{"list":"other","total":56,"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":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"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":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"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":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"1711.10398","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","created":"2017-11-28","cited_by_count":623},{"id":"1812.01187","title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","created":"2018-12-04","cited_by_count":431},{"id":"1605.06409","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","created":"2016-05-20","cited_by_count":414},{"id":"1711.07846","title":"Functional Map of the World","created":"2017-11-21","cited_by_count":338},{"id":"1710.09282","title":"A Survey of Model Compression and Acceleration for Deep Neural Networks","created":"2017-10-23","cited_by_count":301},{"id":"1511.06523","title":"WIDER FACE: A Face Detection Benchmark","created":"2015-11-20","cited_by_count":298},{"id":"1805.00123","title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd","created":"2018-04-30","cited_by_count":284},{"id":"1704.08545","title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","created":"2017-04-27","cited_by_count":261},{"id":"2011.08036","title":"Scaled-YOLOv4: Scaling Cross Stage Partial Network","created":"2020-11-16","cited_by_count":211},{"id":"1611.10012","title":"Speed/accuracy trade-offs for modern convolutional object detectors","created":"2016-11-30","cited_by_count":198},{"id":"1702.05693","title":"CityPersons: A Diverse Dataset for Pedestrian Detection","created":"2017-02-19","cited_by_count":172},{"id":"2005.14187","title":"HAT: Hardware-Aware Transformers for Efficient Natural Language Processing","created":"2020-05-28","cited_by_count":136},{"id":"1904.08008","title":"Clustered Object Detection in Aerial Images","created":"2019-04-16","cited_by_count":83},{"id":"1910.06663","title":"AI Benchmark: All About Deep Learning on Smartphones in 2019","created":"2019-10-15","cited_by_count":77},{"id":"1904.03629","title":"Adaptive NMS: Refining Pedestrian Detection in a Crowd","created":"2019-04-07","cited_by_count":66},{"id":"1711.07752","title":"Repulsion Loss: Detecting Pedestrians in a Crowd","created":"2017-11-21","cited_by_count":62},{"id":"1807.08407","title":"Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd","created":"2018-07-23","cited_by_count":58},{"id":"1805.07193","title":"The EuroCity Persons Dataset: A Novel Benchmark for Object Detection","created":"2018-05-18","cited_by_count":57},{"id":"2004.05520","title":"Density Map Guided Object Detection in Aerial Images","created":"2020-04-12","cited_by_count":56},{"id":"1708.02843","title":"Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism","created":"2017-08-09","cited_by_count":48},{"id":"1812.01600","title":"AutoFocus: Efficient Multi-Scale Inference","created":"2018-12-04","cited_by_count":46},{"id":"2003.00425","title":"Learning When and Where to Zoom with Deep Reinforcement Learning","created":"2020-03-01","cited_by_count":43},{"id":"1909.12118","title":"WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild","created":"2019-09-25","cited_by_count":39},{"id":"1910.06160","title":"Mask-Guided Attention Network for Occluded Pedestrian Detection","created":"2019-10-14","cited_by_count":36},{"id":"1909.06826","title":"PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes","created":"2019-09-15","cited_by_count":30},{"id":"1909.09709","title":"SkyNet: a Hardware-Efficient Method for Object Detection and Tracking on Embedded Systems","created":"2019-09-20","cited_by_count":27},{"id":"1711.05187","title":"Dynamic Zoom-in Network for Fast Object Detection in Large Images","created":"2017-11-14","cited_by_count":23},{"id":"1912.03966","title":"Efficient Object Detection in Large Images using Deep Reinforcement Learning","created":"2019-12-09","cited_by_count":21},{"id":"1910.09188","title":"Attribute-aware Pedestrian Detection in a Crowd","created":"2019-10-21","cited_by_count":20},{"id":"1607.05477","title":"Supervised Transformer Network for Efficient Face Detection","created":"2016-07-19","cited_by_count":14},{"id":"1905.10011","title":"Light-Weight RetinaNet for Object Detection","created":"2019-05-24","cited_by_count":11},{"id":"2003.08799","title":"Generalizable Pedestrian Detection: The Elephant In The Room","created":"2020-03-19","cited_by_count":9},{"id":"2002.09053","title":"Adapted Center and Scale Prediction: More Stable and More Accurate","created":"2020-02-20","cited_by_count":5},{"id":"1609.03536","title":"A Multi-Scale Cascade Fully Convolutional Network Face Detector","created":"2016-09-12","cited_by_count":4},{"id":"2001.09252","title":"PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection","created":"2020-01-25","cited_by_count":4},{"id":"1804.05197","title":"Beyond Trade-off: Accelerate FCN-based Face Detector with Higher Accuracy","created":"2018-04-14","cited_by_count":3},{"id":"1911.08855","title":"RefineDetLite: A Lightweight One-stage Object Detection Framework for CPU-only Devices","created":"2019-11-20","cited_by_count":3},{"id":"2004.12623","title":"Localizing Grouped Instances for Efficient Detection in Low-Resource Scenarios","created":"2020-04-27","cited_by_count":1}],"next_cursor":null}