{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1807.02758","title":"Image Super-Resolution Using Very Deep Residual Channel Attention Networks","created":"2018-07-08","cited_by_count":1264},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"2106.03106","title":"Uformer: A General U-Shaped Transformer for Image Restoration","created":"2021-06-06","cited_by_count":866},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"1711.09078","title":"Video Enhancement with Task-Oriented Flow","created":"2017-11-24","cited_by_count":619},{"id":"1905.02716","title":"EDVR: Video Restoration with Enhanced Deformable Convolutional Networks","created":"2019-05-07","cited_by_count":494},{"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":"2106.09018","title":"End-to-End Semi-Supervised Object Detection with Soft Teacher","created":"2021-06-16","cited_by_count":316},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"id":"2003.05534","title":"Softmax Splatting for Video Frame Interpolation","created":"2020-03-11","cited_by_count":279},{"id":"1904.00830","title":"Depth-Aware Video Frame Interpolation","created":"2019-04-01","cited_by_count":234},{"id":"1812.02898","title":"TDAN: Temporally Deformable Alignment Network for Video Super-Resolution","created":"2018-12-07","cited_by_count":226},{"id":"1708.01692","title":"Video Frame Interpolation via Adaptive Separable Convolution","created":"2017-08-05","cited_by_count":213},{"id":"1702.02463","title":"Video Frame Synthesis using Deep Voxel Flow","created":"2017-02-08","cited_by_count":209},{"id":"1801.04590","title":"Frame-Recurrent Video Super-Resolution","created":"2018-01-14","cited_by_count":160},{"id":"1703.07514","title":"Video Frame Interpolation via Adaptive Convolution","created":"2017-03-22","cited_by_count":158},{"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":"1803.10967","title":"Context-aware Synthesis for Video Frame Interpolation","created":"2018-03-29","cited_by_count":153},{"id":"1704.02738","title":"Detail-revealing Deep Video Super-resolution","created":"2017-04-10","cited_by_count":148},{"id":"1903.10128","title":"Recurrent Back-Projection Network for Video Super-Resolution","created":"2019-03-25","cited_by_count":148},{"id":"1907.10244","title":"AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation","created":"2019-07-24","cited_by_count":134},{"id":"1907.01361","title":"FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation","created":"2019-07-01","cited_by_count":128},{"id":"2007.12622","title":"BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation","created":"2020-07-17","cited_by_count":118},{"id":"1810.08768","title":"MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement","created":"2018-10-20","cited_by_count":112},{"id":"1810.13243","title":"A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation","created":"2018-10-29","cited_by_count":110},{"id":"1905.01639","title":"Deep Video Inpainting","created":"2019-05-05","cited_by_count":109},{"id":"2002.11616","title":"Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution","created":"2020-02-26","cited_by_count":91},{"id":"1811.06981","title":"Learned Video Compression","created":"2018-11-16","cited_by_count":89},{"id":"2006.08070","title":"Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution","created":"2020-06-15","cited_by_count":63},{"id":"1804.00884","title":"PhaseNet for Video Frame Interpolation","created":"2018-04-03","cited_by_count":61},{"id":"1806.08482","title":"Video Inpainting by Jointly Learning Temporal Structure and Spatial Details","created":"2018-06-22","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":"2007.12928","title":"Video Super Resolution Based on Deep Learning: A Comprehensive Survey","created":"2020-07-25","cited_by_count":54},{"id":"2104.10642","title":"Temporal Modulation Network for Controllable Space-Time Video Super-Resolution","created":"2021-04-21","cited_by_count":54},{"id":"2003.13170","title":"Space-Time-Aware Multi-Resolution Video Enhancement","created":"2020-03-30","cited_by_count":49},{"id":"1904.10898","title":"ViDeNN: Deep Blind Video Denoising","created":"2019-04-24","cited_by_count":40},{"id":"2109.04588","title":"BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation","created":"2021-09-09","cited_by_count":35},{"id":"1809.08573","title":"Learning for Video Super-Resolution through HR Optical Flow Estimation","created":"2018-09-23","cited_by_count":24},{"id":"1812.01210","title":"Zoom-In-to-Check: Boosting Video Interpolation via Instance-level Discrimination","created":"2018-12-04","cited_by_count":15},{"id":"2008.10680","title":"Video Frame Interpolation via Generalized Deformable Convolution","created":"2020-08-24","cited_by_count":11},{"id":"2104.07473","title":"Zooming SlowMo: An Efficient One-Stage Framework for Space-Time Video Super-Resolution","created":"2021-04-15","cited_by_count":5}],"next_cursor":null}