On account of having real-time behavior and being easy to implement, spring meshes have been used for modeling deformable objects. Determining spring stiffness parameters for simulation of soft objects with high accur...
详细信息
With the explosive growth of Web and the recent development in digital media technology, the number of images on the Web has grown tremendously. Consequently, Web image clustering has emerged as an important applicati...
详细信息
ISBN:
(纸本)9781605580852
With the explosive growth of Web and the recent development in digital media technology, the number of images on the Web has grown tremendously. Consequently, Web image clustering has emerged as an important application. Some of the initial efforts along this direction revolved around clustering Web images based on the visual features of images or textual features by making use of the text surrounding the images. However, not much work has been done in using multimodal information for clustering Web images. In this paper, we propose a graph theoretical framework for simultaneously integrating visual and textual features for efficient Web image clustering. Specifically, we model visual features, images and words from surrounding text using a tripartite graph. Partitioning this graph leads to clustering of the Web images. Although, graph partitioning approach has been adopted before, the main contribution of this work lies in a new algorithm that we propose - Consistent Isoperimetric High-order Co-clustering (CIHC), for partitioning the tripartite graph. Computationally, CIHC is very quick as it requires a simple solution to a sparse system of linear equations. Our theoretical analysis and extensive experiments performed on real Web images demonstrate the performance of CIHC in terms of the quality, efficiency and scalability in partitioning the visual feature-image-word tripartite graph.
Stereo correspondence research often involves the comparison of techniques to determine which are better under different circumstances. The methods of comparison employed often take the form of applying the techniques...
详细信息
Stereo correspondence research often involves the comparison of techniques to determine which are better under different circumstances. The methods of comparison employed often take the form of applying the techniques to a few stereo image pairs with the technique with the lowest error rate declared superior. However, the majority of these comparisons do not contain any discussion of statistical significance;making the declared superiority of a technique statistically unreliable. In this paper we present a new evaluation method called cluster ranking that yields a statistically significant comparison of the stereo techniques being compared. Cluster ranking leverages statistical inference techniques to first rank the performance of stereo techniques on a single stereo image pair and then combine the rankings from multiple stereo pairs into an over-all ranking;in both of these rankings, only stereo techniques that are statistically different are given different ranks. We demonstrate our framework with a comparison of constructable match cost measures (those that can be assembled from a base set of components) on a data set consisting of 30 synthetic stereo pairs, with varying amounts of noise, and 18 scenes from the 2005 and 2006 Middlebury data sets. Our analysis reveals match cost measures, and measure components, that are statistically superior to all other measures depending on amount of noise, illumination, or exposure time.
Historically, the ACM Multimedia Conference is split into a "technical" program and an "arts" program. These programs sometimes seem completely separate from one another, victims of a "semanti...
详细信息
ISBN:
(纸本)9781605583037
Historically, the ACM Multimedia Conference is split into a "technical" program and an "arts" program. These programs sometimes seem completely separate from one another, victims of a "semantic gap" between disciplines. The goal of this panel is to create a space in which scientists learn from artists, and arts from science. We need to discover new connections between modalities of research. In order to create the most exciting and powerful future forms of interactive multimedia systems, the ones that will create the most beneficial broader impact on humanity, we need to foster new collaborations between artists and scientists. This panel seeks to bridge the great divide of language and communities that has fragmented us, creating a new space for developing connections between the arts and sciences of multimedia research, as embodied through the artists and scientists of ACM Multimedia. The goal is to make this conference a premier site for catalyzing emergent connections. Among the ancient Greeks, the techne, which included the sciences, were based in the arts. Our modes of knowledge production have since separated and grown alienated. "What weird stuff are those people doing?" To bridge the divide, we must understand and acknowledge differences, and use this as a basis for discovering common ground. In the sciences, knowledge is constructed empirically, through hypotheses and validations. Aesthetics and concepts play essential roles in how works of art are formulated to stimulate experiences. Where do these aims intersect and how might they inform each other? In this conference, one track develops pattern recognition methods for content analysis and retrieval. Another develops network and system techniques. Applications invoke these methods in usable systems. Human-centered multimedia serves as a bridge connecting human experiences with algorithmic methods. The interactive art program develops new concepts of how multimedia can function culturally, amidst society,
There are many algorithms in non-photorealistic rendering for representing an image as a composition of small objects. In this paper, we focus on the specific case where the objects to be assembled into a composition ...
