Learn More
Co-saliency is used to discover the common saliency on the multiple images, which is a relatively underexplored area. In this paper, we introduce a new cluster-based algorithm for co-saliency detection. Global correspondence between the multiple images is implicitly learned during the clustering process. Three visual attention cues: contrast, spatial, and(More)
ER-to-Golgi transport in yeast may be reproduced in vitro with washed membranes, purified proteins (COPII, Uso1p and LMA1) and energy. COPII coated vesicles that have budded from the ER are freely diffusible but then dock to Golgi membranes upon the addition of Uso1p. LMA1 and Sec18p are required for vesicle fusion after Uso1p function. Here, we report that(More)
Co-saliency detection aims at discovering the common salient objects existing in multiple images. Most existing methods combine multiple saliency cues based on fixed weights, and ignore the intrinsic relationship of these cues. In this paper, we provide a general saliency map fusion framework, which exploits the relationship of multiple saliency cues and(More)
The performance of existing image dehazing methods is limited by hand-designed features, such as the dark channel, color disparity and maximum contrast, with complex fusion schemes. In this paper, we propose a multi-scale deep neural network for single-image dehazing by learning the mapping between hazy images and their corresponding transmission maps. The(More)
Traffic through the yeast Golgi complex depends on a member of the syntaxin family of SNARE proteins, Sed5p, present in early Golgi cisternae. Sft2p is a non-essential tetra-spanning membrane protein, found mostly in the late Golgi, that can suppress some sed5 alleles. We screened for mutations that show synthetic lethality with sft2 and found one that(More)
Soluble NSF attachment protein receptor (SNARE) proteins are essential for membrane fusion in transport between the yeast ER and Golgi compartments. Subcellular fractionation experiments demonstrate that the ER/Golgi SNAREs Bos1p, Sec22p, Bet1p, Sed5p, and the Rab protein, Ypt1p, are distributed similarly but localize primarily with Golgi membranes. All of(More)
When one records a video/image sequence through a transparent medium (e.g. glass), the image is often a superposition of a transmitted layer (scene behind the medium) and a reflected layer. Recovering the two layers from such images seems to be a highly ill-posed problem since the number of unknowns to recover is twice as many as the given measurements. In(More)
Foreground detection plays a core role in a wide spectrum of applications such as tracking and behavior analysis. It, especially for videos captured by fixed cameras, can be posed as a component decomposition problem, the background of which is typically assumed to lie in a low dimensional subspace. However, in real world cases, dynamic backgrounds like(More)
In this paper, we introduce a novel Flip INvariant Descriptor (FIND). FIND improves the degenerated performance resulted from image flips and reduces both space and time costs. Flip invariance of FIND enables the intractable flip detection to be achieved easily, instead of duplicately implementing the procedure. To alleviate the pressure brought by the(More)
Human vision system understands the environment from 3D perception. However, most existing saliency detection algorithms detect the salient foreground based on 2D image information. In this paper, we propose a saliency detection method using the additional depth information. In our method, saliency cues are provided to follow the laws of the visually(More)