DeepPose: Human Pose Estimation via Deep Neural Networks

Abstract

We propose a method for human pose estimation based on Deep Neural Networks (DNNs). The pose estimation is formulated as a DNN-based regression problem towards body joints. We present a cascade of such DNN regressors which results in high precision pose estimates. The approach has the advantage of reasoning about pose in a holistic fashion and has a simple but yet powerful formulation which capitalizes on recent advances in Deep Learning. We present a detailed empirical analysis with state-of-art or better performance on four academic benchmarks of diverse real-world images.

IEEE Conference on Computer Vision and Pattern Recognition, 2014

Cited by in corpus (434)

• Improved Regularization of Convolutional Neural Networks with Cutout
• AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild
• How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)
• Going Deeper with Convolutions
• A Survey of Deep Learning-based Object Detection
• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• Going Deeper in Facial Expression Recognition using Deep Neural Networks
• Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19
• Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
• OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
• CNN Features off-the-shelf: an Astounding Baseline for Recognition
• Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
• Human pose estimation via Convolutional Part Heatmap Regression
• Speeding up Convolutional Neural Networks with Low Rank Expansions
• Stacked Hourglass Networks for Human Pose Estimation
• Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network
• Deep learning tools for the measurement of animal behavior in neuroscience
• Monocular Human Pose Estimation: A Survey of Deep Learning-based Methods
• GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
• Integrating Spatial Configuration into Heatmap Regression Based CNNs for Landmark Localization
• A Comprehensive Analysis of Deep Regression
• Beyond Skip Connections: Top-Down Modulation for Object Detection
• Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations
• Deep Human Parsing with Active Template Regression
• Recent Advances in Convolutional Neural Networks
• Hands Deep in Deep Learning for Hand Pose Estimation
• LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images
• Convolutional Pose Machines
• Loss Functions and Metrics in Deep Learning
• Object Detection from Video Tubelets with Convolutional Neural Networks
• A Primer on Motion Capture with Deep Learning: Principles, Pitfalls and Perspectives
• Human Pose Regression by Combining Indirect Part Detection and Contextual Information
• MIT Advanced Vehicle Technology Study: Large-Scale Naturalistic Driving Study of Driver Behavior and Interaction with Automation
• Deep Pictorial Gaze Estimation
• Stand-Alone Self-Attention in Vision Models
• Pose Guided Structured Region Ensemble Network for Cascaded Hand Pose Estimation
• Perceiver IO: A General Architecture for Structured Inputs & Outputs
• MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild
• Deep Ranking for Person Re-identification via Joint Representation Learning
• Numerical Coordinate Regression with Convolutional Neural Networks
• Pose Invariant Embedding for Deep Person Re-identification
• Enabling and Emerging Technologies for Social Distancing: A Comprehensive Survey and Open Problems
• Learning to Find Eye Region Landmarks for Remote Gaze Estimation in Unconstrained Settings
• Houdini: Fooling Deep Structured Prediction Models
• DISC: Deep Image Saliency Computing via Progressive Representation Learning
• Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources
• Do Convnets Learn Correspondence?
• Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition
• RepPoints: Point Set Representation for Object Detection
• AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding
• Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning
• Vision-Based Assessment of Parkinsonism and Levodopa-Induced Dyskinesia with Deep Learning Pose Estimation
• R-CNNs for Pose Estimation and Action Detection
• Learning Contextual Dependencies with Convolutional Hierarchical Recurrent Neural Networks
• Compression Artifacts Removal Using Convolutional Neural Networks
• MoVi: A Large Multipurpose Motion and Video Dataset
• Simple Baselines for Human Pose Estimation and Tracking
• Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring
• MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency
• MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation
• Deep Reinforcement Learning for Visual Object Tracking in Videos
• Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
• Single Image 3D Interpreter Network
• EfficientPose: Scalable single-person pose estimation
• Vision-Based Human Pose Estimation via Deep Learning: A Survey
• SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization
• Combining Local Appearance and Holistic View: Dual-Source Deep Neural Networks for Human Pose Estimation
• Deep Video Generation, Prediction and Completion of Human Action Sequences
• Deep Learning-Based Human Pose Estimation: A Survey
• Flowing ConvNets for Human Pose Estimation in Videos
• Stacked Deconvolutional Network for Semantic Segmentation
• Bio-LSTM: A Biomechanically Inspired Recurrent Neural Network for 3D Pedestrian Pose and Gait Prediction
• Facial Expression Recognition from World Wild Web
• Machine Learning: Algorithms, Models, and Applications
• Structured Landmark Detection via Topology-Adapting Deep Graph Learning
• Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
• Towards Accurate Multi-person Pose Estimation in the Wild
• Recurrent Network Models for Human Dynamics
• Identification of Low Surface Brightness Tidal Features in Galaxies Using Convolutional Neural Networks
• BodyNet: Volumetric Inference of 3D Human Body Shapes
• Synthesizing Training Images for Boosting Human 3D Pose Estimation
• Analyzing Modular CNN Architectures for Joint Depth Prediction and Semantic Segmentation
• OriNet: A Fully Convolutional Network for 3D Human Pose Estimation
• Human Pose Estimation with Spatial Contextual Information
• Learning Feature Pyramids for Human Pose Estimation
• RMPE: Regional Multi-person Pose Estimation
• Robust 3D Hand Pose Estimation in Single Depth Images: from Single-View CNN to Multi-View CNNs
• Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
• Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models
• Self-supervised Learning of Interpretable Keypoints from Unlabelled Videos
• Deep High-Resolution Representation Learning for Human Pose Estimation
• TFPose: Direct Human Pose Estimation with Transformers
• Acquisition of Localization Confidence for Accurate Object Detection
• Efficient Convolutional Neural Networks for Depth-Based Multi-Person Pose Estimation
• Pose Trainer: Correcting Exercise Posture using Pose Estimation
• Deformation Capture via Soft and Stretchable Sensor Arrays
• Deep Part Induction from Articulated Object Pairs
• Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnn
• Markerless human pose estimation for biomedical applications: a survey
• Structured Prediction of 3D Human Pose with Deep Neural Networks
• Looking at Outfit to Parse Clothing
• iMapper: Interaction-guided Joint Scene and Human Motion Mapping from Monocular Videos
• Time-series modeling with undecimated fully convolutional neural networks
• Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network
• Towards human-level performance on automatic pose estimation of infant spontaneous movements
• Visual7W: Grounded Question Answering in Images
• Distribution-Aware Coordinate Representation for Human Pose Estimation
• MonoPerfCap: Human Performance Capture from Monocular Video
• ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild
• Heatmap Regression via Randomized Rounding
• A cow structural model for video analytics of cow health
• Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation
• HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale Visual Recognition
• Advanced Millimeter-Wave Radar System for Real-Time Multiple-Human Tracking and Fall Detection
• Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos
• Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video
• Hierarchical binary CNNs for landmark localization with limited resources
• Marvin: an Innovative Omni-Directional Robotic Assistant for Domestic Environments
• Associative Domain Adaptation
• Bi-Directional Cascade Network for Perceptual Edge Detection
• Simple and Lightweight Human Pose Estimation
• Activity-conditioned continuous human pose estimation for performance analysis of athletes using the example of swimming
• Expanded Parts Model for Semantic Description of Humans in Still Images
• Do You Need a Hand? -- a Bimanual Robotic Dressing Assistance Scheme
• The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation
• Enhancing Energy Minimization Framework for Scene Text Recognition with Top-Down Cues
• Variational Information Distillation for Knowledge Transfer
