{"list":"other","total":78,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"2111.09881","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","created":"2021-11-18","cited_by_count":1627},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1501.00092","title":"Image Super-Resolution Using Deep Convolutional Networks","created":"2014-12-31","cited_by_count":1224},{"id":"1511.04587","title":"Accurate Image Super-Resolution Using Very Deep Convolutional Networks","created":"2015-11-14","cited_by_count":903},{"id":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"1904.05160","title":"Large-Scale Long-Tailed Recognition in an Open World","created":"2019-04-10","cited_by_count":705},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1604.03540","title":"Training Region-based Object Detectors with Online Hard Example Mining","created":"2016-04-12","cited_by_count":579},{"id":"1811.00982","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","created":"2018-11-02","cited_by_count":544},{"id":"1912.02424","title":"Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection","created":"2019-12-05","cited_by_count":540},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"1708.00786","title":"Structure-measure: A New Way to Evaluate Foreground Maps","created":"2017-08-02","cited_by_count":480},{"id":"2110.04596","title":"Deep Long-Tailed Learning: A Survey","created":"2021-10-09","cited_by_count":417},{"id":"2006.04388","title":"Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection","created":"2020-06-08","cited_by_count":409},{"id":"1904.11486","title":"Making Convolutional Networks Shift-Invariant Again","created":"2019-04-25","cited_by_count":391},{"id":"1904.02701","title":"Libra R-CNN: Towards Balanced Learning for Object Detection","created":"2019-04-04","cited_by_count":255},{"id":"1908.08297","title":"EGNet:Edge Guidance Network for Salient Object Detection","created":"2019-08-22","cited_by_count":237},{"id":"2008.13367","title":"VarifocalNet: An IoU-aware Dense Object Detector","created":"2020-08-31","cited_by_count":231},{"id":"1612.01697","title":"Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment","created":"2016-12-06","cited_by_count":225},{"id":"2102.10274","title":"Concealed Object Detection","created":"2021-02-20","cited_by_count":212},{"id":"1805.12177","title":"Why do deep convolutional networks generalize so poorly to small image transformations?","created":"2018-05-30","cited_by_count":198},{"id":"1611.04849","title":"Deeply supervised salient object detection with short connections","created":"2016-11-15","cited_by_count":196},{"id":"1308.3052","title":"Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index","created":"2013-08-14","cited_by_count":195},{"id":"1808.01050","title":"Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds","created":"2018-08-02","cited_by_count":186},{"id":"2101.11952","title":"Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss","created":"2021-01-28","cited_by_count":156},{"id":"1803.10404","title":"Lip Movements Generation at a Glance","created":"2018-03-28","cited_by_count":155},{"id":"2006.10408","title":"Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax","created":"2020-06-18","cited_by_count":152},{"id":"2107.12746","title":"Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework","created":"2021-07-27","cited_by_count":152},{"id":"1901.04407","title":"Self-Driving Cars: A Survey","created":"2019-01-14","cited_by_count":148},{"id":"2007.03943","title":"Remix: Rebalanced Mixup","created":"2020-07-08","cited_by_count":144},{"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":"2008.03673","title":"Feature Space Augmentation for Long-Tailed Data","created":"2020-08-09","cited_by_count":136},{"id":"2004.00431","title":"M2m: Imbalanced Classification via Major-to-minor Translation","created":"2020-04-01","cited_by_count":134},{"id":"2106.01883","title":"Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence","created":"2021-06-03","cited_by_count":130},{"id":"1909.00169","title":"Imbalance Problems in Object Detection: A Review","created":"2019-08-31","cited_by_count":118},{"id":"2205.06803","title":"VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder","created":"2022-05-13","cited_by_count":116},{"id":"1811.05181","title":"Gradient Harmonized Single-stage Detector","created":"2018-11-13","cited_by_count":114},{"id":"1909.12220","title":"Implicit Semantic Data Augmentation for Deep Networks","created":"2019-09-26","cited_by_count":106},{"id":"1904.04620","title":"Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving","created":"2019-04-09","cited_by_count":105},{"id":"1906.02611","title":"Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation","created":"2019-06-06","cited_by_count":105},{"id":"1901.03278","title":"Region Proposal by Guided Anchoring","created":"2019-01-10","cited_by_count":87},{"id":"2011.09670","title":"Dense Label Encoding for Boundary Discontinuity Free Rotation Detection","created":"2020-11-19","cited_by_count":79},{"id":"2012.05217","title":"Positional Encoding as Spatial Inductive Bias in GANs","created":"2020-12-09","cited_by_count":69},{"id":"1712.03162","title":"Class Rectification Hard Mining for Imbalanced Deep Learning","created":"2017-12-08","cited_by_count":67},{"id":"2003.03622","title":"Explaining Knowledge Distillation by Quantifying the Knowledge","created":"2020-03-07","cited_by_count":66},{"id":"1904.04821","title":"Prime Sample Attention in Object Detection","created":"2019-04-09","cited_by_count":55},{"id":"2104.00885","title":"Adaptive Class Suppression Loss for Long-Tail Object Detection","created":"2021-04-02","cited_by_count":55},{"id":"1601.05150","title":"Factors in Finetuning Deep Model for object detection","created":"2016-01-20","cited_by_count":53},{"id":"2011.14214","title":"Truly shift-invariant convolutional neural networks","created":"2020-11-28","cited_by_count":53},{"id":"2010.02178","title":"Mind the Pad -- CNNs can Develop Blind Spots","created":"2020-10-05","cited_by_count":41},{"id":"2107.02963","title":"Disentangle Your Dense Object Detector","created":"2021-07-07","cited_by_count":37},{"id":"1710.10577","title":"Examining CNN Representations with respect to Dataset Bias","created":"2017-10-29","cited_by_count":27},{"id":"2101.12322","title":"Position, Padding and Predictions: A Deeper Look at Position Information in CNNs","created":"2021-01-28","cited_by_count":26},{"id":"2203.09730","title":"A Dual Weighting Label Assignment Scheme for Object Detection","created":"2022-03-18","cited_by_count":26},{"id":"2108.01285","title":"Toward Spatially Unbiased Generative Models","created":"2021-08-03","cited_by_count":17},{"id":"2008.05787","title":"Shift Equivariance in Object Detection","created":"2020-08-13","cited_by_count":13},{"id":"2108.07884","title":"Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs","created":"2021-08-17","cited_by_count":12},{"id":"2112.09195","title":"Mitigating the Bias of Centered Objects in Common Datasets","created":"2021-12-16","cited_by_count":7}],"next_cursor":null}