deformable Alignment Network for Video Super-Resolution","created":"2021-05-12","cited_by_count":19},{"id":"2204.08563","title":"Cylin-Painting: Seamless {360\\textdegree} Panoramic Image Outpainting and Beyond","created":"2022-04-18","cited_by_count":12},{"id":"2207.05312","title":"Outpainting by Queries","created":"2022-07-12","cited_by_count":12},{"id":"2201.11403","title":"Generalised Image Outpainting with U-Transformer","created":"2022-01-27","cited_by_count":11},{"id":"2208.00776","title":"Deep 360$^\\circ$ Optical Flow Estimation Based on Multi-Projection Fusion","created":"2022-07-27","cited_by_count":8},{"id":"2206.05844","title":"FisheyeEX: Polar Outpainting for Extending the FoV of Fisheye Lens","created":"2022-06-12","cited_by_count":2}],"next_cursor":null}