Human Pose Estimation with Iterative Error Feedback
Top Cited Papers
- 12 December 2016
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4733-4742
- https://doi.org/10.1109/cvpr.2016.512
Abstract
Hierarchical feature extractors such as Convolutional Networks (ConvNets) have achieved impressive performance on a variety of classification tasks using purely feedforward processing. Feedforward architectures can learn rich representations of the input space but do not explicitly model dependencies in the output spaces, that are quite structured for tasks such as articulated human pose estimation or object segmentation. Here we propose a framework that expands the expressive power of hierarchical feature extractors to encompass both input and output spaces, by introducing top-down feedback. Instead of directly predicting the outputs in one go, we use a self-correcting model that progressively changes an initial solution by feeding back error predictions, in a process we call Iterative Error Feedback (IEF). IEF shows excellent performance on the task of articulated pose estimation in the challenging MPII and LSP benchmarks, matching the state-of-the-art without requiring ground truth scale annotation.Keywords
Other Versions
This publication has 29 references indexed in Scilit:
- DeepPose: Human Pose Estimation via Deep Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Pose Machines: Articulated Pose Estimation via Inference MachinesLecture Notes in Computer Science, 2014
- Strong Appearance and Expressive Spatial Models for Human Pose EstimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Loose-limbed People: Estimating 3D Human Pose and Motion Using Non-parametric Belief PropagationInternational Journal of Computer Vision, 2011
- Brain States: Top-Down Influences in Sensory ProcessingNeuron, 2007
- Support vector machine learning for interdependent and structured output spacesPublished by Association for Computing Machinery (ACM) ,2004
- Fast pose estimation with parameter-sensitive hashingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Cortical feedback improves discrimination between figure and background by V1, V2 and V3 neuronsNature, 1998
- Distributed Hierarchical Processing in the Primate Cerebral CortexCerebral Cortex, 1991
- Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in positionBiological Cybernetics, 1980