{"list":"other","total":83,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1312.4400","title":"Network In Network","created":"2013-12-16","cited_by_count":605},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1912.12033","title":"Deep Learning for 3D Point Clouds: A Survey","created":"2019-12-27","cited_by_count":558},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"1801.10198","title":"Generating Wikipedia by Summarizing Long Sequences","created":"2018-01-30","cited_by_count":335},{"id":"1610.09001","title":"SoundNet: Learning Sound Representations from Unlabeled Video","created":"2016-10-27","cited_by_count":247},{"id":"1607.03250","title":"Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures","created":"2016-07-12","cited_by_count":221},{"id":"2004.03333","title":"Binary Neural Networks: A Survey","created":"2020-03-31","cited_by_count":190},{"id":"1611.07715","title":"Deep Feature Flow for Video Recognition","created":"2016-11-23","cited_by_count":186},{"id":"1707.01213","title":"Data-Driven Sparse Structure Selection for Deep Neural Networks","created":"2017-07-05","cited_by_count":181},{"id":"1703.10025","title":"Flow-Guided Feature Aggregation for Video Object Detection","created":"2017-03-29","cited_by_count":177},{"id":"1810.11809","title":"Discrimination-aware Channel Pruning for Deep Neural Networks","created":"2018-10-28","cited_by_count":171},{"id":"1704.03471","title":"What do Neural Machine Translation Models Learn about Morphology?","created":"2017-04-11","cited_by_count":166},{"id":"2006.03236","title":"Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing","created":"2020-06-05","cited_by_count":162},{"id":"1904.05049","title":"Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution","created":"2019-04-10","cited_by_count":140},{"id":"1811.12432","title":"AdaFrame: Adaptive Frame Selection for Fast Video Recognition","created":"2018-11-29","cited_by_count":134},{"id":"1904.04289","title":"SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition","created":"2019-04-08","cited_by_count":134},{"id":"1810.05331","title":"Dynamic Channel Pruning: Feature Boosting and Suppression","created":"2018-10-12","cited_by_count":129},{"id":"1812.09355","title":"What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models","created":"2018-12-21","cited_by_count":124},{"id":"2007.00072","title":"Data Movement Is All You Need: A Case Study on Optimizing Transformers","created":"2020-06-30","cited_by_count":108},{"id":"1511.06984","title":"End-to-end Learning of Action Detection from Frame Glimpses in Videos","created":"2015-11-22","cited_by_count":101},{"id":"2002.11985","title":"Compressing Large-Scale Transformer-Based Models: A Case Study on BERT","created":"2020-02-27","cited_by_count":96},{"id":"1808.04752","title":"A Survey on Methods and Theories of Quantized Neural Networks","created":"2018-08-13","cited_by_count":75},{"id":"1602.08465","title":"Seq-NMS for Video Object Detection","created":"2016-02-26","cited_by_count":68},{"id":"1604.02532","title":"T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos","created":"2016-04-09","cited_by_count":67},{"id":"1907.13369","title":"Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition","created":"2019-07-31","cited_by_count":66},{"id":"1711.11577","title":"Towards High Performance Video Object Detection","created":"2017-11-30","cited_by_count":60},{"id":"1904.02422","title":"Resource Efficient 3D Convolutional Neural Networks","created":"2019-04-04","cited_by_count":50},{"id":"1502.07209","title":"Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks","created":"2015-02-25","cited_by_count":45},{"id":"1812.04368","title":"Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression","created":"2018-12-11","cited_by_count":40},{"id":"1711.06368","title":"Mobile Video Object Detection with Temporally-Aware Feature Maps","created":"2017-11-17","cited_by_count":39},{"id":"1703.02529","title":"NoScope: Optimizing Neural Network Queries over Video at Scale","created":"2017-03-07","cited_by_count":37},{"id":"1412.6071","title":"Fractional Max-Pooling","created":"2014-12-18","cited_by_count":35},{"id":"1812.04056","title":"Accelerating Convolutional