Conference abstract · 2018
Conference abstractPublished 15 Aug 2016
Opening the black box: Hierarchical sampling optimization for estimating human hand pose
Imperial College London, UK
Abstract
Select any words in the title or abstract, or press this and choose a sentence.
We address the problem of hand pose estimation, formulated as an inverse problem. Typical approaches optimize an energy function over pose parameters using a âÂ?Â?black boxâÂ?Â? image generation procedure. This procedure knows little about either the relationships between the parameters or the form of the energy function. In this talk, we show that we can significantly improve upon black box optimization by exploiting high-level knowledge of the parameter structure and using a local surrogate energy function. Our new framework, hierarchical sampling optimization, consists of a sequence of predictors organized into a kinematic hierarchy. Each predictor is conditioned on its ancestors, and generates a set of samples over a subset of the pose parameters. The highly-efficient surrogate energy is used to select among samples. Having evaluated the full hierarchy, the partial pose samples are concatenated to generate a full-pose hypothesis. Several hypotheses are generated using the same procedure, and finally the original full energy function selects the best result. Experimental evaluation on three publically available datasets shows that our method is particularly impressive in low-compute scenarios where it significantly outperforms all other state-of-the-art methods.
Subjects
Computer Science & ITEngineeringAsk about this article
Answers come only from this article's title, abstract and keywords, each sentence pointing to where it comes from. Your question is sent to OpenAI to write the answer. Scholars Central does not store it.
Similar by topic
Conference abstract · 2017
Viewpoint class based camera pose estimation and object recognition
Conference abstract · 16 Nov 2015
Parameter estimation in a hierarchical random intercept model with censored response: An approach using a SEM algorithm and Gibbs sampling
Conference abstract · 1 Dec 2016
Computer Graphics 2016: Scanned human body model realistic pose deformation - Shuaiyin Zhu - Hong Kong
Conference abstract · 7 Nov 2016
Scanned human body model realistic pose deformation
More from this journal
The newest in Journal of Information Technology & Software Engineering.
Research article · 16 Apr 2025
Smart Livestock Health and GPS Tracking Solution Powered by IoE Technology
Commentary · 19 Mar 2025
DevOps Integration for Continuous Delivery and Deployment
Opinion · 19 Mar 2025
Machine Learning Algorithms for Software Quality Improvement
Conferences in this field
Upcoming conferences in this field.
Follow
New articles from what you follow go into your email digest, once you agree to alert emails.
- JournalJournal of Information Technology & Software Engineering
- SubjectComputer Science & IT
- SubjectEngineering
- BylineArticles whose byline prints “Tae-Kyun Kim”

