{"list":"other","total":68,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2012.09688","title":"PCT: Point cloud transformer","created":"2020-12-17","cited_by_count":732},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"1711.10398","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","created":"2017-11-28","cited_by_count":623},{"id":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"1911.08251","title":"General $E(2)$-Equivariant Steerable CNNs","created":"2019-11-19","cited_by_count":446},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"1704.06904","title":"Residual Attention Network for Image Classification","created":"2017-04-23","cited_by_count":386},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"1708.06500","title":"Sparsity Invariant CNNs","created":"2017-08-22","cited_by_count":326},{"id":"2004.13621","title":"Exploring Self-attention for Image Recognition","created":"2020-04-28","cited_by_count":313},{"id":"1603.09114","title":"LIFT: Learned Invariant Feature Transform","created":"2016-03-30","cited_by_count":306},{"id":"1612.04642","title":"Harmonic Networks: Deep Translation and Rotation Equivariance","created":"2016-12-14","cited_by_count":295},{"id":"2108.05699","title":"Oriented R-CNN for Object Detection","created":"2021-08-12","cited_by_count":231},{"id":"1804.00819","title":"End-to-End Dense Video Captioning with Masked Transformer","created":"2018-04-03","cited_by_count":214},{"id":"1904.11491","title":"Local Relation Networks for Image Recognition","created":"2019-04-25","cited_by_count":210},{"id":"2102.12219","title":"Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges","created":"2021-02-24","cited_by_count":204},{"id":"2103.07733","title":"ReDet: A Rotation-equivariant Detector for Aerial Object Detection","created":"2021-03-13","cited_by_count":203},{"id":"1908.05612","title":"R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object","created":"2019-08-15","cited_by_count":194},{"id":"2008.09397","title":"Align Deep Features for Oriented Object Detection","created":"2020-08-21","cited_by_count":187},{"id":"1703.01086","title":"Arbitrary-Oriented Scene Text Detection via Rotation Proposals","created":"2017-03-03","cited_by_count":176},{"id":"2007.10247","title":"Learning Joint Spatial-Temporal Transformations for Video Inpainting","created":"2020-07-20","cited_by_count":163},{"id":"2011.10881","title":"Rethinking Transformer-based Set Prediction for Object Detection","created":"2020-11-21","cited_by_count":156},{"id":"2101.11952","title":"Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss","created":"2021-01-28","cited_by_count":156},{"id":"1911.09358","title":"Gliding vertex on the horizontal bounding box for multi-oriented object detection","created":"2019-11-21","cited_by_count":134},{"id":"2011.09315","title":"End-to-End Object Detection with Adaptive Clustering Transformer","created":"2020-11-18","cited_by_count":109},{"id":"2105.02358","title":"Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks","created":"2021-05-05","cited_by_count":109},{"id":"1803.05265","title":"Rotation-Sensitive Regression for Oriented Scene Text Detection","created":"2018-03-14","cited_by_count":88},{"id":"2008.02496","title":"ConvBERT: Improving BERT with Span-based Dynamic Convolution","created":"2020-08-06","cited_by_count":88},{"id":"1609.04453","title":"A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning","created":"2016-09-14","cited_by_count":86},{"id":"2011.09670","title":"Dense Label Encoding for Boundary Discontinuity Free Rotation Detection","created":"2020-11-19","cited_by_count":79},{"id":"2109.04553","title":"Is Attention Better Than Matrix Decomposition?","created":"2021-09-09","cited_by_count":77},{"id":"1911.08299","title":"Learning Modulated Loss for Rotated Object Detection","created":"2019-11-19","cited_by_count":73},{"id":"2005.09973","title":"Dynamic Refinement Network for Oriented and Densely Packed Object Detection","created":"2020-05-20","cited_by_count":72},{"id":"1701.01833","title":"Oriented Response Networks","created":"2017-01-07","cited_by_count":68},{"id":"1604.06318","title":"TI-POOLING: transformation-invariant pooling for feature learning in Convolutional Neural Networks","created":"2016-04-21","cited_by_count":67},{"id":"2004.13316","title":"SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing","created":"2020-04-28","cited_by_count":62},{"id":"1806.04331","title":"Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networks","created":"2018-06-12","cited_by_count":54},{"id":"1807.02700","title":"Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery","created":"2018-07-07","cited_by_count":46},{"id":"1903.00857","title":"CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing Imagery","created":"2019-03-03","cited_by_count":43},{"id":"1910.10485","title":"Fully Quantized Transformer for Machine Translation","created":"2019-10-17","cited_by_count":36},{"id":"1412.5104","title":"Locally Scale-Invariant Convolutional Neural Networks","created":"2014-12-16","cited_by_count":34},{"id":"1910.02940","title":"Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation","created":"2019-10-07","cited_by_count":29},{"id":"1906.08628","title":"Learning Generalized Transformation Equivariant Representations via Autoencoding Transformations","created":"2019-06-19","cited_by_count":22},{"id":"2109.12848","title":"A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection","created":"2021-09-27","cited_by_count":22},{"id":"1711.09405","title":"Learning a Rotation Invariant Detector with Rotatable Bounding Box","created":"2017-11-26","cited_by_count":21},{"id":"2106.00880","title":"Rotation Equivariant Feature Image Pyramid Network for Object Detection in Optical Remote Sensing Imagery","created":"2021-06-02","cited_by_count":11}],"next_cursor":null}