Abstract: A method is provided for receiving a selection of a key frame in a video and including the key frame within a first plurality of frames from the video. The method includes adjusting at least one weighting factor for a value entry in the first plurality of frames to obtain a second plurality of frames having at least one reduced dimensionality and obtaining a one-dimensional representation of the first plurality of frames with a plurality of weighted entry values from the second plurality of frames. Further, the method includes correlating two entry values in the one-dimensional representation to obtain a selector, storing the at least one weighting factor as a network entry in a process network when the selector picks the key frame from the first plurality of frames, and applying the process network to a third plurality of frames in the video to form a summary of the video.

Abstract: A method for receiving an input user query from a user in any of multiple languages and creating an input user query vector for the input user query is provided. The input user query vector has a length equal to a pre-selected length determined by a dimension of a multimodal space. The method includes associating an image vector to the input user query vector in the multimodal space, the image vector having the pre-selected length, identifying, from an image database, an image associated with the image vector, and providing the image for display to the user in a results panel of a user interface. A system configured to perform the above method is also provided.

Abstract: Methods and systems for virtual on-set communication are provided. In one aspect, a method includes receiving, from a device of a first user, an input indicating that the first user is ready to start working on a project associated with the first user. The method also includes identifying, based on the project associated with the first user, a second set of users associated with the project. The method also includes generating a session identifier for a communication channel between the first user and one or more users of the second set of users. The method also includes generating messages for the communication channel, wherein the messages include a link to the communication channel. The method also includes transmitting the messages to the one or more users of the second set of users.

Abstract: A method for receiving a first text in a source language is provided. The method includes associating the first text in the source language with a first vector, selected from a plurality of vectors associated with the source language in an embedded set, and identifying a second vector that is closer to the first vector than a pre-selected threshold. The second vector is associated with a second text in a target language. The method includes associating the first text in the source language with the second text in the target language, wherein the embedded set includes a first image vector for a first image and a second image vector for a second image, and returning the second text in the target language, the second text being a translation of the first text from the source language to the target language. A system configured to perform the above method is also provided.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for identification of a salient portion of an image. A system may receive user input identifying a search query for content from a client device. The system may determine a listing of images responsive to the search query from an image collection. The system may obtain one or more image crops for at least one image of the listing of images based on a saliency map of the at least one image. In one or more implementations, each of the one or more image crops indicates a salient region of a corresponding image. The system may provide a set of search results responsive to the search query to the client device. In one or more implementations, the set of search results includes the obtained one or more image crops in a prioritized listing of image crops.

Abstract: A method and system for ranking images in response to a user presenting search criteria on a user interface of a computing device, comprising (1) searching a first database to locate a set of pertinent images satisfying the search criteria, (2) extracting a set of suggested color palettes from the set of images, (3) processing each color palette from the set of suggested color palettes by iteratively performing the following operations: (a) identifying a next color palette, (b) identifying a set of images from which the next color palette is extracted from, (c)) determine a set of parameters of a first set of operations, and (d) ascertaining an image rank measure for each image from the set of images by performing the first set of operations, and (4) generating a ranked display of the set of images based on the image rank measure.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for edit distance based spellcheck. A system may include a search engine using edit distance based spellcheck covering a set of valid words in a language model describing probabilities for each candidate word. The subject system first identifies strings that are one edit away from a source word, selects at least one of the strings with the highest probability in the language model and uses that selected string as the spelling correction. If there are no valid words found, the subject system determines the edit distance between the source word and all candidate words in the language model whose length differential with the source word is smaller than a threshold and whose first character is the same as that of the source word, and selects the candidate word with the highest language probability and lowest edit distance.

Abstract: A method and system for conducting image search comprising: searching a first database to locate a set of pertinent images, iteratively performing the following operations for each image in the set of pertinent images: (a) extracting the histogram of red green and blue colors (RGB colors) from a given image; (b) distilling the extracted RGB colors down to create a reduced color palette for the given image; (c) segmenting the extracted RGB colors into a set of segments representing distinct parts of the color spectrum; (d) selecting a subset of segments to assemble a color palette for the given image; and (e) updating the assembled color palette and the customer behavior score for the given image in the first database; and generating a display of suggested color palettes for the search query.

Abstract: Methods for suggesting an audio file for playback with a video file using an analysis of objects in images from the video file are provided. In one aspect, a method includes receiving a selection of a video file, identifying shot transition timings in the video file, and analyzing each shot transition associated with the identified shot transition to a identify an entity within the respective shot transition. The method also includes providing an identification of the identified entities to a natural language model to identify at least one mood associated with the identified entities, selecting, from a collection of audio files, at least one audio file associated with the at least one mood and including an average audio onset distance within an audio onset distance threshold, and providing an identification of the at least one audio file as a suggestion for audio playback with the video file. Systems and machine-readable media are also provided.

Abstract: A method and system for conducting image search is provided that includes searching a first database to locate a set of pertinent images, iteratively performing the following operations for each image in the set of pertinent images (a) extracting the histogram of red green and blue colors (RGB colors) from a given image (b) distilling the extracted RGB colors down to create a reduced color palette for the given image (c) segmenting the extracted RGB colors into a set of segments representing distinct parts of the color spectrum; (d) selecting a subset of segments to assemble a color palette for the given image; (e) updating the assembled color palette and the customer behavior score for the given image in the first database; and generating a ranked display of suggested color palettes for the search query by aggregating the customer behavior scores for the search query across all images.

