{"list":"other","total":97,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"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":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"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":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"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":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"1801.09414","title":"CosFace: Large Margin Cosine Loss for Deep Face Recognition","created":"2018-01-29","cited_by_count":971},{"id":"1312.4400","title":"Network In Network","created":"2013-12-16","cited_by_count":605},{"id":"1807.05511","title":"Object Detection with Deep Learning: A Review","created":"2018-07-15","cited_by_count":528},{"id":"2002.11569","title":"Overfitting in adversarially robust deep learning","created":"2020-02-26","cited_by_count":506},{"id":"1605.06409","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","created":"2016-05-20","cited_by_count":414},{"id":"2003.07853","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","created":"2020-03-17","cited_by_count":326},{"id":"1802.10062","title":"CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes","created":"2018-02-27","cited_by_count":267},{"id":"2006.02334","title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution","created":"2020-06-03","cited_by_count":222},{"id":"2003.13145","title":"Can AI help in screening Viral and COVID-19 pneumonia?","created":"2020-03-29","cited_by_count":200},{"id":"1611.10012","title":"Speed/accuracy trade-offs for modern convolutional object detectors","created":"2016-11-30","cited_by_count":198},{"id":"2004.01398","title":"TEA: Temporal Excitation and Aggregation for Action Recognition","created":"2020-04-03","cited_by_count":165},{"id":"2004.03548","title":"Temporal Pyramid Network for Action Recognition","created":"2020-04-07","cited_by_count":163},{"id":"1908.03684","title":"Bayesian Loss for Crowd Count Estimation with Point Supervision","created":"2019-08-10","cited_by_count":162},{"id":"1811.10452","title":"Context-Aware Crowd Counting","created":"2018-11-26","cited_by_count":150},{"id":"1903.03303","title":"Learning from Synthetic Data for Crowd Counting in the Wild","created":"2019-03-08","cited_by_count":148},{"id":"1911.10692","title":"Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning","created":"2019-11-25","cited_by_count":145},{"id":"2006.11339","title":"Video Panoptic Segmentation","created":"2020-06-19","cited_by_count":142},{"id":"1711.06897","title":"Single-Shot Refinement Neural Network for Object Detection","created":"2017-11-18","cited_by_count":129},{"id":"2001.09691","title":"Multi-Modal Domain Adaptation for Fine-Grained Action Recognition","created":"2020-01-27","cited_by_count":115},{"id":"1611.08976","title":"Range Loss for Deep Face Recognition with Long-tail","created":"2016-11-28","cited_by_count":111},{"id":"2004.02307","title":"EfficientPS: Efficient Panoptic Segmentation","created":"2020-04-05","cited_by_count":111},{"id":"1801.00054","title":"Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward","created":"2017-12-29","cited_by_count":105},{"id":"2107.00650","title":"CLIP-It! Language-Guided Video Summarization","created":"2021-07-01","cited_by_count":99},{"id":"2104.11892","title":"A Survey of Modern Deep Learning based Object Detection Models","created":"2021-04-24","cited_by_count":98},{"id":"2003.11617","title":"Covid-19: Automatic detection from X-Ray images utilizing Transfer Learning with Convolutional Neural Networks","created":"2020-03-25","cited_by_count":92},{"id":"2003.10849","title":"Automatic Detection of Coronavirus Disease (COVID-19) Using X-ray Images and Deep Convolutional Neural Networks","created":"2020-03-24","cited_by_count":86},{"id":"1912.00381","title":"Gate-Shift Networks for Video Action Recognition","created":"2019-12-01","cited_by_count":76},{"id":"1812.03904","title":"Attention-guided Unified Network for Panoptic Segmentation","created":"2018-12-10","cited_by_count":71},{"id":"2004.09363","title":"Deep-COVID: Predicting COVID-19 From Chest X-Ray Images Using Deep Transfer Learning","created":"2020-04-20","cited_by_count":67},{"id":"1907.13369","title":"Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition","created":"2019-07-31","cited_by_count":66},{"id":"2103.05127","title":"Model Complexity of Deep Learning: A Survey","created":"2021-03-08","cited_by_count":65},{"id":"2003.11055","title":"COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray Images","created":"2020-03-24","cited_by_count":60},{"id":"1811.09998","title":"Low-resolution Face Recognition in the Wild via