Emre Dogan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Emre Dogan has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
Atilla Baskurt
Université de Lyon, CNRS Villeurbanne France
2 shared publicationsChristian Wolf
Université de Lyon, CNRS Villeurbanne France
2 shared publicationsEric Lombardi
Université de Lyon, CNRS Villeurbanne France
2 shared publicationsGonen Eren
Department of Computer Engineering Galatasaray University 36 Ciragan Cd Istanbul 34349 Turkey
2 shared publications
Latest Publications
- Open Access
- 21 December 2017
- Published by Institution of Engineering and Technology (IET) in IET Computer Vision
- Vol. 12 (4) , 403-411
Multi‐view pose estimation with mixtures of parts and adaptive viewpoint selection
We propose a new method for human pose estimation which leverages information from multiple views to impose a strong prior on articulated pose. The novelty of the method concerns the types of coherence modelled. Consistency is maximised over the different views through different terms modelling classical geometric information (coherence of the resulting poses) as well as appearance information which is modelled as latent variables in the global energy function. Moreover, adequacy of each view is assessed and their contributions are adjusted accordingly. Experiments on the HumanEva and Utrecht multi‐person motion datasets show that the proposed method significantly decreases the estimation error compared to single‐view results.
- 21 December 2017
- Published by Institution of Engineering and Technology (IET) in IET Computer Vision
- Vol. 12 (4) , 403-411
Open AccessMulti‐view pose estimation with mixtures of parts and adaptive viewpoint selection
We propose a new method for human pose estimation which leverages information from multiple views to impose a strong prior on articulated pose. The novelty of the method concerns the types of coherence modelled. Consistency is maximised over the different views through different terms modelling classical geometric information (coherence of the resulting poses) as well as appearance information which is modelled as latent variables in the global energy function. Moreover, adequacy of each view is assessed and their contributions are adjusted accordingly. Experiments on the HumanEva and Utrecht multi‐person motion datasets show that the proposed method significantly decreases the estimation error compared to single‐view results.
- Open Access
Multi-view pose estimation with mixtures-of-parts and adaptive viewpoint selection
We propose a new method for human pose estimation which leverages information from multiple views to impose a strong prior on articulated pose. The novelty of the method concerns the types of coherence modelled. Consistency is maximised over the different views through different terms modelling classical geometric information (coherence of the resulting poses) as well as appearance information which is modelled as latent variables in the global energy function. Moreover, adequacy of each view is assessed and their contributions are adjusted accordingly. Experiments on the HumanEva and UMPM datasets show that the proposed method significantly decreases the estimation error compared to single-view results.
Open AccessMulti-view pose estimation with mixtures-of-parts and adaptive viewpoint selection
We propose a new method for human pose estimation which leverages information from multiple views to impose a strong prior on articulated pose. The novelty of the method concerns the types of coherence modelled. Consistency is maximised over the different views through different terms modelling classical geometric information (coherence of the resulting poses) as well as appearance information which is modelled as latent variables in the global energy function. Moreover, adequacy of each view is assessed and their contributions are adjusted accordingly. Experiments on the HumanEva and UMPM datasets show that the proposed method significantly decreases the estimation error compared to single-view results.