{"list":"other","total":87,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"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":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1607.02533","title":"Adversarial examples in the physical world","created":"2016-07-08","cited_by_count":1769},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1611.01704","title":"End-to-end Optimized Image Compression","created":"2016-11-05","cited_by_count":696},{"id":"1907.11932","title":"Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment","created":"2019-07-27","cited_by_count":671},{"id":"1312.4400","title":"Network In Network","created":"2013-12-16","cited_by_count":605},{"id":"1709.01686","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","created":"2017-09-06","cited_by_count":596},{"id":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"id":"1312.6184","title":"Do Deep Nets Really Need to be Deep?","created":"2013-12-21","cited_by_count":474},{"id":"1412.5567","title":"Deep Speech: Scaling up end-to-end speech recognition","created":"2014-12-17","cited_by_count":354},{"id":"2004.12993","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","created":"2020-04-27","cited_by_count":332},{"id":"2006.04152","title":"BERT Loses Patience: Fast and Robust Inference with Early Exit","created":"2020-06-07","cited_by_count":273},{"id":"1910.10073","title":"Depth-Adaptive Transformer","created":"2019-10-22","cited_by_count":236},{"id":"2004.02178","title":"FastBERT: a Self-distilling BERT with Adaptive Inference Time","created":"2020-04-05","cited_by_count":226},{"id":"1312.6229","title":"OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks","created":"2013-12-21","cited_by_count":224},{"id":"1804.03230","title":"NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications","created":"2018-04-09","cited_by_count":147},{"id":"2003.07326","title":"Resolution Adaptive Networks for Efficient Inference","created":"2020-03-16","cited_by_count":146},{"id":"1611.05128","title":"Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning","created":"2016-11-16","cited_by_count":134},{"id":"1709.01921","title":"Distributed Deep Neural Networks over the Cloud, the Edge and End Devices","created":"2017-09-06","cited_by_count":120},{"id":"2008.06402","title":"SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud","created":"2020-08-14","cited_by_count":112},{"id":"1910.14315","title":"BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems","created":"2019-10-31","cited_by_count":95},{"id":"1801.08618","title":"JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services","created":"2018-01-25","cited_by_count":80},{"id":"1911.04118","title":"TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection","created":"2019-11-11","cited_by_count":74},{"id":"1902.01000","title":"BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Services","created":"2019-02-04","cited_by_count":68},{"id":"1908.06294","title":"Improved Techniques for Training Adaptive Deep Networks","created":"2019-08-17","cited_by_count":66},{"id":"1802.03931","title":"Deep feature compression for collaborative object detection","created":"2018-02-12","cited_by_count":48},{"id":"1806.08198","title":"DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures","created":"2018-06-21","cited_by_count":40},{"id":"1908.05024","title":"Person Re-identification in Aerial Imagery","created":"2019-08-14","cited_by_count":36},{"id":"1909.12978","title":"MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution","created":"2019-09-27","cited_by_count":36},{"id":"1804.06537","title":"Understanding Convolutional Neural Networks with Information Theory: An Initial Exploration","created":"2018-04-18","cited_by_count":32},{"id":"1907.04523","title":"Dual Dynamic Inference: Enabling More Efficient, Adaptive and Controllable Deep Inference","created":"2019-07-10","cited_by_count":31},{"id":"1804.00057","title":"Understanding Autoencoders with Information Theoretic Concepts","created":"2018-03-30","cited_by_count":29},{"id":"2006.16581","title":"Early Exit or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images","created":"2020-06-30","cited_by_count":28},{"id":"2007.15818","title":"Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks","created":"2020-07-31","cited_by_count":28},{"id":"1901.07947","title":"Machine Learning for Wireless Communications in the Internet of Things: A Comprehensive Survey","created":"2019-01-23","cited_by_count":27},{"id":"1603.08462","title":"Survey of Important Issues in UAV Communication Networks","created":"2016-03-28","cited_by_count":23},{"id":"1806.00746","title":"Eye in the Sky: Real-time Drone Surveillance System (DSS) for Violent Individuals Identification using ScatterNet Hybrid Deep Learning Network","created":"2018-06-03","cited_by_count":20},{"id":"1812.06426","title":"Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge","created":"2018-12-16","cited_by_count":20},{"id":"2005.02534","title":"The Cascade Transformer: an Application for Efficient Answer Sentence Selection","created":"2020-05-05","cited_by_count":20},{"id":"2002.07036","title":"Back-and-Forth prediction for deep tensor compression","created":"2020-02-14","cited_by_count":16},{"id":"1607.08011","title":"Understanding the limits of LoRaWAN","created":"2016-07-27","cited_by_count":11},{"id":"2007.13312","title":"Split Computing for Complex Object Detectors: Challenges and Preliminary Results","created":"2020-07-27","cited_by_count":7},{"id":"1806.05783","title":"Will TCP work in mmWave 5G Cellular Networks?","created":"2018-06-15","cited_by_count":4}],"next_cursor":null}