{"list":"other","total":57,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"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":"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"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":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"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":"1801.09414","title":"CosFace: Large Margin Cosine Loss for Deep Face Recognition","created":"2018-01-29","cited_by_count":971},{"id":"1710.08092","title":"VGGFace2: A dataset for recognising faces across pose and age","created":"2017-10-23","cited_by_count":914},{"id":"1604.02878","title":"Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks","created":"2016-04-11","cited_by_count":903},{"id":"1704.08063","title":"SphereFace: Deep Hypersphere Embedding for Face Recognition","created":"2017-04-26","cited_by_count":737},{"id":"1607.08221","title":"MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition","created":"2016-07-27","cited_by_count":624},{"id":"1411.7923","title":"Learning Face Representation from Scratch","created":"2014-11-28","cited_by_count":453},{"id":"1702.08423","title":"Age Progression/Regression by Conditional Adversarial Autoencoder","created":"2017-02-27","cited_by_count":429},{"id":"1911.11907","title":"GhostNet: More Features from Cheap Operations","created":"2019-11-27","cited_by_count":410},{"id":"2002.10857","title":"Circle Loss: A Unified Perspective of Pair Similarity Optimization","created":"2020-02-25","cited_by_count":403},{"id":"2103.06627","title":"MagFace: A Universal Representation for Face Recognition and Quality Assessment","created":"2021-03-11","cited_by_count":334},{"id":"2004.00288","title":"CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition","created":"2020-04-01","cited_by_count":321},{"id":"1801.05599","title":"Additive Margin Softmax for Face Verification","created":"2018-01-17","cited_by_count":278},{"id":"1804.06655","title":"Deep Face Recognition: A Survey","created":"2018-04-18","cited_by_count":276},{"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":"2103.04098","title":"WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition","created":"2021-03-06","cited_by_count":223},{"id":"1512.00596","title":"The MegaFace Benchmark: 1 Million Faces for Recognition at Scale","created":"2015-12-02","cited_by_count":200},{"id":"1512.01274","title":"MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems","created":"2015-12-03","cited_by_count":195},{"id":"1511.02683","title":"A Light CNN for Deep Face Representation with Noisy Labels","created":"2015-11-09","cited_by_count":126},{"id":"1707.01629","title":"Dual Path Networks","created":"2017-07-06","cited_by_count":119},{"id":"1810.13243","title":"A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation","created":"2018-10-29","cited_by_count":110},{"id":"1905.00292","title":"AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations","created":"2019-05-01","cited_by_count":83},{"id":"1502.00873","title":"DeepID3: Face Recognition with Very Deep Neural Networks","created":"2015-02-03","cited_by_count":62},{"id":"1908.10654","title":"CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing","created":"2019-08-28","cited_by_count":61},{"id":"1912.00833","title":"Mis-classified Vector Guided Softmax Loss for Face Recognition","created":"2019-11-26","cited_by_count":60},{"id":"2101.04407","title":"FaceX-Zoo: A PyTorch Toolbox for Face Recognition","created":"2021-01-12","cited_by_count":49},{"id":"1705.00393","title":"Level Playing Field for Million Scale Face Recognition","created":"2017-05-01","cited_by_count":43},{"id":"1611.01484","title":"UMDFaces: An Annotated Face Dataset for Training Deep Networks","created":"2016-11-04","cited_by_count":42},{"id":"2102.08622","title":"Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-Training","created":"2021-02-17","cited_by_count":32},{"id":"2008.05314","title":"TF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture Search","created":"2020-08-12","cited_by_count":21},{"id":"1809.00338","title":"Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition","created":"2018-09-02","cited_by_count":20},{"id":"1506.07310","title":"Targeting Ultimate Accuracy: Face Recognition via Deep Embedding","created":"2015-06-24","cited_by_count":18},{"id":"2004.13954","title":"Rethink the Connections among Generalization, Memorization and the Spectral Bias of DNNs","created":"2020-04-29","cited_by_count":11},{"id":"1506.07704","title":"AttentionNet: Aggregating Weak Directions for Accurate Object Detection","created":"2015-06-25","cited_by_count":10},{"id":"1909.00632","title":"Towards Flops-constrained Face Recognition","created":"2019-09-02","cited_by_count":9}],"next_cursor":null}