{"list":"other","total":81,"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"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":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"1902.06162","title":"Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey","created":"2019-02-16","cited_by_count":657},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2011.09157","title":"Dense Contrastive Learning for Self-Supervised Visual Pre-Training","created":"2020-11-18","cited_by_count":512},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1803.08669","title":"Pyramid Stereo Matching Network","created":"2018-03-23","cited_by_count":489},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"1904.09925","title":"Attention Augmented Convolutional Networks","created":"2019-04-22","cited_by_count":363},{"id":"1703.04309","title":"End-to-End Learning of Geometry and Context for Deep Stereo Regression","created":"2017-03-13","cited_by_count":360},{"id":"2109.07547","title":"RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching","created":"2021-09-15","cited_by_count":353},{"id":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327},{"id":"2204.07141","title":"Masked Siamese Networks for Label-Efficient Learning","created":"2022-04-14","cited_by_count":302},{"id":"2011.10043","title":"Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning","created":"2020-11-19","cited_by_count":297},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291},{"id":"2203.16194","title":"FlowFormer: A Transformer Architecture for Optical Flow","created":"2022-03-30","cited_by_count":275},{"id":"2211.05783","title":"Unifying Flow, Stereo and Depth Estimation","created":"2022-11-10","cited_by_count":275},{"id":"2210.03109","title":"Real-World Robot Learning with Masked Visual Pre-training","created":"2022-10-06","cited_by_count":245},{"id":"2203.11483","title":"Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation","created":"2022-03-22","cited_by_count":197},{"id":"2010.13501","title":"Hierarchical Neural Architecture Search for Deep Stereo Matching","created":"2020-10-26","cited_by_count":166},{"id":"2210.10716","title":"CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion","created":"2022-10-19","cited_by_count":160},{"id":"2007.13916","title":"Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases","created":"2020-07-28","cited_by_count":143},{"id":"2203.02146","title":"Attention Concatenation Volume for Accurate and Efficient Stereo Matching","created":"2022-03-04","cited_by_count":130},{"id":"1904.09117","title":"SelFlow: Self-Supervised Learning of Optical Flow","created":"2019-04-19","cited_by_count":128},{"id":"2007.12140","title":"HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching","created":"2020-07-23","cited_by_count":120},{"id":"2203.12719","title":"What to Hide from Your Students: Attention-Guided Masked Image Modeling","created":"2022-03-23","cited_by_count":118},{"id":"2112.10740","title":"Are Large-scale Datasets Necessary for Self-Supervised Pre-training?","created":"2021-12-20","cited_by_count":117},{"id":"2106.05656","title":"MST: Masked Self-Supervised Transformer for Visual Representation","created":"2021-06-10","cited_by_count":114},{"id":"1608.05842","title":"Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothness","created":"2016-08-20","cited_by_count":101},{"id":"2104.03602","title":"SiT: Self-supervised vIsion Transformer","created":"2021-04-08","cited_by_count":99},{"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":"2006.02535","title":"A Survey on Deep Learning Techniques for Stereo-based Depth Estimation","created":"2020-06-01","cited_by_count":90},{"id":"1807.08865","title":"StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction","created":"2018-07-24","cited_by_count":88},{"id":"2203.16896","title":"CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow","created":"2022-03-31","cited_by_count":82},{"id":"2202.03382","title":"Corrupted Image Modeling for Self-Supervised Visual Pre-Training","created":"2022-02-07","cited_by_count":68},{"id":"2203.11335","title":"Global Matching with Overlapping Attention for Optical Flow Estimation","created":"2022-03-21","cited_by_count":64},{"id":"2204.08442","title":"Deep Equilibrium Optical Flow Estimation","created":"2022-04-18","cited_by_count":64},{"id":"2006.12797","title":"PCW-Net: Pyramid Combination and Warping Cost Volume for Stereo Matching","created":"2020-06-23","cited_by_count":62},{"id":"2210.07277","title":"The Hidden Uniform Cluster Prior in Self-Supervised Learning","created":"2022-10-13","cited_by_count":58},{"id":"2205.14623","title":"SKFlow: Learning Optical Flow with Super Kernels","created":"2022-05-29","cited_by_count":56},{"id":"2008.01342","title":"LoCo: Local Contrastive Representation Learning","created":"2020-08-04","cited_by_count":55},{"id":"2104.02166","title":"Learning Optical Flow from a Few Matches","created":"2021-04-05","cited_by_count":53},{"id":"2206.04671","title":"Open Challenges in Deep Stereo: the Booster Dataset","created":"2022-06-09","cited_by_count":48},{"id":"2204.00330","title":"DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow","created":"2022-04-01","cited_by_count":40},{"id":"2004.04627","title":"AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching","created":"2020-04-09","cited_by_count":31},{"id":"2105.08941","title":"Large-scale Localization Datasets in Crowded Indoor Spaces","created":"2021-05-19","cited_by_count":29},{"id":"1710.08247","title":"Generic 3D Representation via Pose Estimation and Matching","created":"2017-10-23","cited_by_count":17},{"id":"2210.02077","title":"Exploring The Role of Mean Teachers in Self-supervised Masked Auto-Encoders","created":"2022-10-05","cited_by_count":13},{"id":"1804.00796","title":"Left-Right Comparative Recurrent Model for Stereo Matching","created":"2018-04-03","cited_by_count":12},{"id":"2210.16900","title":"High Resolution Multi-Scale RAFT (Robust Vision Challenge 2022)","created":"2022-10-30","cited_by_count":12}],"next_cursor":null}