{"list":"other","total":55,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"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":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1411.4734","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","created":"2014-11-18","cited_by_count":483},{"id":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"1603.04992","title":"Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue","created":"2016-03-16","cited_by_count":368},{"id":"1803.02276","title":"GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose","created":"2018-03-06","cited_by_count":342},{"id":"1511.05440","title":"Deep multi-scale video prediction beyond mean square error","created":"2015-11-17","cited_by_count":300},{"id":"1605.07157","title":"Unsupervised Learning for Physical Interaction through Video Prediction","created":"2016-05-23","cited_by_count":260},{"id":"1908.10553","title":"Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video","created":"2019-08-28","cited_by_count":244},{"id":"1710.11252","title":"Stochastic Variational Video Prediction","created":"2017-10-30","cited_by_count":234},{"id":"1805.09806","title":"Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation","created":"2018-05-24","cited_by_count":222},{"id":"1605.08104","title":"Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning","created":"2016-05-25","cited_by_count":204},{"id":"2104.14540","title":"The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth","created":"2021-04-29","cited_by_count":190},{"id":"1604.03901","title":"Single-Image Depth Perception in the Wild","created":"2016-04-13","cited_by_count":180},{"id":"1802.05522","title":"Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints","created":"2018-02-15","cited_by_count":179},{"id":"1904.04998","title":"Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras","created":"2019-04-10","cited_by_count":170},{"id":"1502.07411","title":"Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields","created":"2015-02-26","cited_by_count":169},{"id":"2009.06489","title":"The Hardware Lottery","created":"2020-09-14","cited_by_count":160},{"id":"1803.03893","title":"Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction","created":"2018-03-11","cited_by_count":159},{"id":"2007.06936","title":"Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance","created":"2020-07-14","cited_by_count":148},{"id":"2007.10603","title":"Feature-metric Loss for Self-supervised Learning of Depth and Egomotion","created":"2020-07-21","cited_by_count":140},{"id":"1907.05820","title":"Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Camera","created":"2019-07-12","cited_by_count":130},{"id":"2006.10704","title":"Latent Video Transformer","created":"2020-06-18","cited_by_count":106},{"id":"1903.01434","title":"VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation","created":"2019-03-04","cited_by_count":74},{"id":"2111.04060","title":"Are we ready for a new paradigm shift? A Survey on Visual Deep MLP","created":"2021-11-07","cited_by_count":63},{"id":"2103.01950","title":"Predicting Video with VQVAE","created":"2021-03-02","cited_by_count":61},{"id":"1703.07684","title":"Predicting Deeper into the Future of Semantic Segmentation","created":"2017-03-22","cited_by_count":51},{"id":"2003.06409","title":"Probabilistic Future Prediction for Video Scene Understanding","created":"2020-03-13","cited_by_count":45},{"id":"1711.03665","title":"Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency","created":"2017-11-10","cited_by_count":40},{"id":"1809.05786","title":"GANVO: Unsupervised Deep Monocular Visual Odometry and Depth Estimation with Generative Adversarial Networks","created":"2018-09-16","cited_by_count":21},{"id":"1809.08318","title":"Recurrent Flow-Guided Semantic Forecasting","created":"2018-09-21","cited_by_count":19},{"id":"1904.10666","title":"Segmenting the Future","created":"2019-04-24","cited_by_count":19},{"id":"1810.00746","title":"Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods","created":"2018-10-01","cited_by_count":17},{"id":"2104.03962","title":"Panoptic Segmentation Forecasting","created":"2021-04-08","cited_by_count":7},{"id":"1609.06377","title":"Geometry-Based Next Frame Prediction from Monocular Video","created":"2016-09-20","cited_by_count":6},{"id":"2106.15011","title":"Are conditional GANs explicitly conditional?","created":"2021-06-28","cited_by_count":2}],"next_cursor":null}