{"list":"other","total":69,"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","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":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"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":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1505.00853","title":"Empirical Evaluation of Rectified Activations in Convolutional Network","created":"2015-05-05","cited_by_count":519},{"id":"1611.09813","title":"Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision","created":"2016-11-29","cited_by_count":494},{"id":"1310.1531","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","created":"2013-10-06","cited_by_count":424},{"id":"1705.03098","title":"A simple yet effective baseline for 3d human pose estimation","created":"2017-05-08","cited_by_count":401},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"1602.00134","title":"Convolutional Pose Machines","created":"2016-01-30","cited_by_count":325},{"id":"1312.4659","title":"DeepPose: Human Pose Estimation via Deep Neural Networks","created":"2013-12-17","cited_by_count":305},{"id":"1411.4280","title":"Efficient Object Localization Using Convolutional Networks","created":"2014-11-16","cited_by_count":227},{"id":"1611.07828","title":"Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose","created":"2016-11-23","cited_by_count":221},{"id":"2012.13392","title":"Deep Learning-Based Human Pose Estimation: A Survey","created":"2020-12-24","cited_by_count":207},{"id":"1804.03142","title":"Markerless tracking of user-defined features with deep learning","created":"2018-04-09","cited_by_count":206},{"id":"1611.10012","title":"Speed/accuracy trade-offs for modern convolutional object detectors","created":"2016-11-30","cited_by_count":198},{"id":"1506.04878","title":"End-to-end people detection in crowded scenes","created":"2015-06-16","cited_by_count":140},{"id":"1406.2984","title":"Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation","created":"2014-06-11","cited_by_count":129},{"id":"1611.09326","title":"The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation","created":"2016-11-28","cited_by_count":122},{"id":"1511.06645","title":"DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation","created":"2015-11-20","cited_by_count":117},{"id":"2004.00060","title":"HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation","created":"2020-03-31","cited_by_count":112},{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99},{"id":"1605.03170","title":"DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model","created":"2016-05-10","cited_by_count":96},{"id":"2012.06567","title":"A Comprehensive Study of Deep Video Action Recognition","created":"2020-12-11","cited_by_count":88},{"id":"1701.00295","title":"Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image","created":"2017-01-01","cited_by_count":73},{"id":"2006.01423","title":"Monocular Human Pose Estimation: A Survey of Deep Learning-based Methods","created":"2020-06-02","cited_by_count":59},{"id":"1506.02897","title":"Flowing ConvNets for Human Pose Estimation in Videos","created":"2015-06-09","cited_by_count":55},{"id":"1604.07669","title":"Real-time Action Recognition with Enhanced Motion Vector CNNs","created":"2016-04-26","cited_by_count":51},{"id":"1909.13868","title":"Deep learning tools for the measurement of animal behavior in neuroscience","created":"2019-09-30","cited_by_count":44},{"id":"1605.05180","title":"Structured Prediction of 3D Human Pose with Deep Neural Networks","created":"2016-05-17","cited_by_count":43},{"id":"1803.06316","title":"Temporal Gaussian Mixture Layer for Videos","created":"2018-03-16","cited_by_count":40},{"id":"1508.06708","title":"Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation","created":"2015-08-27","cited_by_count":37},{"id":"1807.11195","title":"Multi-Fiber Networks for Video Recognition","created":"2018-07-30","cited_by_count":34},{"id":"2110.00111","title":"Deep Learning-based Action Detection in Untrimmed Videos: A Survey","created":"2021-09-30","cited_by_count":32},{"id":"1712.06316","title":"LSTM Pose Machines","created":"2017-12-18","cited_by_count":28},{"id":"1511.06692","title":"Direct Prediction of 3D Body Poses from Motion Compensated Sequences","created":"2015-11-20","cited_by_count":26},{"id":"1407.3399","title":"Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations","created":"2014-07-12","cited_by_count":24},{"id":"1704.00389","title":"Hidden Two-Stream Convolutional Networks for Action Recognition","created":"2017-04-02","cited_by_count":24},{"id":"1310.4249","title":"Mapping the stereotyped behaviour of freely-moving fruit flies","created":"2013-10-16","cited_by_count":21},{"id":"1612.03052","title":"ActionFlowNet: Learning Motion Representation for Action Recognition","created":"2016-12-09","cited_by_count":18},{"id":"1405.4506","title":"Bag of Visual Words and Fusion Methods for Action Recognition: Comprehensive Study and Good Practice","created":"2014-05-18","cited_by_count":13},{"id":"1712.05784","title":"Measuring behavior across scales","created":"2017-12-15","cited_by_count":10},{"id":"2112.01987","title":"Leaving Flatland: Advances in 3D behavioral measurement","created":"2021-12-03","cited_by_count":10},{"id":"1409.7963","title":"MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation","created":"2014-09-28","cited_by_count":6},{"id":"2010.00641","title":"Multiscale Detection of Cancerous Tissue in High Resolution Slide Scans","created":"2020-10-01","cited_by_count":6},{"id":"1608.08851","title":"Efficient Two-Stream Motion and Appearance 3D CNNs for Video Classification","created":"2016-08-31","cited_by_count":5},{"id":"2208.03819","title":"Cross-Skeleton Interaction Graph Aggregation Network for Representation Learning of Mouse Social Behaviour","created":"2022-08-07","cited_by_count":4}],"next_cursor":null}