{"list":"other","total":65,"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":"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"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":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"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":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"2012.09688","title":"PCT: Point cloud transformer","created":"2020-12-17","cited_by_count":732},{"id":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2203.06604","title":"Masked Autoencoders for Point Cloud Self-supervised Learning","created":"2022-03-13","cited_by_count":459},{"id":"1704.03915","title":"Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution","created":"2017-04-12","cited_by_count":453},{"id":"1611.00850","title":"Optical Flow Estimation using a Spatial Pyramid Network","created":"2016-11-03","cited_by_count":424},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327},{"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":"2003.05534","title":"Softmax Splatting for Video Frame Interpolation","created":"2020-03-11","cited_by_count":279},{"id":"2205.14401","title":"Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training","created":"2022-05-28","cited_by_count":264},{"id":"1904.00830","title":"Depth-Aware Video Frame Interpolation","created":"2019-04-01","cited_by_count":234},{"id":"2104.02409","title":"Learning to Estimate Hidden Motions with Global Motion Aggregation","created":"2021-04-06","cited_by_count":224},{"id":"1706.01307","title":"Submanifold Sparse Convolutional Networks","created":"2017-06-05","cited_by_count":223},{"id":"2103.14167","title":"COTR: Correspondence Transformer for Matching Across Images","created":"2021-03-25","cited_by_count":183},{"id":"2007.10247","title":"Learning Joint Spatial-Temporal Transformations for Video Inpainting","created":"2020-07-20","cited_by_count":163},{"id":"1801.04590","title":"Frame-Recurrent Video Super-Resolution","created":"2018-01-14","cited_by_count":160},{"id":"1911.00627","title":"Quadratic video interpolation","created":"2019-11-02","cited_by_count":145},{"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":"1905.01639","title":"Deep Video Inpainting","created":"2019-05-05","cited_by_count":109},{"id":"2205.03892","title":"ConvMAE: Masked Convolution Meets Masked Autoencoders","created":"2022-05-08","cited_by_count":105},{"id":"2009.01835","title":"Flow-edge Guided Video Completion","created":"2020-09-03","cited_by_count":104},{"id":"2104.14544","title":"AutoFlow: Learning a Better Training Set for Optical Flow","created":"2021-04-29","cited_by_count":102},{"id":"2109.02974","title":"FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting","created":"2021-09-07","cited_by_count":95},{"id":"1809.05571","title":"Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation","created":"2018-09-14","cited_by_count":94},{"id":"1812.06264","title":"Hierarchical Discrete Distribution Decomposition for Match Density Estimation","created":"2018-12-15","cited_by_count":93},{"id":"1711.11152","title":"Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition","created":"2017-11-29","cited_by_count":82},{"id":"2203.16896","title":"CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow","created":"2022-03-31","cited_by_count":82},{"id":"2106.02520","title":"CATs: Cost Aggregation Transformers for Visual Correspondence","created":"2021-06-04","cited_by_count":77},{"id":"1903.07414","title":"A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization","created":"2019-03-15","cited_by_count":76},{"id":"2105.07014","title":"SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping","created":"2021-05-14","cited_by_count":74},{"id":"2203.11335","title":"Global Matching with Overlapping Attention for Optical Flow Estimation","created":"2022-03-21","cited_by_count":64},{"id":"2205.14623","title":"SKFlow: Learning Optical Flow with Super Kernels","created":"2022-05-29","cited_by_count":56},{"id":"1801.02108","title":"SBNet: Sparse Blocks Network for Fast Inference","created":"2018-01-07","cited_by_count":54},{"id":"2104.13918","title":"High-Resolution Optical Flow from 1D Attention and Correlation","created":"2021-04-28","cited_by_count":54},{"id":"2104.02166","title":"Learning Optical Flow from a Few Matches","created":"2021-04-05","cited_by_count":53},{"id":"1810.01455","title":"Representation Flow for Action Recognition","created":"2018-10-02","cited_by_count":51},{"id":"2012.00212","title":"UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning","created":"2020-12-01","cited_by_count":49},{"id":"2001.02129","title":"Deep Video Super-Resolution using HR Optical Flow Estimation","created":"2020-01-06","cited_by_count":40},{"id":"2207.00531","title":"Masked Autoencoder for Self-Supervised Pre-training on Lidar Point Clouds","created":"2022-07-01","cited_by_count":39},{"id":"2105.10886","title":"VS-Net: Voting with Segmentation for Visual Localization","created":"2021-05-23","cited_by_count":29},{"id":"2004.01905","title":"Optical Flow in Dense Foggy Scenes using Semi-Supervised Learning","created":"2020-04-04","cited_by_count":20},{"id":"2104.03097","title":"LIFE: Lighting Invariant Flow Estimation","created":"2021-04-07","cited_by_count":6}],"next_cursor":null}