|
Feature: Invited Talk Abstracts |
|
Pursuit of Low-dimensional Structures in High-dimensional Data
Yi Ma (China)
Abstract: In this talk, we will discuss a new class of models and techniques that can effectively model and extract rich low-dimensional structures in high-dimensional data such as images and videos, despite nonlinear transformation, gross corruption, or severely compressed measurements. This work leverages recent advancements in convex optimization for recovering low-rank or sparse signals that provide both strong theoretical guarantees and efficient and scalable algorithms for solving such high-dimensional combinatorial problems. These results and tools actually generalize to a large family of low-complexity structures whose associated (convex) regularizers are decomposable. We illustrate how these new mathematical models and tools could bring disruptive changes to solutions to many challenging tasks in computer vision, image processing, and pattern recognition. We will also illustrate some emerging applications of these tools to other data types such as web documents, image tags, microarray data, audio/music analysis, and graphical models. This is joint work with John Wright of Columbia, Emmanuel Candes of Stanford, Zhouchen Lin of Peking University, and my students Zhengdong Zhang, Xiao Liang of Tsinghua University, Arvind Ganesh, Zihan Zhou, Kerui Min and Hossein Mobahi of UIUC. |
|
Interest Points Detectors and Descriptors in Image Recognition
Krystian Mikolajczyk (UK)
Abstract: Much research in computer vision and pattern recognition is focused on developing new approaches for popular bags of visual words models such as interest point detectors, descriptors, spatio-temporal representations, codebook and coding schemes as well as classifiers. In this talk, I will present our recent projects on image and video recognition where interest points and local descriptors play a crucial role. I will present our recent approaches to extract and represent spatio-temporal characteristics of local features, in particular, their appearance-motion history captured from a moving camera. I will also discuss the machine learning techniques we apply to improve discriminative capabilities of local descriptors or fuse information from various feature channels to maximize recognition performance. These, as well as the process of designing the recognition approach to meet the application requirements will be discussed in the context of several applications including object detection from UAVs, sport recognition, mood classification and animal identification. |
|
Patient and Process Specific Imaging and Visualization for Computer Assisted Interventions
Nassir Navab (Germany)
Abstract: In this talk, I first focus on the needs for development of novel techniques for patient and process specific intra-operative imaging and visualization and present some of our latest results as exemplary cases. As novel intra-operative and multi-modality imaging techniques provide the surgical crew with rich co-registered information, their appropriate visualization and their integration into surgical workflow, their validation and finally their full deployment are becoming active subjects of research in our community. Pattern recognition, computer vision and machine learning techniques are further developed to help recovering and modeling surgical procedures and providing innovative solutions. I will in particular trace the Freehand SPECT and Camera Augmented Mobile C-arm (CAMC) from the early development of research ideas within our multi-disciplinary research laboratories to their deployment in different surgical suites. I will finally show how the 'real world laboratories' at our university hospitals demonstrate their efficiency through the smooth path they pave for bringing advance imaging and visualization techniques into the surgical theatres. |
|
Three Approaches of Scene Text Recognition: An informal comparison on difficult images
Jin Hyung Kim (Korea)
Abstract: Three KAIST approaches for scene text recognition will be presented in this talk: color-based, edge-based, and part-based approaches. Although features of color, edge and part-relationship are utilized in all of the three approaches, there are differences on the main focus in each of these approaches. The color-based approach focuses on image segmentation mainly based on color, while the edge-based approach focuses on edge following to extract text objects. The part-based approach is an attempt to directly pin point existence of character parts in image. Each of the three approaches has merits and demerits. The text extraction results of the three approaches will be shown on some representative images known 'difficult' in the community. So, one may feel how the approaches will behave in other difficult images. |
