{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"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":"1801.07892","title":"Generative Image Inpainting with Contextual Attention","created":"2018-01-24","cited_by_count":580},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"1804.07723","title":"Image Inpainting for Irregular Holes Using Partial Convolutions","created":"2018-04-20","cited_by_count":505},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"2104.13371","title":"BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment","created":"2021-04-27","cited_by_count":342},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329},{"id":"1808.00449","title":"Learning Blind Video Temporal Consistency","created":"2018-08-01","cited_by_count":253},{"id":"2103.14586","title":"Understanding Robustness of Transformers for Image Classification","created":"2021-03-26","cited_by_count":249},{"id":"2201.12288","title":"VRT: A Video Restoration Transformer","created":"2022-01-28","cited_by_count":220},{"id":"1708.07632","title":"Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition","created":"2017-08-25","cited_by_count":178},{"id":"2007.10247","title":"Learning Joint Spatial-Temporal Transformations for Video Inpainting","created":"2020-07-20","cited_by_count":163},{"id":"1905.02884","title":"Deep Flow-Guided Video Inpainting","created":"2019-05-08","cited_by_count":116},{"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":"2103.10022","title":"Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE","created":"2021-03-18","cited_by_count":106},{"id":"2009.01835","title":"Flow-edge Guided Video Completion","created":"2020-09-03","cited_by_count":104},{"id":"2012.08512","title":"FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation","created":"2020-12-15","cited_by_count":98},{"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":"2106.11149","title":"OadTR: Online Action Detection with Transformers","created":"2021-06-21","cited_by_count":83},{"id":"2007.08434","title":"Appearance-Preserving 3D Convolution for Video-based Person Re-identification","created":"2020-07-16","cited_by_count":63},{"id":"2204.04216","title":"Learning Trajectory-Aware Transformer for Video Super-Resolution","created":"2022-04-08","cited_by_count":61},{"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":"1803.00557","title":"The 2018 DAVIS Challenge on Video Object Segmentation","created":"2018-03-01","cited_by_count":47},{"id":"1908.08718","title":"Onion-Peel Networks for Deep Video Completion","created":"2019-08-23","cited_by_count":46},{"id":"1503.05528","title":"Video Inpainting of Complex Scenes","created":"2015-03-18","cited_by_count":41},{"id":"2012.08054","title":"Image Inpainting Guided by Coherence Priors of Semantics and Textures","created":"2020-12-15","cited_by_count":37},{"id":"2009.05721","title":"Short-Term and Long-Term Context Aggregation Network for Video Inpainting","created":"2020-09-12","cited_by_count":35},{"id":"2104.03507","title":"Progressive Temporal Feature Alignment Network for Video Inpainting","created":"2021-04-08","cited_by_count":35},{"id":"1909.07957","title":"An Internal Learning Approach to Video Inpainting","created":"2019-09-17","cited_by_count":33},{"id":"2004.02803","title":"Deformable 3D Convolution for Video Super-Resolution","created":"2020-04-06","cited_by_count":32},{"id":"2108.06765","title":"Occlusion-Aware Video Object Inpainting","created":"2021-08-15","cited_by_count":30},{"id":"2104.06637","title":"Decoupled Spatial-Temporal Transformer for Video Inpainting","created":"2021-04-14","cited_by_count":28},{"id":"2208.03012","title":"Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution","created":"2022-08-05","cited_by_count":25},{"id":"2108.01912","title":"Internal Video Inpainting by Implicit Long-range Propagation","created":"2021-08-04","cited_by_count":19}],"next_cursor":null}