• Part Detector Discovery in Deep Convolutional Neural Networks
• Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression
• FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks
• 6-DoF Object Pose from Semantic Keypoints
• SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation
• Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views
• A Deep Learning Approach for Pose Estimation from Volumetric OCT Data
• RGB-D-based Human Motion Recognition with Deep Learning: A Survey
• Multivariate Time Series Classification using Dilated Convolutional Neural Network
• 3D Human Pose Estimation in the Wild by Adversarial Learning
• Cascade Feature Aggregation for Human Pose Estimation
• Deep Unsupervised Learning of Visual Similarities
• Articulated Clinician Detection Using 3D Pictorial Structures on RGB-D Data
• OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation
• Object Detection in Video with Spatiotemporal Sampling Networks
• Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Images
• Polar Transformer Networks
• DeepOPF: A Deep Neural Network Approach for Security-Constrained DC Optimal Power Flow
• Semantic Object Parsing with Local-Global Long Short-Term Memory
• MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation
• Designing Deep Networks for Surface Normal Estimation
• Improving Auto-Augment via Augmentation-Wise Weight Sharing
• Joint Attention in Driver-Pedestrian Interaction: from Theory to Practice
• Unsupervised decoding of long-term, naturalistic human neural recordings with automated video and audio annotations
• EventAnchor: Reducing Human Interactions in Event Annotation of Racket Sports Videos
• Space-Time Representation of People Based on 3D Skeletal Data: A Review
• Self-Transfer Learning for Fully Weakly Supervised Object Localization
• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
• DeepHash: Getting Regularization, Depth and Fine-Tuning Right
• EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight Transfer
• Viewpoints and Keypoints
• Joint Object and Part Segmentation using Deep Learned Potentials
• Chainer: A Deep Learning Framework for Accelerating the Research Cycle
• Efficient Object Localization Using Convolutional Networks
• Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation
• Monocular Total Capture: Posing Face, Body, and Hands in the Wild
• Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework
• Pose Embeddings: A Deep Architecture for Learning to Match Human Poses
• Estimating 6D Pose From Localizing Designated Surface Keypoints
• Zero-Shot Multi-View Indoor Localization via Graph Location Networks
• Multi-Scale Structure-Aware Network for Human Pose Estimation
• Factors of Transferability for a Generic ConvNet Representation
• Optimal and Robust Category-level Perception: Object Pose and Shape Estimation from 2D and 3D Semantic Keypoints
• Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey
• Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation
• Assigning a Grade: Accurate Measurement of Road Quality Using Satellite Imagery
• Enhancing Human Pose Estimation in Ancient Vase Paintings via Perceptually-grounded Style Transfer Learning
• A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image
• Hypercolumns for Object Segmentation and Fine-grained Localization
• Optimal Pose and Shape Estimation for Category-level 3D Object Perception
• DanceIt: Music-inspired Dancing Video Synthesis
• Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation
• 3D Interpreter Networks for Viewer-Centered Wireframe Modeling
• Brain-mediated Transfer Learning of Convolutional Neural Networks
• Feedback Graph Convolutional Network for Skeleton-based Action Recognition
• HRPVT: High-Resolution Pyramid Vision Transformer for medium and small-scale human pose estimation
• Marvel: A Data-centric Compiler for DNN Operators on Spatial Accelerators
• DeepMark: One-Shot Clothing Detection
• Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint Estimates
• Unveiling the frontiers of deep learning: innovations shaping diverse domains
• MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior
• Removing Backdoor-Based Watermarks in Neural Networks with Limited Data
• Person-in-WiFi: Fine-grained Person Perception using WiFi
• Integral Human Pose Regression
• Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation
• Learning Temporal Pose Estimation from Sparsely-Labeled Videos
• Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision
• First Person Action-Object Detection with EgoNet
• Holistic Planimetric prediction to Local Volumetric prediction for 3D Human Pose Estimation
• Auditing ImageNet: Towards a Model-driven Framework for Annotating Demographic Attributes of Large-Scale Image Datasets
• Pose from Action: Unsupervised Learning of Pose Features based on Motion
• RGB-based 3D Hand Pose Estimation via Privileged Learning with Depth Images
• Understanding Reuse, Performance, and Hardware Cost of DNN Dataflows: A Data-Centric Approach Using MAESTRO
• A Mathematical Analysis of Learning Loss for Active Learning in Regression
• Let's Dance: Learning From Online Dance Videos
• 3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training
• Exploiting Offset-guided Network for Pose Estimation and Tracking