Neural Networks via Activation Map Compression","created":"2018-12-10","cited_by_count":34},{"id":"1812.00353","title":"Accelerate CNN via Recursive Bayesian Pruning","created":"2018-12-02","cited_by_count":27},{"id":"1902.02910","title":"AdaScale: Towards Real-time Video Object Detection Using Adaptive Scaling","created":"2019-02-08","cited_by_count":27},{"id":"1804.05472","title":"Optimizing Video Object Detection via a Scale-Time Lattice","created":"2018-04-16","cited_by_count":25},{"id":"1702.06355","title":"Object Detection in Videos with Tubelet Proposal Networks","created":"2017-02-21","cited_by_count":24},{"id":"1711.05187","title":"Dynamic Zoom-in Network for Fast Object Detection in Large Images","created":"2017-11-14","cited_by_count":23},{"id":"1811.00641","title":"Online Embedding Compression for Text Classification using Low Rank Matrix Factorization","created":"2018-11-01","cited_by_count":22},{"id":"1902.10345","title":"Stateful Dataflow Multigraphs: A Data-Centric Model for Performance Portability on Heterogeneous Architectures","created":"2019-02-27","cited_by_count":21},{"id":"1804.06508","title":"UCNN: Exploiting Computational Reuse in Deep Neural Networks via Weight Repetition","created":"2018-04-18","cited_by_count":20},{"id":"1412.5661","title":"DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection","created":"2014-12-17","cited_by_count":19},{"id":"1504.08362","title":"PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions","created":"2015-04-30","cited_by_count":17},{"id":"1709.04347","title":"Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection","created":"2017-09-13","cited_by_count":13},{"id":"1803.05729","title":"Exploring Linear Relationship in Feature Map Subspace for ConvNets Compression","created":"2018-03-15","cited_by_count":11},{"id":"2005.12193","title":"Feature Statistics Guided Efficient Filter Pruning","created":"2020-05-21","cited_by_count":11},{"id":"1804.05830","title":"Towards High Performance Video Object Detection for Mobiles","created":"2018-04-16","cited_by_count":9},{"id":"1810.06807","title":"Morph: Flexible Acceleration for 3D CNN-based Video Understanding","created":"2018-10-16","cited_by_count":9},{"id":"1704.04313","title":"CBinfer: Change-Based Inference for Convolutional Neural Networks on Video Data","created":"2017-04-14","cited_by_count":8},{"id":"1810.00434","title":"CaTDet: Cascaded Tracked Detector for Efficient Object Detection from Video","created":"2018-09-30","cited_by_count":7},{"id":"1604.00427","title":"Leaving Some Stones Unturned: Dynamic Feature Prioritization for Activity Detection in Streaming Video","created":"2016-04-01","cited_by_count":6},{"id":"1604.03239","title":"CRAFT Objects from Images","created":"2016-04-12","cited_by_count":6},{"id":"1808.05488","title":"CBinfer: Exploiting Frame-to-Frame Locality for Faster Convolutional Network Inference on Video Streams","created":"2018-08-15","cited_by_count":6},{"id":"1909.07636","title":"Thanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural Networks","created":"2019-09-17","cited_by_count":6},{"id":"2003.12621","title":"Acceleration of Convolutional Neural Network Using FFT-Based Split Convolutions","created":"2020-03-27","cited_by_count":6},{"id":"1610.03950","title":"Compressing Neural Language Models by Sparse Word Representations","created":"2016-10-13","cited_by_count":4},{"id":"2005.13796","title":"A Feature-map Discriminant Perspective for Pruning Deep Neural Networks","created":"2020-05-28","cited_by_count":4},{"id":"1812.06611","title":"A Layer Decomposition-Recomposition Framework for Neuron Pruning towards Accurate Lightweight Networks","created":"2018-12-17","cited_by_count":2},{"id":"1906.07912","title":"ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection","created":"2019-06-19","cited_by_count":2},{"id":"2008.06543","title":"AntiDote: Attention-based Dynamic Optimization for Neural Network Runtime Efficiency","created":"2020-08-14","cited_by_count":2},{"id":"1708.03795","title":"Kill Two Birds With One Stone: Boosting Both Object Detection Accuracy and Speed With adaptive Patch-of-Interest Composition","created":"2017-08-12","cited_by_count":1}],"next_cursor":null}