Charles R. Dyer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Charles R. Dyer has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Brandon M. Smith
University of Wisconsin-Madison
1 shared publication - Guodong Guo
Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China
1 shared publication - Kiriakos N. Kutulakos
University of Wisconsin-Madison
1 shared publication - Lopamudra Mukherjee
University of Calcutta
1 shared publication - Raman Arora
University of Washington
1 shared publication - Thomas S. Huang
Beckman Institute, UIUC, Urbana, IL 61801
1 shared publication
Latest Publications
- Open Access
Efficient Branching Cascaded Regression for Face Alignment under Significant Head Rotation
Despite much interest in face alignment in recent years, the large majority of work has focused on near-frontal faces. Algorithms typically break down on profile faces, or are too slow for real-time applications. In this work we propose an efficient approach to face alignment that can handle 180 degrees of head rotation in a unified way (e.g., without resorting to view-based models) using 2D training data. The foundation of our approach is cascaded shape regression (CSR), which has emerged recently as the leading strategy. We propose a generalization of conventional CSRs that we call branching cascaded regression (BCR). Conventional CSRs are single-track; that is, they progress from one cascade level to the next in a straight line, with each regressor attempting to fit the entire dataset. We instead split the regression problem into two or more simpler ones after each cascade level. Intuitively, each regressor can then operate on a simpler objective function (i.e., with fewer conflicting gradient directions). Within the BCR framework, we model and infer pose-related landmark visibility and face shape simultaneously using Structured Point Distribution Models (SPDMs). We propose to learn task-specific feature mapping functions that are adaptive to landmark visibility, and that use SPDM parameters as regression targets instead of 2D landmark coordinates. Additionally, we introduce a new in-the-wild dataset of profile faces to validate our approach.
Open AccessEfficient Branching Cascaded Regression for Face Alignment under Significant Head Rotation
Despite much interest in face alignment in recent years, the large majority of work has focused on near-frontal faces. Algorithms typically break down on profile faces, or are too slow for real-time applications. In this work we propose an efficient approach to face alignment that can handle 180 degrees of head rotation in a unified way (e.g., without resorting to view-based models) using 2D training data. The foundation of our approach is cascaded shape regression (CSR), which has emerged recently as the leading strategy. We propose a generalization of conventional CSRs that we call branching cascaded regression (BCR). Conventional CSRs are single-track; that is, they progress from one cascade level to the next in a straight line, with each regressor attempting to fit the entire dataset. We instead split the regression problem into two or more simpler ones after each cascade level. Intuitively, each regressor can then operate on a simpler objective function (i.e., with fewer conflicting gradient directions). Within the BCR framework, we model and infer pose-related landmark visibility and face shape simultaneously using Structured Point Distribution Models (SPDMs). We propose to learn task-specific feature mapping functions that are adaptive to landmark visibility, and that use SPDM parameters as regression targets instead of 2D landmark coordinates. Additionally, we introduce a new in-the-wild dataset of profile faces to validate our approach.
- 1 January 2011
- Published by Springer Nature
- p. 41-54
Projective Joint Invariants for Matching Curves in Camera Networks
- 1 January 2011
- Published by Springer Nature
- p. 41-54
Projective Joint Invariants for Matching Curves in Camera Networks
- 1 January 2009
- p. 2028-2035
Half-Integrality based Algorithms for Cosegmentation of Images
We study the cosegmentation problem where the objective is to segment the same object (i.e., region) from a pair of images. The segmentation for each image can be cast using a partitioning/segmentation function with an additional constraint that seeks to make the histograms of the segmented regions (based on intensity and texture features) similar. Using Markov Random Field (MRF) energy terms for the simultaneous segmentation of the images together with histogram consistency requirements using the squared L2 (rather than L1) distance, after linearization and adjustments, yields an optimization model with some interesting combinatorial properties. We discuss these properties which are closely related to certain relaxation strategies recently introduced in computer vision. Finally, we show experimental results of the proposed approach.
- 1 January 2009
- p. 2028-2035
Half-Integrality based Algorithms for Cosegmentation of Images
We study the cosegmentation problem where the objective is to segment the same object (i.e., region) from a pair of images. The segmentation for each image can be cast using a partitioning/segmentation function with an additional constraint that seeks to make the histograms of the segmented regions (based on intensity and texture features) similar. Using Markov Random Field (MRF) energy terms for the simultaneous segmentation of the images together with histogram consistency requirements using the squared L2 (rather than L1) distance, after linearization and adjustments, yields an optimization model with some interesting combinatorial properties. We discuss these properties which are closely related to certain relaxation strategies recently introduced in computer vision. Finally, we show experimental results of the proposed approach.
- 1 January 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505790,p. 1-6
Locally Adjusted Robust Regression for Human Age Estimation
Automatic human age estimation has considerable potential applications in human computer interaction and multimedia communication. However, the age estimation problem is challenging. We design a locally adjusted robust regressor (LARR) for learning and prediction of human ages. The novel approach reduces the age estimation errors significantly over all previous methods. Experiments on two aging databases show the success of the proposed method for human aging estimation.
- 1 January 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505790,p. 1-6
Locally Adjusted Robust Regression for Human Age Estimation
Automatic human age estimation has considerable potential applications in human computer interaction and multimedia communication. However, the age estimation problem is challenging. We design a locally adjusted robust regressor (LARR) for learning and prediction of human ages. The novel approach reduces the age estimation errors significantly over all previous methods. Experiments on two aging databases show the success of the proposed method for human aging estimation.
- 31 October 1995
- Published by Elsevier in Artificial Intelligence
- Vol. 78 (1-2) , 147-177
Global surface reconstruction by purposive control of observer motion
- 31 October 1995
- Published by Elsevier in Artificial Intelligence
- Vol. 78 (1-2) , 147-177
Global surface reconstruction by purposive control of observer motion
- 1 April 1994
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 12 (2-3) , 113-136
Recovering shape by purposive viewpoint adjustment
- 1 April 1994
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 12 (2-3) , 113-136
Recovering shape by purposive viewpoint adjustment