• Towards a Comprehensive Solution for a Vision-based Digitized Neurological Examination
• DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection
• Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization
• Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos
• LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood
• Machine Learning in Biomechanics: Key Applications and Limitations in Walking, Running, and Sports Movements
• FBI-Pose: Towards Bridging the Gap between 2D Images and 3D Human Poses using Forward-or-Backward Information
• Consistent and Flexible Selectivity Estimation for High-Dimensional Data
• Dropout: Explicit Forms and Capacity Control
• DPNNet-2.0 Part I: Finding hidden planets from simulated images of protoplanetary disk gaps
• A Practical Guide to CNNs and Fisher Vectors for Image Instance Retrieval
• AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation
• Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement
• Quantized Densely Connected U-Nets for Efficient Landmark Localization
• Human Pose Estimation in Space and Time using 3D CNN
• Deep Dual Consecutive Network for Human Pose Estimation
• Actions and Attributes from Wholes and Parts
• Multiple Instance Reinforcement Learning for Efficient Weakly-Supervised Detection in Images
• Test-Time Personalization with a Transformer for Human Pose Estimation
• Convolutional Models for Joint Object Categorization and Pose Estimation
• Group Invariant Deep Representations for Image Instance Retrieval
• Recognition and 3D Localization of Pedestrian Actions from Monocular Video
• Dual Path Networks for Multi-Person Human Pose Estimation
• Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation
• Seeing Invisible Poses: Estimating 3D Body Pose from Egocentric Video
• KETO: Learning Keypoint Representations for Tool Manipulation
• Image Quality Assessment Guided Deep Neural Networks Training
• Attribute And-Or Grammar for Joint Parsing of Human Attributes, Part and Pose
• Joint Multi-Person Pose Estimation and Semantic Part Segmentation
• Benchmarking pig detection and tracking under diverse and challenging conditions
• Multi-Stage HRNet: Multiple Stage High-Resolution Network for Human Pose Estimation
• Deep Template Matching for Pedestrian Attribute Recognition with the Auxiliary Supervision of Attribute-wise Keypoints
• Recent Advances in 3D Object and Hand Pose Estimation
• Globally Tuned Cascade Pose Regression via Back Propagation with Application in 2D Face Pose Estimation and Heart Segmentation in 3D CT Images
• Visual Compiler: Synthesizing a Scene-Specific Pedestrian Detector and Pose Estimator
• Learning to Refine Human Pose Estimation
• On Dropout and Nuclear Norm Regularization
• Accelerating Deep Neural Networks with Spatial Bottleneck Modules
• Towards High Performance Human Keypoint Detection
• MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation
• SPCNet:Spatial Preserve and Content-aware Network for Human Pose Estimation
• Cross-Domain Adaptation for Animal Pose Estimation
• Semantic keypoint-based pose estimation from single RGB frames
• From Kinematics To Dynamics: Estimating Center of Pressure and Base of Support from Video Frames of Human Motion
• Learning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition
• Accelerating Large-Kernel Convolution Using Summed-Area Tables
• Learning Compositional Visual Concepts with Mutual Consistency
• Video Contents Understanding using Deep Neural Networks
• Pose Recognition with Cascade Transformers
• Adaloss: Adaptive Loss Function for Landmark Localization
• Dynamic multi-object Gaussian process models: A framework for data-driven functional modelling of human joints
• Real-time Human Pose Estimation from Video with Convolutional Neural Networks
• PoseTrack: Joint Multi-Person Pose Estimation and Tracking
• EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras
• 3D Human Pose Estimation with 2D Marginal Heatmaps
• Learning Fine-grained Features via a CNN Tree for Large-scale Classification
• MetaCloth: Learning Unseen Tasks of Dense Fashion Landmark Detection from a Few Samples
• Pose-Based Two-Stream Relational Networks for Action Recognition in Videos
• ProNet: Learning to Propose Object-specific Boxes for Cascaded Neural Networks
• Structured Feature Learning for Pose Estimation
• A Context-and-Spatial Aware Network for Multi-Person Pose Estimation
• Global Context for Convolutional Pose Machines
• Dynamic Action Recognition: A convolutional neural network model for temporally organized joint location data
• CoKe: Localized Contrastive Learning for Robust Keypoint Detection
• Towards Lifelong Self-Supervision: A Deep Learning Direction for Robotics
• Rotation-invariant Mixed Graphical Model Network for 2D Hand Pose Estimation
• DeepGUM: Learning Deep Robust Regression with a Gaussian-Uniform Mixture Model
• Deep learning-based estimation of whole-body kinematics from multi-view images
• Multiview Supervision By Registration
• Continual Learning from Synthetic Data for a Humanoid Exercise Robot
• Real-time Detection of 2D Tool Landmarks with Synthetic Training Data
• Learning Dynamics from Kinematics: Estimating 2D Foot Pressure Maps from Video Frames
• Deep Metric Learning-Based Semi-Supervised Regression With Alternate Learning
• Can Ground Truth Label Propagation from Video help Semantic Segmentation?
