{"list":"other","total":88,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"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":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"1612.00137","title":"RMPE: Regional Multi-person Pose Estimation","created":"2016-12-01","cited_by_count":340},{"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":"1511.06523","title":"WIDER FACE: A Face Detection Benchmark","created":"2015-11-20","cited_by_count":298},{"id":"1909.04349","title":"FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images","created":"2019-09-10","cited_by_count":271},{"id":"1807.10267","title":"Generating 3D faces using Convolutional Mesh Autoencoders","created":"2018-07-26","cited_by_count":268},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"1801.01615","title":"Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies","created":"2018-01-05","cited_by_count":239},{"id":"1705.01389","title":"Learning to Estimate 3D Hand Pose from Single RGB Images","created":"2017-05-03","cited_by_count":234},{"id":"1704.07809","title":"Hand Keypoint Detection in Single Images using Multiview Bootstrapping","created":"2017-04-25","cited_by_count":231},{"id":"1903.05134","title":"Universally Slimmable Networks and Improved Training Techniques","created":"2019-03-12","cited_by_count":221},{"id":"1812.00324","title":"CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark","created":"2018-12-02","cited_by_count":214},{"id":"1611.05424","title":"Associative Embedding: End-to-End Learning for Joint Detection and Grouping","created":"2016-11-16","cited_by_count":212},{"id":"1902.03451","title":"3D Hand Shape and Pose from Images in the Wild","created":"2019-02-09","cited_by_count":190},{"id":"2003.11142","title":"BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models","created":"2020-03-24","cited_by_count":188},{"id":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"id":"1710.10000","title":"PoseTrack: A Benchmark for Human Pose Estimation and Tracking","created":"2017-10-27","cited_by_count":173},{"id":"1910.06278","title":"Distribution-Aware Coordinate Representation for Human Pose Estimation","created":"2019-10-14","cited_by_count":165},{"id":"1812.01598","title":"Monocular Total Capture: Posing Face, Body, and Hands in the Wild","created":"2018-12-04","cited_by_count":162},{"id":"1712.01057","title":"GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB","created":"2017-12-04","cited_by_count":147},{"id":"1805.10483","title":"Look at Boundary: A Boundary-Aware Face Alignment Algorithm","created":"2018-05-26","cited_by_count":138},{"id":"1803.08225","title":"PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model","created":"2018-03-22","cited_by_count":133},{"id":"1701.01779","title":"Towards Accurate Multi-person Pose Estimation in the Wild","created":"2017-01-06","cited_by_count":131},{"id":"1904.07399","title":"Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression","created":"2019-04-16","cited_by_count":128},{"id":"1511.06645","title":"DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation","created":"2015-11-20","cited_by_count":117},{"id":"1904.04196","title":"Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Rendering","created":"2019-04-08","cited_by_count":115},{"id":"2004.00060","title":"HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation","created":"2020-03-31","cited_by_count":112},{"id":"1711.06753","title":"Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks","created":"2017-11-17","cited_by_count":109},{"id":"1605.03170","title":"DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model","created":"2016-05-10","cited_by_count":96},{"id":"1905.02876","title":"Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation","created":"2019-05-08","cited_by_count":90},{"id":"2004.02980","title":"LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood","created":"2020-04-06","cited_by_count":87},{"id":"1704.02201","title":"Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor","created":"2017-04-07","cited_by_count":84},{"id":"1905.13214","title":"On Network Design Spaces for Visual Recognition","created":"2019-05-30","cited_by_count":68},{"id":"1702.07432","title":"Multi-Context Attention for Human Pose Estimation","created":"2017-02-24","cited_by_count":66},{"id":"2001.01233","title":"EcoNAS: Finding Proxies for Economical Neural Architecture Search","created":"2020-01-05","cited_by_count":61},{"id":"1803.04108","title":"Style Aggregated Network for Facial Landmark Detection","created":"2018-03-12","cited_by_count":60},{"id":"1708.01101","title":"Learning Feature Pyramids for Human Pose Estimation","created":"2017-08-03","cited_by_count":57},{"id":"1807.00966","title":"Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors","created":"2018-07-03","cited_by_count":49},{"id":"1704.02612","title":"BigHand2.2M Benchmark: Hand Pose Dataset and State of the Art Analysis","created":"2017-04-09","cited_by_count":46},{"id":"1611.07727","title":"PoseTrack: Joint Multi-Person Pose Estimation and Tracking","created":"2016-11-23","cited_by_count":44},{"id":"1706.01789","title":"Deep Alignment Network: A convolutional neural network for robust face alignment","created":"2017-06-06","cited_by_count":44},{"id":"1903.09214","title":"Multi-person Articulated Tracking with Spatial and Temporal Embeddings","created":"2019-03-21","cited_by_count":38},{"id":"1408.3967","title":"Learning Deep Representation for Face Alignment with Auxiliary Attributes","created":"2014-08-18","cited_by_count":32},{"id":"1602.04124","title":"Fast and Robust Hand Tracking Using Detection-Guided Optimization","created":"2016-02-12","cited_by_count":30},{"id":"1910.02543","title":"Improving One-shot NAS by Suppressing the Posterior Fading","created":"2019-10-06","cited_by_count":28},{"id":"1612.01465","title":"ArtTrack: Articulated Multi-person Tracking in the Wild","created":"2016-12-05","cited_by_count":27},{"id":"2105.10154","title":"ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search","created":"2021-05-21","cited_by_count":26},{"id":"1909.13423","title":"Single-Network Whole-Body Pose Estimation","created":"2019-09-30","cited_by_count":24},{"id":"1611.05396","title":"Dynamic Attention-controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-set Sample Weighting","created":"2016-11-16","cited_by_count":20},{"id":"1707.03742","title":"Large-scale Multiview 3D Hand Pose Dataset","created":"2017-07-12","cited_by_count":20},{"id":"1802.06713","title":"Disentangling 3D Pose in A Dendritic CNN for Unconstrained 2D Face Alignment","created":"2018-02-19","cited_by_count":18},{"id":"1912.11234","title":"Computation Reallocation for Object Detection","created":"2019-12-24","cited_by_count":17},{"id":"2001.08869","title":"Nonparametric Structure Regularization Machine for 2D Hand Pose Estimation","created":"2020-01-24","cited_by_count":12},{"id":"1708.06023","title":"Joint Multi-view Face Alignment in the Wild","created":"2017-08-20","cited_by_count":11},{"id":"2012.09496","title":"Exploiting Learnable Joint Groups for Hand Pose Estimation","created":"2020-12-17","cited_by_count":11},{"id":"1511.07356","title":"Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation","created":"2015-11-23","cited_by_count":10},{"id":"1910.11535","title":"TRB: A Novel Triplet Representation for Understanding 2D Human Body","created":"2019-10-25","cited_by_count":10},{"id":"2012.07086","title":"EfficientPose: Efficient Human Pose Estimation with Neural Architecture Search","created":"2020-12-13","cited_by_count":10},{"id":"2001.08047","title":"Attention! A Lightweight 2D Hand Pose Estimation Approach","created":"2020-01-22","cited_by_count":9},{"id":"2012.13587","title":"Inception Convolution with Efficient Dilation Search","created":"2020-12-25","cited_by_count":9},{"id":"2008.07018","title":"AutoPose: Searching Multi-Scale Branch Aggregation for Pose Estimation","created":"2020-08-16","cited_by_count":6}],"next_cursor":null}