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: Embodiments of the present disclosure provide a display method and apparatus based on augmented reality, a device, and a storage medium, the method includes receiving a first video; acquiring a video material by segmenting a target object from the first video; acquiring and displaying a real scene image, where the real scene image is acquired by an image collection apparatus; and displaying the video material at a target position of the real scene image in an augmented manner and playing the video material. Since the video material is acquired by receiving the first video and segmenting the target object from the first video, the video material may be set according to the needs of the user.

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: Systems and methods for managing a presentation of a dynamic profile photo are provided. In particular, a server may receive contextual information associated with one or more users. The server may determine that the contextual information is consistent with a predetermined contextual action. In some examples, the server may identify a dynamic profile photo associated with the predetermined contextual information; and present, in response to the determination that the contextual information is consistent with the predetermined contextual action, the dynamic profile photo to the one or more users.

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: Systems and methods for generating a video including a plurality of graphic objects provided in a shared environment is described. The method includes acquiring, at a first computing device, a shared session identifier from a shared session manager, the shared session identifier being associated with a first user identifier, receiving a selection of a second user identifier, causing the shared session identifier and the first user identifier to be provided to a second computing device associated with the second user identifier, receiving as input, a first graphic object for rendering to a display associated with the first computing device, the first graphic object being associated with the first user identifier, receiving from a data synchronizer, a second graphic object associated with the second user identifier and the shared session identifier for rendering to the display associated with the second computing device, and generating a video including graphic objects.

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 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.