• AMIL: Adversarial Multi Instance Learning for Human Pose Estimation
• On the Robustness of Human Pose Estimation
• Large Area 3D Human Pose Detection Via Stereo Reconstruction in Panoramic Cameras
• 3D Robot Pose Estimation from 2D Images
• TRB: A Novel Triplet Representation for Understanding 2D Human Body
• Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping
• EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation
• DeepOPF: Deep Neural Network for DC Optimal Power Flow
• Anti-Confusing: Region-Aware Network for Human Pose Estimation
• 3D Pose Detection in Videos: Focusing on Occlusion
• Multi-scale Aggregation R-CNN for 2D Multi-person Pose Estimation
• Human Arm Pose Estimation with a Shoulder-worn Force-Myography Device for Human-Robot Interaction
• Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey
• Locating Cephalometric X-Ray Landmarks with Foveated Pyramid Attention
• ACE-Net: Fine-Level Face Alignment through Anchors and Contours Estimation
• A Multi-view RGB-D Approach for Human Pose Estimation in Operating Rooms
• Deep Kinematic Pose Regression
• P-CNN: Pose-based CNN Features for Action Recognition
• Human Pose Estimation from Depth Images via Inference Embedded Multi-task Learning
• Vulnerability Analysis of Chest X-Ray Image Classification Against Adversarial Attacks
• 3D Virtual Garment Modeling from RGB Images
• Fast Human Pose Estimation
• Attaining human-level performance with atlas location autocontext for anatomical landmark detection in 3D CT data
• Analysis of Deep-Learning Methods in an ISO/TS 15066-Compliant Human-Robot Safety Framework
• Dense 3D Regression for Hand Pose Estimation
• Learning to Run with Potential-Based Reward Shaping and Demonstrations from Video Data
• Patch-based 3D Human Pose Refinement
• Efficient Pig Counting in Crowds with Keypoints Tracking and Spatial-aware Temporal Response Filtering
• Single Person Pose Estimation: A Survey
• Unconstrained Fashion Landmark Detection via Hierarchical Recurrent Transformer Networks
• Can Super Resolution be used to improve Human Pose Estimation in Low Resolution Scenarios?
