作者:
Grauman, K.Betke, M.Lombardi, J.Gips, J.Bradski, G.R.Vision Interface Group
AI Laboratory Massachusetts Institute of Technology 77 Massachusetts Avenue CambridgeMA02139 United States Computer Science Department
Boston University 111 Cummington St BostonMA02215 United States EagleEyes
Computer Science Department Boston College Fulton Hall Chestnut HillMA02467 United States Vision
Graphics and Pattern Recognition Microcomputer Research Laboratory Intel Corporation SC12-303 2200 Mission College Blvd Santa ClaraCA95054-1537 United States
Two video-based human-computer interaction tools are introduced that can activate a binary switch and issue a selection command. "BlinkLink," as the first tool is called, automatically detects a user's e...
详细信息
Images and videos taken in foggy weather often suffer from low visibility. Recent studies demonstrate the effectiveness of dark channel prior [3] and guided filter [4] based approaches for image dehazing. However, the...
详细信息
ISBN:
(纸本)9781479982479
Images and videos taken in foggy weather often suffer from low visibility. Recent studies demonstrate the effectiveness of dark channel prior [3] and guided filter [4] based approaches for image dehazing. However, these methods require high computational cost which makes them infeasible for realtime and embedding systems. In this paper, we propose Edge-Guided Interpolated Filter (EGIF) for fast image and video dehazing. The main contributions are twofold. Firstly, we develop Guided Interpolated Filter (GIF) to significantly speed up the estimation of transmission map, which is the most computational cost step in previous methods. Secondly, we utilize edge map as guidance image in GIF to enhance the fine details in dehazed images. Experimental results show that GIF can largely improve the computational efficiency and achieve comparable dehazing performance as previous guided filter based methods. EGIF can further enhance the sharpness of transmission map. Our method can achieve real-time processing for image of size 1024 × 768 with single CPU core (2GHz).
Existing cross-modal hashing still faces three challenges: (1) Most batch-based methods are unsuitable for processing large-scale and streaming data. (2) Current online methods often suffer from insufficient semantic ...
详细信息
In order to help understand how the genes are affected by different disease conditions in a biological system, clustering is typically performed to analyze gene expression data. In this paper, we propose to solve the ...
详细信息
In order to help understand how the genes are affected by different disease conditions in a biological system, clustering is typically performed to analyze gene expression data. In this paper, we propose to solve the clustering problem using a graph theoretical approach, and apply a novel graph partitioning model -isoperimetric graph partitioning (IGP), to group biological samples from gene expression data. The IGP algorithm has several advantages compared to the well-established spectral graph partitioning (SGP) model. First, IGP requires a simple solution to a sparse system of linear equations instead of the eigen-problem in the SGP model. Second, IGP avoids degenerate cases produced by spectral approach to achieve a partition with higher accuracy. Moreover, we integrate unsupervised gene selection into the proposed approach through two-way ordering of gene expression data, such that we can eliminate irrelevant or redundant genes in the data and obtain an improved clustering result. We evaluate our approach on several well-known problems involving gene expression profiles of colon cancer and leukemia subtypes. Our experiment results demonstrate that IGP constantly outperforms SGP and produces a better result that is closer to the original labeling of sample sets provided by domain experts. Furthermore, the clustering accuracy is improved significantly when IGP is integrated with the unsupervised gene (feature) selection.
Retinal images have been increasingly important in clinical diagnostics of several eye and systemic diseases. To help the medical doctors in this work, automatic and semi-automatic diagnosis methods can be used to inc...
详细信息
Few-shot font generation (FFG), aiming at generating font images with a few samples, is an emerging topic in recent years due to the academic and commercial values. Typically, the FFG approaches follow the style-conte...
Few-shot font generation (FFG), aiming at generating font images with a few samples, is an emerging topic in recent years due to the academic and commercial values. Typically, the FFG approaches follow the style-content disentanglement paradigm, which transfers the target font styles to characters by combining the content representations of source characters and the style codes of reference samples. Most existing methods attempt to increase font generation ability via exploring powerful style representations, which may be a sub-optimal solution for the FFG task due to the lack of modeling spatial transformation in transferring font styles. In this paper, we model font generation as a continuous transformation process from the source character image to the target font image via the creation and dissipation of font pixels, and embed the corresponding transformations into a neural transformation field. With the estimated transformation path, the neural transformation field generates a set of intermediate transformation results via the sampling process, and a font rendering formula is developed to accumulate them into the target font image. Extensive experiments show that our method achieves state-of-the-art performance on few-shot font generation task, which demonstrates the effectiveness of our proposed model. Our implementation is available at: https://***/fubinfb/NTF.
This paper presents a novel approach to compute DCT-I, DCT-III, and DCT-IV. By using a modular mapping and truncating, DCTs are approximated by linear sums of discrete moments computed fast only through additions. Thi...
详细信息
Metal artifacts in computed tomography (CT) arise from a mismatch between physics of image formation and idealized assumptions during tomographic reconstruction. These artifacts are particularly strong around metal im...
详细信息
Decision trees represent a simple and powerful method of induction from labeled examples. Univariate decision trees consider the value of a single attribute at each node, leading to the splits that are parallel to the...
详细信息
Decision trees represent a simple and powerful method of induction from labeled examples. Univariate decision trees consider the value of a single attribute at each node, leading to the splits that are parallel to the axes. In linear multivariate decision trees, all the attributes are used and the partition at each node is based on a linear discriminate (a hyperplane). Nonlinear multivariate decision trees are able to divide the input space arbitrarily based on higher order parameterizations of the discriminate, though one should be aware of the increase of the complexity and the decrease in the number of examples available as moves further down the tree. In omnivariate decision trees, the decision node may be univariate, linear, or nonlinear. Such architecture frees the designer from choosing the appropriate tree type for a given problem. In this paper, we propose to do the model selection at each decision node based on a novel classifiability measure when building omnivariate decision trees. The classifiability measure captures the possible sources of misclassification with relative ease and is able to accurately reflect the complexity of subproblems at each node. The proposed approach does not require the time consuming statistic tests at each node and therefore does not suffer from as high computational burden as typical model selection algorithm. Our simulation results over several data sets indicate that our approach can achieve at least as good classification accuracy as statistical tests based model select algorithms, but in much faster speed.
It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-dimensional videos, due to large local redundancy and complex global dependency between video frames. The recent advances in th...
详细信息
暂无评论