{"list":"other","total":62,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"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":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1604.03540","title":"Training Region-based Object Detectors with Online Hard Example Mining","created":"2016-04-12","cited_by_count":579},{"id":"1908.06112","title":"Symmetric Cross Entropy for Robust Learning with Noisy Labels","created":"2019-08-16","cited_by_count":500},{"id":"1711.02512","title":"Fine-tuning CNN Image Retrieval with No Human Annotation","created":"2017-11-03","cited_by_count":499},{"id":"1901.07518","title":"Hybrid Task Cascade for Instance Segmentation","created":"2019-01-22","cited_by_count":481},{"id":"1701.06548","title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","created":"2017-01-23","cited_by_count":464},{"id":"2004.08955","title":"ResNeSt: Split-Attention Networks","created":"2020-04-19","cited_by_count":445},{"id":"1903.07071","title":"Bag of Tricks and A Strong Baseline for Deep Person Re-identification","created":"2019-03-17","cited_by_count":430},{"id":"1904.11486","title":"Making Convolutional Networks Shift-Invariant Again","created":"2019-04-25","cited_by_count":391},{"id":"1704.04503","title":"Soft-NMS -- Improving Object Detection With One Line of Code","created":"2017-04-14","cited_by_count":382},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"1807.09441","title":"Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net","created":"2018-07-25","cited_by_count":364},{"id":"1904.11492","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","created":"2019-04-25","cited_by_count":331},{"id":"1804.01438","title":"Learning Discriminative Features with Multiple Granularities for Person Re-Identification","created":"2018-04-04","cited_by_count":291},{"id":"1701.08398","title":"Re-ranking Person Re-identification with k-reciprocal Encoding","created":"2017-01-29","cited_by_count":262},{"id":"2006.02334","title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution","created":"2020-06-03","cited_by_count":222},{"id":"2004.03548","title":"Temporal Pyramid Network for Action Recognition","created":"2020-04-07","cited_by_count":163},{"id":"2008.10032","title":"Seesaw Loss for Long-Tailed Instance Segmentation","created":"2020-08-23","cited_by_count":146},{"id":"2003.07064","title":"On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location","created":"2020-03-16","cited_by_count":142},{"id":"2101.07974","title":"TCLR: Temporal Contrastive Learning for Video Representation","created":"2021-01-20","cited_by_count":136},{"id":"2001.04086","title":"GridMask Data Augmentation","created":"2020-01-13","cited_by_count":123},{"id":"2003.13630","title":"TResNet: High Performance GPU-Dedicated Architecture","created":"2020-03-30","cited_by_count":119},{"id":"1908.07801","title":"InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting","created":"2019-08-21","cited_by_count":95},{"id":"2107.00420","title":"CBNet: A Composite Backbone Network Architecture for Object Detection","created":"2021-07-01","cited_by_count":77},{"id":"2007.00992","title":"Rethinking Channel Dimensions for Efficient Model Design","created":"2020-07-02","cited_by_count":41},{"id":"2012.10150","title":"SCNet: Training Inference Sample Consistency for Instance Segmentation","created":"2020-12-18","cited_by_count":38},{"id":"2106.02523","title":"Hallucination In Object Detection -- A Study In Visual Part Verification","created":"2021-06-04","cited_by_count":16},{"id":"2103.03768","title":"VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2021-03-05","cited_by_count":11},{"id":"2110.00470","title":"Instance Segmentation Challenge Track Technical Report, VIPriors Workshop at ICCV 2021: Task-Specific Copy-Paste Data Augmentation Method for Instance Segmentation","created":"2021-10-01","cited_by_count":5},{"id":"2112.01072","title":"The Second Place Solution for ICCV2021 VIPriors Instance Segmentation Challenge","created":"2021-12-02","cited_by_count":2}],"next_cursor":null}