• Post-Data Augmentation to Improve Deep Pose Estimation of Extreme and Wild Motions
• Regression as Classification: Influence of Task Formulation on Neural Network Features
• Generative Models for Pose Transfer
• Robust pose tracking with a joint model of appearance and shape
• StarMap for Category-Agnostic Keypoint and Viewpoint Estimation
• Adversarial Semantic Data Augmentation for Human Pose Estimation
• SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated Data
• Train Your Data Processor: Distribution-Aware and Error-Compensation Coordinate Decoding for Human Pose Estimation
• Benchmarking Shadow Removal for Facial Landmark Detection and Beyond
• Hierarchical Kinematic Human Mesh Recovery
• Sub-pixel face landmarks using heatmaps and a bag of tricks
• Video Based Fall Detection Using Human Poses
• Multi-View Matching (MVM): Facilitating Multi-Person 3D Pose Estimation Learning with Action-Frozen People Video
• Enhanced 3D Human Pose Estimation from Videos by using Attention-Based Neural Network with Dilated Convolutions
• Key Frame Proposal Network for Efficient Pose Estimation in Videos
• Multi-Scale Networks for 3D Human Pose Estimation with Inference Stage Optimization
• Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation
• Improving Temporal Interpolation of Head and Body Pose using Gaussian Process Regression in a Matrix Completion Setting
• Composite Localization for Human Pose Estimation
• Human Pose Forecasting via Deep Markov Models
• Evaluation of Deep Learning based Pose Estimation for Sign Language Recognition
• The Computational Complexity of Understanding Network Decisions
• MPDCompress - Matrix Permutation Decomposition Algorithm for Deep Neural Network Compression
• Chained Predictions Using Convolutional Neural Networks
• Nested Invariance Pooling and RBM Hashing for Image Instance Retrieval
• Bi-directional Graph Structure Information Model for Multi-Person Pose Estimation
• Detangling People: Individuating Multiple Close People and Their Body Parts via Region Assembly
• 3D Human Pose Estimation Based on 2D-3D Consistency with Synchronized Adversarial Training
• Joint Viewpoint and Keypoint Estimation with Real and Synthetic Data
• Real-time Multiple People Hand Localization in 4D Point Clouds
• Lightweight 3D Human Pose Estimation Network Training Using Teacher-Student Learning
• Nonparametric Structure Regularization Machine for 2D Hand Pose Estimation
• Persistent Evidence of Local Image Properties in Generic ConvNets
• Multi-Task Spatiotemporal Neural Networks for Structured Surface Reconstruction
• 3D Human Pose Machines with Self-supervised Learning
• Single upper limb pose estimation method based on improved stacked hourglass network
• Deep High-Resolution Representation Learning for Cross-Resolution Person Re-identification
• Single View Physical Distance Estimation using Human Pose
• Sketch2PoseNet: Efficient and Generalized Sketch to 3D Human Pose Prediction
• TrackID3x3: A Dataset and Algorithm for Multi-Player Tracking with Identification and Pose Estimation in 3x3 Basketball Full-court Videos
• Measurement of Medial Elbow Joint Space using Landmark Detection
• Beyond Pixels: A Comprehensive Survey from Bottom-up to Semantic Image Segmentation and Cosegmentation
• SyDog: A Synthetic Dog Dataset for Improved 2D Pose Estimation
• SpineOne: A One-Stage Detection Framework for Degenerative Discs and Vertebrae
• Skeleton-Graph: Long-Term 3D Motion Prediction From 2D Observations Using Deep Spatio-Temporal Graph CNNs
• Neural Network Based Lidar Gesture Recognition for Realtime Robot Teleoperation
• ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment
• SHD360: A Benchmark Dataset for Salient Human Detection in 360° Videos
• Bayesian Uncertainty and Expected Gradient Length -- Regression: Two Sides Of The Same Coin?
• LCollision: Fast Generation of Collision-Free Human Poses using Learned Non-Penetration Constraints
• Structured Context Enhancement Network for Mouse Pose Estimation
• Boosting Image Super-Resolution Via Fusion of Complementary Information Captured by Multi-Modal Sensors
• EfficientPose: Efficient Human Pose Estimation with Neural Architecture Search
• An Efficient Quantitative Approach for Optimizing Convolutional Neural Networks
• Deep Feedback Inverse Problem Solver
• NFCNN: Toward a Noise Fusion Convolutional Neural Network for Image Denoising
• Computer Vision and Abnormal Patient Gait Assessment a Comparison of Machine Learning Models
• Multi-Person Pose Estimation with Enhanced Feature Aggregation and Selection
• Joint COCO and Mapillary Workshop at ICCV 2019 Keypoint Detection Challenge Track Technical Report: Distribution-Aware Coordinate Representation for Human Pose Estimation