详细信息
ISBN:
(纸本)1568813376
There are many algorithms in non-photorealistic rendering for representing an image as a composition of small objects. In this paper, we focus on the specific case where the objects to be assembled into a composition are letters rather than images or abstract geometric forms. We develop a solution to the "calligraphic packing" problem based on dividing up a target region into pieces and warping a letter into each piece. We define an energy function that chooses a warp that best represents the original letter. We discuss variations in rendering style and show results produced by our system.
We present a novel rendering algorithm that analyses the ray profiles along the line of sight. The profiles are subdivided according to encountered peaks and valleys at so called transition points. The sensitivity of ...
详细信息
ISBN:
(纸本)1568813376
We present a novel rendering algorithm that analyses the ray profiles along the line of sight. The profiles are subdivided according to encountered peaks and valleys at so called transition points. The sensitivity of these transition points is calibrated via two thresholds. The slope threshold is based on the magnitude of a peak following a valley, while the peeling threshold measures the depth of the transition point relative to the neighboring rays. This technique separates the dataset into a number of feature layers. The user can scroll through the layers inspecting various features from the current view position. While our technique has been inspired by opacity peeling approach, we demonstrate that we can reveal detectable features even in the third and forth layers for both CT and MRI datasets.
Web image clustering has drawn significant attention in the research community recently. However, not much work has been done in using multi-modal information for clustering Web images. In this paper, we address the p...
详细信息
ISBN:
(纸本)9781595937025
Web image clustering has drawn significant attention in the research community recently. However, not much work has been done in using multi-modal information for clustering Web images. In this paper, we address the problem of Web image clustering by simultaneous integration of visual and textual features from a graph partitioning perspective. In particular, we modelled visual features, images, and words from the surrounding text of the images using a tripartite graph. This graph is actually considered as a fusion of two bipartite graphs that are partitioned simultaneously by the proposed Consistent Isoperimetric High-order Co-clustering(CIHC) framework. Although a similar approach has been adopted before, the main contribution of this work lies in the computational efficiency, quality in Web image clustering and scalability to large image repositories that CIHC is able to achieve. We demonstrate this through experimental results performed on real Web images. Copyright 2007 ACM.
作者：
Kerdels, JochenPeters, GabrieleDFKI
German Research Center for Artificial Intelligence Robotics Lab. Robert Hooke Str. 5 D-28359 Bremen Germany University of Dortmund
Department of Computer Science Computer Graphics Otto-Hahn-Str. 16 D-44221 Dortmund Germany
In the field of computer vision feature matching in high dimensional feature spaces is a commonly used technique for object recognition. One major problem is to find an adequate similarity measure for the particular f...
详细信息
Modern image processing techniques increasingly use prior models of the expected distribution of objects. Principal component eigen-models are often selected for shape prior modeling, but are limited in capturing only...
详细信息
Modern image processing techniques increasingly use prior models of the expected distribution of objects. Principal component eigen-models are often selected for shape prior modeling, but are limited in capturing only the second order moment statistics. On the other hand, kernel densities can in concept reproduce arbitrary statistics, but are problematic for high dimensional data such as shapes. An evident approach is to combine these methods, using PCA to reduce the problem dimensionality, followed by kernel density modeling of the PCA coefficients. In this paper we show that useful algorithmic and editing operations can be formulated in term of this simple approach. The operations are illustrated in the context of point distribution shape models. Particular points can be rapidly evaluated as being plausible or outliers, and a plausible shape can be completed given limited operator input in a manually guided procedure. This "PCA+KD" approach is conceptually simple, scalable (becoming increasingly accurate with additional training data), provides improved modeling power, and supports useful algorithmic queries.
This paper presents an interactive technique for the dense texture-based visualization of unsteady 3D flow, taking into account issues of computational efficiency and visual perception. High efficiency is achieved by ...
详细信息
暂无评论