Abstract: A computer-implemented method is provided for retrieving an image from a user in a desired format and for detecting a compression efficiency for the image. When the compression efficiency is above a pre-selected threshold the computer-implemented method includes obtaining a saliency representation of the image, capturing a feature description of a non-salient portion of the image, flattening the non-salient portion in a new image, storing the new image in a selected format in a memory and storing a background descriptor for the image in the memory.

Abstract: Methods for identifying visual portions of visual media files that are responsive to at least one visual media input file submitted as a search query are provided. In one aspect, a method includes generating an index of visual portions of a plurality of visual media files from a collection of media files, and receiving from a user a search query, for the collection, including at least one visual media input file. The method also includes analyzing the index to identify at least one responsive visual media file from the collection that includes a visual portion associated with a visual similarity score, to the at least one visual media input file, which exceeds a similarity threshold value, and providing, in response to the search query, an identifier of the at least one responsive visual media file for display as responsive to the search query. Systems and machine-readable media are also provided.

Abstract: A method and system for displaying a dynamic mosaic of media files, the method comprising: receiving media files, determining a fill direction, constructing a layout, determining an edge set from the media files previously placed on the layout, determining a trailing edge, and adjacent edges, constructing a set of closed rectangles an open rectangle from the trailing edge and adjacent edges, providing a first set of frames by iteratively attempting to fill up to one closed rectangle from the set of closed rectangles, providing a second set of frames by filling the open rectangle by placing one searched media file in the open rectangle if no closed rectangle in the set of closed rectangles can be filled, and inserting one of the first set of frames and the second set of frames into a current layout before updating a current edge set based on the inserted frames.

Abstract: Methods for prioritizing a set of images identified as responsive to an image search query from a user based on features of the images identified as relevant to a geographic region of the user are provided. In one aspect, the method includes submitting a plurality of images to a computer-operated convolutional neural network that is configured to analyze image pixel data for each of the plurality of images to identify features, in each of the plurality of images, influencing a download probability of the corresponding image in a plurality of geographic regions. The method also includes receiving, from the neural network and for each of the plurality of images, a download probability of each image for each of the plurality of geographic regions. Systems and machine-readable media are also provided.

Abstract: A method for dynamically displaying results of simultaneous two dimensional image search comprises: maintaining a first database comprising a set of records, each record comprising an image and an associated set of annotations describing the image, receiving an annotation criterion and a color scheme from a user, generating a target color scoring template from the color scheme, conducting a content based search by searching the first database to identify a set of pertinent images satisfying the annotation criterion, and performing the following operations for each image in the set of pertinent images: resizing a given image to a predefined size before generating an image color spectrum histogram for the given image, adding the given image to a pool of acceptable images if the generated image color spectrum histogram matches with the target color scoring template; and dynamically displaying images in the pool of acceptable images to the user.

Abstract: A method and system for conducting image search comprising: searching a first database to locate a set of pertinent images, iteratively performing the following operations for each image in the set of pertinent images: (a) extracting the histogram of red green and blue colors (RGB colors) from a given image; (b) distilling the extracted RGB colors down to create a reduced color palette for the given image; (c) segmenting the extracted RGB colors into a set of segments representing distinct parts of the color spectrum; (d) selecting a subset of segments to assemble a color palette for the given image; and (e) updating the assembled color palette and the customer behavior score for the given image in the first database; and generating a display of suggested color palettes for the search query.

Abstract: A method for dynamically displaying results of simultaneous two dimensional image search comprises: maintaining a first database comprising a set of records, each record comprising an image and an associated set of annotations describing the image, receiving an annotation criterion and a color scheme from a user, generating a target color scoring template from the color scheme, conducting a content based search by searching the first database to identify a set of pertinent images satisfying the annotation criterion, and performing the following operations for each image in the set of pertinent images: resizing a given image to a predefined size before generating an image color spectrum histogram for the given image, adding the given image to a pool of acceptable images if the generated image color spectrum histogram matches with the target color scoring template; and dynamically displaying images in the pool of acceptable images to the user.

Abstract: Computer image clustering systems and methods for conducting effective media searches by grouping multimedia documents tagged by keywords into a hierarchy of images configured to: (1) maintain a first database, (2) maintain an initial occurrence matrix, (3) maintain an occurrence matrix, (4) maintain a media file activation score for each media file in the first database, (5) generate a log version of the occurrence matrix, (6) maintain an inverse media file frequency value for each descriptive term in the first database, (7) generate a descriptive term frequency matrix and generate a list of document vectors in multidimensional space (list), and (8) organize and process each media file in the list into a high activation score category and a low activation score category.

Abstract: Methods for prioritizing a set of images identified as responsive to an image search query from a user based on features of the images identified as relevant to a geographic region of the user are provided. In one aspect, the method includes submitting a plurality of images to a computer-operated convolutional neural network that is configured to analyze image pixel data for each of the plurality of images to identify features, in each of the plurality of images, influencing a download probability of the corresponding image in a plurality of geographic regions. The method also includes receiving, from the neural network and for each of the plurality of images, a download probability of each image for each of the plurality of geographic regions. Systems and machine-readable media are also provided.

Abstract: A context based tag recommendation system for annotating stock photography media files, the system configured to: maintain a first database comprising a set of media files and a set of annotations associated with the media file set, maintain a second database comprising a second set of records, each record comprising an annotation, at least one co-occurring annotation, and a count, receive at least one media file tag input (input), query the second database using the input to identify a ranked set of co-occurring annotations and a count associated with each annotation in the ranked set of co-occurring annotations, query the first database to identify a selected set of similar media files, by iteratively retrieving image files associated a selective group of annotations from the ranked set of co-occurring annotations, present a list of recommended annotations based on the ranked set of co-occurring annotations and the selected set of similar media files.