• Zero-shot Adversarial Quantization
• 15 Keypoints Is All You Need
• Learning Transferable Kinematic Dictionary for 3D Human Pose and Shape Reconstruction
• Robust Regression via Deep Negative Correlation Learning
• PAR: Personal Activity Radius Camera View for Contextual Sensing
• A Neural Network for Detailed Human Depth Estimation from a Single Image
• Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization
• Unsupervised Videographic Analysis of Rodent Behaviour
• Human Keypoint Detection by Progressive Context Refinement
• Location-aware Upsampling for Semantic Segmentation
• Deep Pose Consensus Networks
• Calibrated Prediction Intervals for Neural Network Regressors
• Skeleton Transformer Networks: 3D Human Pose and Skinned Mesh from Single RGB Image
• Improved Generalization of Heading Direction Estimation for Aerial Filming Using Semi-supervised Regression
• PAC-GAN: An Effective Pose Augmentation Scheme for Unsupervised Cross-View Person Re-identification
• Recurrent 3D Pose Sequence Machines
• Human Pose Estimation using Global and Local Normalization
• Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation
• Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image
• 3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information
• Automating Image Analysis by Annotating Landmarks with Deep Neural Networks
• Robust Optimization for Deep Regression
• Enhanced Mixtures of Part Model for Human Pose Estimation
• Implicit Label Augmentation on Partially Annotated Clips via Temporally-Adaptive Features Learning
• Dropout Drops Double Descent
• ClothHMR: 3D Mesh Recovery of Humans in Diverse Clothing from Single Image
• A Non-linear Differential CNN-Rendering Module for 3D Data Enhancement
• Using an Ancillary Neural Network to Capture Weekends and Holidays in an Adjoint Neural Network Architecture for Intelligent Building Management
• Human Pose Estimation using Motion Priors and Ensemble Models
• A Mobile Robot Generating Video Summaries of Seniors' Indoor Activities
• Multi-Scale Spatially-Asymmetric Recalibration for Image Classification
• Towards Viewpoint Invariant 3D Human Pose Estimation
• Privacy-preserving classifiers recognize shared mobility behaviours from WiFi network imperfect data
• VolNet: Estimating Human Body Part Volumes from a Single RGB Image
• A Data-driven Approach for Human Pose Tracking Based on Spatio-temporal Pictorial Structure
• MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network
• Bottom-up Pose Estimation of Multiple Person with Bounding Box Constraint
• Multi-Scale Supervised Network for Human Pose Estimation
• Mixture of Parts Revisited: Expressive Part Interactions for Pose Estimation
• Object Parsing in Sequences Using CoordConv Gated Recurrent Networks
• Security Event Recognition for Visual Surveillance
• MirrorNet: A Deep Bayesian Approach to Reflective 2D Pose Estimation from Human Images
• Adversarial Defense via Local Flatness Regularization
• An Adversarial Human Pose Estimation Network Injected with Graph Structure
• Real-time RGBD-based Extended Body Pose Estimation
• Video Analysis of "YouTube Funnies" to Aid the Study of Human Gait and Falls - Preliminary Results and Proof of Concept
• Simple Multi-Resolution Representation Learning for Human Pose Estimation
• Human 3D keypoints via spatial uncertainty modeling
• Self-supervised Deep Learning for Reading Activity Classification
• Deep Convolutional Poses for Human Interaction Recognition in Monocular Videos
• Learning Equivariant Representations
• ActiveNet: A computer-vision based approach to determine lethargy
• Self-Supervision and Spatial-Sequential Attention Based Loss for Multi-Person Pose Estimation
• GAIA: A Transfer Learning System of Object Detection that Fits Your Needs
• Low-resolution Human Pose Estimation
• Classifying In-Place Gestures with End-to-End Point Cloud Learning
• ORCEA: Object Recognition by Continuous Evidence Assimilation
• Detecting and Segmenting Adversarial Graphics Patterns from Images
• Improving Pose Estimation through Contextual Activity Fusion
• Improving 3D Object Detection for Pedestrians with Virtual Multi-View Synthesis Orientation Estimation
• CoopSubNet: Cooperating Subnetwork for Data-Driven Regularization of Deep Networks under Limited Training Budgets
• Semi- and Weakly-supervised Human Pose Estimation
• Unsupervised Construction of Human Body Models Using Principles of Organic Computing
• A Framework for Human Pose Estimation in Videos
• Learning to Estimate Pose by Watching Videos
• Joint Representation of Multiple Geometric Priors via a Shape Decomposition Model for Single Monocular 3D Pose Estimation