Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for jointly training an image embedding model and a text embedding model. In one aspect, a method comprises: processing data from a historical query log of a search system to generate a candidate set of training examples, wherein each training example comprises: (i) a search query comprising a sequence of one or more words, (ii) an image, and (iii) selection data characterizing how often users selected the image in response to the image being identified by a search result for the search query; selecting a plurality of training examples from the candidate set of training examples; and using the training data to jointly train the image embedding model and the text embedding model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an image embedding model. In one aspect, a method comprises: obtaining training data comprising a plurality of training examples, wherein each training example comprises: an image pair comprising a first image and a second image; and selection data indicating one or more of: (i) a co-click rate of the image pair, and (ii) a similar-image click rate of the image pair; and using the training data to train an image embedding model having a plurality of image embedding model parameters.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an image embedding model. In one aspect, a method comprises: obtaining training data comprising a plurality of training examples, wherein each training example comprises: an image pair comprising a first image and a second image; and selection data indicating one or more of: (i) a co-click rate of the image pair, and (ii) a similar-image click rate of the image pair; and using the training data to train an image embedding model having a plurality of image embedding model parameters.

Abstract: A media application determines, based on pixels of images or videos from a collection of media items, clusters of media items such that the media items in each cluster have a visual similarity, wherein the collection of media items is associated with a user account. The media application selects a subset of the clusters of media from corresponding clusters of media items based on the media items in each cluster having a visual similarity within a range of threshold similarity values. The media application causes a user interface to be displayed that includes the subset of the clusters of media.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for jointly training an image embedding model and a text embedding model. In one aspect, a method comprises: processing data from a historical query log of a search system to generate a candidate set of training examples, wherein each training example comprises: (i) a search query comprising a sequence of one or more words, (ii) an image, and (iii) selection data characterizing how often users selected the image in response to the image being identified by a search result for the search query; selecting a plurality of training examples from the candidate set of training examples; and using the training data to jointly train the image embedding model and the text embedding model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an image embedding model. In one aspect, a method comprises: obtaining training data comprising a plurality of training examples, wherein each training example comprises: an image pair comprising a first image and a second image; and selection data indicating one or more of: (i) a co-click rate of the image pair, and (ii) a similar-image click rate of the image pair; and using the training data to train an image embedding model having a plurality of image embedding model parameters.

Abstract: A method for promoting semiconductor manufacturing yield comprising the following steps and a computer readable medium encoded with a computer program implementing the method is provided. First, a processed layer is inspected to generate an inspected image with defects thereon. Next, the inspected image is aligned to an original design layout information of the processed layer. In addition, the defects are classified according to geometric features of the original design layout information of the processed layer and at least previous one layer and/or at least next one layer.

Abstract: A method for filtering noises in an image scanned by charged particles includes steps of grouping pixels with similar types in the image into a plurality of pixel groups; and removing noises for each pixel group in the image according to a corresponding noise model to obtain the scanned image with better quality and/or contrast. A system for filtering noises in an image scanned by charged particles is also disclosed.