{"list":"other","total":134,"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":"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":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"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":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"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":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"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":"1803.01271","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","created":"2018-03-04","cited_by_count":1476},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"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":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"1412.6806","title":"Striving for Simplicity: The All Convolutional Net","created":"2014-12-21","cited_by_count":990},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"1406.4729","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","created":"2014-06-18","cited_by_count":720},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"1802.03601","title":"Deep Visual Domain Adaptation: A Survey","created":"2018-02-10","cited_by_count":635},{"id":"2009.07896","title":"Captum: A unified and generic model interpretability library for PyTorch","created":"2020-09-16","cited_by_count":547},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"2004.01888","title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","created":"2020-04-04","cited_by_count":490},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1812.11703","title":"SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks","created":"2018-12-31","cited_by_count":446},{"id":"1812.01187","title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","created":"2018-12-04","cited_by_count":431},{"id":"1605.06409","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","created":"2016-05-20","cited_by_count":414},{"id":"1901.00976","title":"Contrastive Adaptation Network for Unsupervised Domain Adaptation","created":"2019-01-04","cited_by_count":407},{"id":"1903.05625","title":"Tracking without bells and whistles","created":"2019-03-13","cited_by_count":382},{"id":"1911.11929","title":"CSPNet: A New Backbone that can Enhance Learning Capability of CNN","created":"2019-11-27","cited_by_count":381},{"id":"2105.03247","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","created":"2021-05-07","cited_by_count":381},{"id":"1903.01945","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","created":"2019-03-05","cited_by_count":373},{"id":"2012.15460","title":"TransTrack: Multiple Object Tracking with Transformer","created":"2020-12-31","cited_by_count":371},{"id":"1503.04069","title":"LSTM: A Search Space Odyssey","created":"2015-03-13","cited_by_count":316},{"id":"1511.05440","title":"Deep multi-scale video prediction beyond mean square error","created":"2015-11-17","cited_by_count":300},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"1904.11490","title":"RepPoints: Point Set Representation for Object Detection","created":"2019-04-25","cited_by_count":264},{"id":"1810.12890","title":"DropBlock: A regularization method for convolutional networks","created":"2018-10-30","cited_by_count":262},{"id":"1904.02701","title":"Libra R-CNN: Towards Balanced Learning for Object Detection","created":"2019-04-04","cited_by_count":255},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"2006.06664","title":"Quasi-Dense Similarity Learning for Multiple Object Tracking","created":"2020-06-11","cited_by_count":220},{"id":"1606.07536","title":"Coupled Generative Adversarial Networks","created":"2016-06-24","cited_by_count":216},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"1604.06182","title":"The THUMOS Challenge on Action Recognition for Videos \"in the Wild\"","created":"2016-04-21","cited_by_count":213},{"id":"2011.08036","title":"Scaled-YOLOv4: Scaling Cross Stage Partial Network","created":"2020-11-16","cited_by_count":211},{"id":"2103.14259","title":"OTA: Optimal Transport Assignment for Object Detection","created":"2021-03-26","cited_by_count":178},{"id":"1607.03516","title":"Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation","created":"2016-07-12","cited_by_count":163},{"id":"1901.01892","title":"Scale-Aware Trident Networks for Object Detection","created":"2019-01-07","cited_by_count":159},{"id":"1901.08043","title":"Bottom-up Object Detection by Grouping Extreme and Center Points","created":"2019-01-23","cited_by_count":156},{"id":"2103.08808","title":"Track to Detect and Segment: An Online Multi-Object Tracker","created":"2021-03-16","cited_by_count":156},{"id":"1612.01939","title":"Correlation Alignment for Unsupervised Domain Adaptation","created":"2016-12-06","cited_by_count":147},{"id":"1605.08110","title":"Video Summarization with Long Short-term Memory","created":"2016-05-26","cited_by_count":142},{"id":"1908.08681","title":"Mish: A Self Regularized Non-Monotonic Activation Function","created":"2019-08-23","cited_by_count":141},{"id":"1903.00621","title":"Feature Selective Anchor-Free Module for Single-Shot Object Detection","created":"2019-03-02","cited_by_count":139},{"id":"1701.06659","title":"DSSD : Deconvolutional Single Shot Detector","created":"2017-01-23","cited_by_count":131},{"id":"1907.09408","title":"A Survey of Deep Learning-based Object Detection","created":"2019-07-11","cited_by_count":106},{"id":"1812.01289","title":"Timeception for Complex Action Recognition","created":"2018-12-04","cited_by_count":89},{"id":"1811.04533","title":"M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network","created":"2018-11-12","cited_by_count":76},{"id":"1803.10699","title":"Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment","created":"2018-03-28","cited_by_count":74},{"id":"2003.02824","title":"Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation","created":"2020-03-05","cited_by_count":74},{"id":"1805.12233","title":"How Important Is a Neuron?","created":"2018-05-30","cited_by_count":73},{"id":"2012.10671","title":"SMART Frame Selection for Action Recognition","created":"2020-12-19","cited_by_count":73},{"id":"1703.08132","title":"Weakly Supervised Action Learning with RNN based Fine-to-coarse Modeling","created":"2017-03-23","cited_by_count":70},{"id":"2104.03541","title":"Multiple Object Tracking with Correlation Learning","created":"2021-04-08","cited_by_count":67},{"id":"1911.12983","title":"Correlation-aware Adversarial Domain Adaptation and Generalization","created":"2019-11-29","cited_by_count":65},{"id":"2105.11595","title":"SiamMOT: Siamese Multi-Object Tracking","created":"2021-05-25","cited_by_count":62},{"id":"1505.04868","title":"Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors","created":"2015-05-19","cited_by_count":58}],"next_cursor":"100"}