{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"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":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"1411.7923","title":"Learning Face Representation from Scratch","created":"2014-11-28","cited_by_count":453},{"id":"1912.03458","title":"Dynamic Convolution: Attention over Convolution Kernels","created":"2019-12-07","cited_by_count":356},{"id":"2003.07853","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","created":"2020-03-17","cited_by_count":326},{"id":"1605.09673","title":"Dynamic Filter Networks","created":"2016-05-31","cited_by_count":319},{"id":"1711.11575","title":"Relation Networks for Object Detection","created":"2017-11-30","cited_by_count":305},{"id":"1612.04642","title":"Harmonic Networks: Deep Translation and Rotation Equivariance","created":"2016-12-14","cited_by_count":295},{"id":"1801.05599","title":"Additive Margin Softmax for Face Verification","created":"2018-01-17","cited_by_count":278},{"id":"1904.04971","title":"CondConv: Conditionally Parameterized Convolutions for Efficient Inference","created":"2019-04-10","cited_by_count":273},{"id":"1708.08197","title":"Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments","created":"2017-08-28","cited_by_count":260},{"id":"1910.03667","title":"REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs","created":"2019-10-08","cited_by_count":228},{"id":"1804.07573","title":"MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices","created":"2018-04-20","cited_by_count":182},{"id":"1807.06514","title":"BAM: Bottleneck Attention Module","created":"2018-07-17","cited_by_count":172},{"id":"1712.02327","title":"Burst Denoising with Kernel Prediction Networks","created":"2017-12-06","cited_by_count":157},{"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":"1904.05373","title":"Pixel-Adaptive Convolutional Neural Networks","created":"2019-04-10","cited_by_count":126},{"id":"1905.02188","title":"CARAFE: Content-Aware ReAssembly of FEatures","created":"2019-05-06","cited_by_count":119},{"id":"2103.06255","title":"Involution: Inverting the Inherence of Convolution for Visual Recognition","created":"2021-03-10","cited_by_count":99},{"id":"2010.06208","title":"DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets","created":"2020-10-13","cited_by_count":70},{"id":"2004.06965","title":"Unified Dynamic Convolutional Network for Super-Resolution with Variational Degradations","created":"2020-04-15","cited_by_count":61},{"id":"2104.14107","title":"Decoupled Dynamic Filter Networks","created":"2021-04-29","cited_by_count":53},{"id":"2003.12243","title":"Dynamic Region-Aware Convolution","created":"2020-03-27","cited_by_count":50},{"id":"2007.11823","title":"WeightNet: Revisiting the Design Space of Weight Networks","created":"2020-07-23","cited_by_count":50},{"id":"2004.10694","title":"DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks","created":"2020-04-22","cited_by_count":39},{"id":"2108.07895","title":"Adaptive Convolutions with Per-pixel Dynamic Filter Atom","created":"2021-08-17","cited_by_count":11},{"id":"2201.03817","title":"Tackling Multipath and Biased Training Data for IMU-Assisted BLE Proximity Detection","created":"2022-01-11","cited_by_count":5},{"id":"2107.11617","title":"LAConv: Local Adaptive Convolution for Image Fusion","created":"2021-07-24","cited_by_count":1}],"next_cursor":null}