Selective Knowledge Distillation","created":"2018-11-25","cited_by_count":55},{"id":"1604.00600","title":"HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection","created":"2016-04-03","cited_by_count":46},{"id":"1903.05027","title":"An End-to-End Network for Panoptic Segmentation","created":"2019-03-12","cited_by_count":46},{"id":"2011.11675","title":"Scaling Wide Residual Networks for Panoptic Segmentation","created":"2020-11-23","cited_by_count":32},{"id":"1708.02813","title":"BlitzNet: A Real-Time Deep Network for Scene Understanding","created":"2017-08-09","cited_by_count":29},{"id":"1908.03716","title":"SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Counting","created":"2019-08-10","cited_by_count":28},{"id":"2003.14395","title":"COVID-ResNet: A Deep Learning Framework for Screening of COVID19 from Radiographs","created":"2020-03-31","cited_by_count":28},{"id":"2004.12823","title":"A Critic Evaluation of Methods for COVID-19 Automatic Detection from X-Ray Images","created":"2020-04-27","cited_by_count":28},{"id":"1707.01691","title":"RON: Reverse Connection with Objectness Prior Networks for Object Detection","created":"2017-07-06","cited_by_count":27},{"id":"1911.07527","title":"SOGNet: Scene Overlap Graph Network for Panoptic Segmentation","created":"2019-11-18","cited_by_count":26},{"id":"2004.06272","title":"Bidirectional Graph Reasoning Network for Panoptic Segmentation","created":"2020-04-14","cited_by_count":26},{"id":"2104.12465","title":"GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization","created":"2021-04-26","cited_by_count":26},{"id":"2003.14031","title":"BANet: Bidirectional Aggregation Network with Occlusion Handling for Panoptic Segmentation","created":"2020-03-31","cited_by_count":25},{"id":"1804.06215","title":"DetNet: A Backbone network for Object Detection","created":"2018-04-17","cited_by_count":22},{"id":"1612.06851","title":"Beyond Skip Connections: Top-Down Modulation for Object Detection","created":"2016-12-20","cited_by_count":21},{"id":"1910.03892","title":"Fast Panoptic Segmentation Network","created":"2019-10-09","cited_by_count":19},{"id":"2010.03341","title":"Deep Learning in Diabetic Foot Ulcers Detection: A Comprehensive Evaluation","created":"2020-10-07","cited_by_count":19},{"id":"2110.07582","title":"Network Representation Learning: From Preprocessing, Feature Extraction to Node Embedding","created":"2021-10-14","cited_by_count":19},{"id":"2001.05864","title":"Weakly Supervised Video Summarization by Hierarchical Reinforcement Learning","created":"2020-01-12","cited_by_count":18},{"id":"2111.10250","title":"Panoptic Segmentation: A Review","created":"2021-11-19","cited_by_count":18},{"id":"2004.11676","title":"Automated diagnosis of COVID-19 with limited posteroanterior chest X-ray images using fine-tuned deep neural networks","created":"2020-04-23","cited_by_count":14},{"id":"2004.05717","title":"Towards an Effective and Efficient Deep Learning Model for COVID-19 Patterns Detection in X-ray Images","created":"2020-04-12","cited_by_count":13},{"id":"2201.07394","title":"KappaFace: Adaptive Additive Angular Margin Loss for Deep Face Recognition","created":"2022-01-19","cited_by_count":11},{"id":"1911.00764","title":"Single-Shot Panoptic Segmentation","created":"2019-11-02","cited_by_count":9},{"id":"2002.09703","title":"Automatic Data Augmentation via Deep Reinforcement Learning for Effective Kidney Tumor Segmentation","created":"2020-02-22","cited_by_count":8},{"id":"1801.00543","title":"Unsupervised Object-Level Video Summarization with Online Motion Auto-Encoder","created":"2018-01-02","cited_by_count":7},{"id":"2105.12532","title":"Unsupervised Video Summarization via Multi-source Features","created":"2021-05-26","cited_by_count":7},{"id":"1904.08056","title":"DENet: A Universal Network for Counting Crowd with Varying Densities and Scales","created":"2019-04-17","cited_by_count":6},{"id":"2012.01632","title":"Single-shot Path Integrated Panoptic Segmentation","created":"2020-12-03","cited_by_count":5},{"id":"1910.08787","title":"SpatialFlow: Bridging All Tasks for Panoptic Segmentation","created":"2019-10-19","cited_by_count":4},{"id":"2201.01466","title":"Challenges of Artificial Intelligence -- From Machine Learning and Computer Vision to Emotional Intelligence","created":"2022-01-05","cited_by_count":3},{"id":"2008.10112","title":"Robust Vision Challenge 2020 -- 1st Place Report for Panoptic Segmentation","created":"2020-08-23","cited_by_count":2},{"id":"2011.09796","title":"Unifying Instance and Panoptic Segmentation with Dynamic Rank-1 Convolutions","created":"2020-11-19","cited_by_count":2}],"next_cursor":null}