{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"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":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"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":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"1412.7062","title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","created":"2014-12-22","cited_by_count":554},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"1912.03458","title":"Dynamic Convolution: Attention over Convolution Kernels","created":"2019-12-07","cited_by_count":356},{"id":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"1612.00137","title":"RMPE: Regional Multi-person Pose Estimation","created":"2016-12-01","cited_by_count":340},{"id":"1711.09485","title":"SkipNet: Learning Dynamic Routing in Convolutional Networks","created":"2017-11-26","cited_by_count":332},{"id":"1605.09673","title":"Dynamic Filter Networks","created":"2016-05-31","cited_by_count":319},{"id":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"id":"2004.02147","title":"BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation","created":"2020-04-05","cited_by_count":294},{"id":"1606.02147","title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","created":"2016-06-07","cited_by_count":291},{"id":"1904.04971","title":"CondConv: Conditionally Parameterized Convolutions for Efficient Inference","created":"2019-04-10","cited_by_count":273},{"id":"1703.00837","title":"Meta Networks","created":"2017-03-02","cited_by_count":269},{"id":"1704.08545","title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","created":"2017-04-27","cited_by_count":261},{"id":"1711.08229","title":"Integral Human Pose Regression","created":"2017-11-22","cited_by_count":256},{"id":"1908.10357","title":"HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation","created":"2019-08-27","cited_by_count":247},{"id":"1910.06278","title":"Distribution-Aware Coordinate Representation for Human Pose Estimation","created":"2019-10-14","cited_by_count":165},{"id":"1810.12348","title":"Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks","created":"2018-10-29","cited_by_count":139},{"id":"1701.01779","title":"Towards Accurate Multi-person Pose Estimation in the Wild","created":"2017-01-06","cited_by_count":131},{"id":"1902.04502","title":"Fast-SCNN: Fast Semantic Segmentation Network","created":"2019-02-12","cited_by_count":125},{"id":"2004.01547","title":"Context Prior for Scene Segmentation","created":"2020-04-03","cited_by_count":121},{"id":"1804.09337","title":"Learning a Discriminative Feature Network for Semantic Segmentation","created":"2018-04-25","cited_by_count":114},{"id":"1907.09595","title":"MixConv: Mixed Depthwise Convolutional Kernels","created":"2019-07-22","cited_by_count":108},{"id":"1903.08469","title":"In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images","created":"2019-03-20","cited_by_count":100},{"id":"1904.02216","title":"DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation","created":"2019-04-03","cited_by_count":100},{"id":"1912.10917","title":"FasterSeg: Searching for Faster Real-time Semantic Segmentation","created":"2019-12-23","cited_by_count":73},{"id":"1708.01101","title":"Learning Feature Pyramids for Human Pose Estimation","created":"2017-08-03","cited_by_count":57},{"id":"2003.10027","title":"Dynamic ReLU","created":"2020-03-22","cited_by_count":55},{"id":"2007.02269","title":"Rethinking Bottleneck Structure for Efficient Mobile Network Design","created":"2020-07-05","cited_by_count":54},{"id":"1908.09550","title":"Customizable Architecture Search for Semantic Segmentation","created":"2019-08-26","cited_by_count":41},{"id":"1903.03777","title":"Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search","created":"2019-03-09","cited_by_count":39},{"id":"1909.06793","title":"Graph-guided Architecture Search for Real-time Semantic Segmentation","created":"2019-09-15","cited_by_count":28},{"id":"2008.05202","title":"Representative Graph Neural Network","created":"2020-08-12","cited_by_count":19},{"id":"1806.00178","title":"IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks","created":"2018-06-01","cited_by_count":14},{"id":"1804.06202","title":"IGCV$2$: Interleaved Structured Sparse Convolutional Neural Networks","created":"2018-04-17","cited_by_count":12},{"id":"2007.08090","title":"EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation","created":"2020-07-16","cited_by_count":12},{"id":"1811.11254","title":"ShelfNet for Fast Semantic Segmentation","created":"2018-11-27","cited_by_count":1}],"next_cursor":null}