{"list":"other","total":56,"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"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":"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":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"1804.03209","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","created":"2018-04-09","cited_by_count":752},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"1904.01169","title":"Res2Net: A New Multi-scale Backbone Architecture","created":"2019-04-02","cited_by_count":470},{"id":"1903.06586","title":"Selective Kernel Networks","created":"2019-03-15","cited_by_count":403},{"id":"1904.11492","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","created":"2019-04-25","cited_by_count":331},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"1805.07932","title":"Bilinear Attention Networks","created":"2018-05-21","cited_by_count":280},{"id":"1607.01668","title":"Tensor Decomposition for Signal Processing and Machine Learning","created":"2016-07-06","cited_by_count":224},{"id":"1908.07678","title":"Asymmetric Non-local Neural Networks for Semantic Segmentation","created":"2019-08-21","cited_by_count":196},{"id":"1702.08591","title":"The Shattered Gradients Problem: If resnets are the answer, then what is the question?","created":"2017-02-28","cited_by_count":157},{"id":"1810.12348","title":"Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks","created":"2018-10-29","cited_by_count":139},{"id":"1810.11579","title":"$A^2$-Nets: Double Attention Networks","created":"2018-10-27","cited_by_count":136},{"id":"2006.06668","title":"Disentangled Non-Local Neural Networks","created":"2020-06-11","cited_by_count":132},{"id":"1803.02579","title":"Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks","created":"2018-03-07","cited_by_count":122},{"id":"1707.01629","title":"Dual Path Networks","created":"2017-07-06","cited_by_count":119},{"id":"1708.01471","title":"Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering","created":"2017-08-04","cited_by_count":117},{"id":"1611.04231","title":"Identity Matters in Deep Learning","created":"2016-11-14","cited_by_count":109},{"id":"1708.02691","title":"Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations","created":"2017-08-09","cited_by_count":104},{"id":"1906.09777","title":"A Tensorized Transformer for Language Modeling","created":"2019-06-24","cited_by_count":86},{"id":"1804.08450","title":"Decorrelated Batch Normalization","created":"2018-04-23","cited_by_count":83},{"id":"1412.1710","title":"Convolutional Neural Networks at Constrained Time Cost","created":"2014-12-04","cited_by_count":81},{"id":"1410.1141","title":"On the Computational Efficiency of Training Neural Networks","created":"2014-10-05","cited_by_count":71},{"id":"1905.12207","title":"On the Expressive Power of Deep Polynomial Neural Networks","created":"2019-05-29","cited_by_count":66},{"id":"1909.11519","title":"Gated Channel Transformation for Visual Recognition","created":"2019-09-25","cited_by_count":43},{"id":"1705.05502","title":"The power of deeper networks for expressing natural functions","created":"2017-05-16","cited_by_count":35},{"id":"1603.00162","title":"Convolutional Rectifier Networks as Generalized Tensor Decompositions","created":"2016-03-01","cited_by_count":32},{"id":"1906.04972","title":"Toward Interpretable Music Tagging with Self-Attention","created":"2019-06-12","cited_by_count":30},{"id":"2004.01961","title":"Neural Architecture Search for Lightweight Non-Local Networks","created":"2020-04-04","cited_by_count":23},{"id":"2009.04075","title":"Multilinear Latent Conditioning for Generating Unseen Attribute Combinations","created":"2020-09-09","cited_by_count":14},{"id":"1611.05709","title":"Factorized Bilinear Models for Image Recognition","created":"2016-11-17","cited_by_count":13},{"id":"1909.05479","title":"Generating Accurate Pseudo-labels in Semi-Supervised Learning and Avoiding Overconfident Predictions via Hermite Polynomial Activations","created":"2019-09-12","cited_by_count":13},{"id":"1804.06739","title":"Are ResNets Provably Better than Linear Predictors?","created":"2018-04-18","cited_by_count":12},{"id":"1805.07477","title":"Norm-Preservation: Why Residual Networks Can Become Extremely Deep?","created":"2018-05-18","cited_by_count":12},{"id":"2104.05077","title":"CoPE: Conditional image generation using Polynomial Expansions","created":"2021-04-11","cited_by_count":12},{"id":"1802.01808","title":"Mixed Link Networks","created":"2018-02-06","cited_by_count":10},{"id":"1908.06571","title":"PolyGAN: High-Order Polynomial Generators","created":"2019-08-19","cited_by_count":10},{"id":"1703.06993","title":"SORT: Second-Order Response Transform for Visual Recognition","created":"2017-03-20","cited_by_count":8},{"id":"1909.03834","title":"Linear Context Transform Block","created":"2019-09-06","cited_by_count":5}],"next_cursor":null}