{"list":"other","total":57,"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":"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1711.06396","title":"VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection","created":"2017-11-17","cited_by_count":1323},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"1912.13192","title":"PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection","created":"2019-12-31","cited_by_count":891},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1804.02505","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","created":"2018-04-07","cited_by_count":788},{"id":"1803.00567","title":"Computational Optimal Transport","created":"2018-03-01","cited_by_count":780},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2103.01458","title":"Diffusion Probabilistic Models for 3D Point Cloud Generation","created":"2021-03-02","cited_by_count":735},{"id":"1701.07875","title":"Wasserstein GAN","created":"2017-01-26","cited_by_count":639},{"id":"1911.10127","title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","created":"2019-11-22","cited_by_count":490},{"id":"1912.06378","title":"Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching","created":"2019-12-13","cited_by_count":417},{"id":"2006.04139","title":"Learning Texture Transformer Network for Image Super-Resolution","created":"2020-06-07","cited_by_count":347},{"id":"2003.07853","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","created":"2020-03-17","cited_by_count":326},{"id":"1902.10556","title":"Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference","created":"2019-02-27","cited_by_count":254},{"id":"2012.01411","title":"PatchmatchNet: Learned Multi-View Patchmatch Stereo","created":"2020-12-02","cited_by_count":207},{"id":"2011.02910","title":"Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers","created":"2020-11-05","cited_by_count":190},{"id":"2104.14540","title":"The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth","created":"2021-04-29","cited_by_count":190},{"id":"2109.04456","title":"NEAT: Neural Attention Fields for End-to-End Autonomous Driving","created":"2021-09-09","cited_by_count":174},{"id":"1912.08329","title":"Cost Volume Pyramid Based Depth Inference for Multi-View Stereo","created":"2019-12-18","cited_by_count":154},{"id":"2104.04314","title":"CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching","created":"2021-04-09","cited_by_count":154},{"id":"1911.12012","title":"Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness","created":"2019-11-27","cited_by_count":151},{"id":"1908.04422","title":"Point-Based Multi-View Stereo Network","created":"2019-08-12","cited_by_count":147},{"id":"1703.03492","title":"A New Representation of Skeleton Sequences for 3D Action Recognition","created":"2017-03-09","cited_by_count":126},{"id":"2007.12140","title":"HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching","created":"2020-07-23","cited_by_count":120},{"id":"2111.14600","title":"TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers","created":"2021-11-29","cited_by_count":117},{"id":"1909.05845","title":"DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch","created":"2019-09-12","cited_by_count":114},{"id":"2107.02191","title":"TransformerFusion: Monocular RGB Scene Reconstruction using Transformers","created":"2021-07-05","cited_by_count":106},{"id":"1904.08103","title":"Multi-Scale Geometric Consistency Guided Multi-View Stereo","created":"2019-04-17","cited_by_count":105},{"id":"2003.13017","title":"Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement","created":"2020-03-29","cited_by_count":105},{"id":"2008.07928","title":"Visibility-aware Multi-view Stereo Network","created":"2020-08-18","cited_by_count":98},{"id":"2201.01501","title":"Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation","created":"2022-01-05","cited_by_count":82},{"id":"2007.10872","title":"Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking","created":"2020-07-21","cited_by_count":81},{"id":"2204.03636","title":"SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation","created":"2022-04-07","cited_by_count":76},{"id":"2108.03824","title":"AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network","created":"2021-08-09","cited_by_count":71},{"id":"1912.11746","title":"Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume","created":"2019-12-26","cited_by_count":59},{"id":"2112.05126","title":"IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo","created":"2021-12-09","cited_by_count":56},{"id":"1912.03001","title":"Pyramid Multi-view Stereo Net with Self-adaptive View Aggregation","created":"2019-12-06","cited_by_count":44},{"id":"2104.13325","title":"MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions","created":"2021-04-27","cited_by_count":43},{"id":"2007.07714","title":"PVSNet: Pixelwise Visibility-Aware Multi-View Stereo Network","created":"2020-07-15","cited_by_count":35},{"id":"2112.08996","title":"Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation","created":"2021-12-16","cited_by_count":29},{"id":"2108.08943","title":"PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility","created":"2021-08-19","cited_by_count":17},{"id":"2112.05999","title":"Curvature-guided dynamic scale networks for Multi-view Stereo","created":"2021-12-11","cited_by_count":17},{"id":"2112.00336","title":"Multi-View Stereo with Transformer","created":"2021-12-01","cited_by_count":14}],"next_cursor":null}