Abstract: An optical character recognition (OCR) system disclosed herein may include three major parts: Training Data Generator, Training Module and main OCR module. The Training Data Generator may include an arbitrarily large library of fonts, a set of variable font parameters, such as font size and style (e.g., bold, italic, etc.), and position in the synthesis image. Additionally, an end-to-end training pipeline allows the OCR algorithm to be highly customizable and scalable to different scenarios. Furthermore, the OCR system can be effectively trained without any real-world training data.

Abstract: In some embodiments, a method maps attributes of metadata for a plurality of content instances to metadata nodes. The metadata nodes are connected to type nodes that define a type of metadata for each metadata node and a respective content node for a respective content instance. The method generates a plurality of sample paths using the content nodes, the metadata nodes, and the type nodes from the mapping of attributes of the metadata. A similarity of content nodes is analyzed using the plurality of sample paths. Then, the method generates a representation of each of the plurality of content instances using the similarity of the content nodes. The representation represents the similarity between content instances in the plurality of content instances.

Abstract: In some embodiments, a first detector generates a first output based on a first probability that an image was inserted in a video. The first detector is trained with a set of known images to detect the set of known images. A second detector generates a second output based on a second probability that an image was inserted in the video. The second detector is used to detect the set of unknown images without training. The method analyzes the first output from the first detector based on the probability of the image existing in the video and the second output from the second detector based on the probability of the image existing in the video to generate a combined score from the first output and the second output. An indication of whether the image is detected in the video is output based on the combined score.

Abstract: In some embodiments, a method detects a first set of frames in a video that include lines of text, the detecting performed at a frame level on each individual frame. A first representation is generated from the first set of frames and a second representation is generated from the first set of frames. The method filters the first representation based on a number of lines of text within a space in the space dimension to select a second set of frames and filters the second representation based on a number of frames within time intervals in the time dimension to select a third set of frames. Frames in both the second set of frames and the third set of frames are analyzed to determine whether the lines of text in both the second set of frames and the third set of frames are burned-in subtitles.

Abstract: In some embodiments, a method detects a first set of frames in a video that include lines of text, the detecting performed at a frame level on each individual frame. A first representation is generated from the first set of frames and a second representation is generated from the first set of frames. The method filters the first representation based on a number of lines of text within a space in the space dimension to select a second set of frames and filters the second representation based on a number of frames within time intervals in the time dimension to select a third set of frames. Frames in both the second set of frames and the third set of frames are analyzed to determine whether the lines of text in both the second set of frames and the third set of frames are burned-in subtitles.

Abstract: In some embodiments, a method trains a first prediction network to predict similarity between images in videos. The training uses boundaries detected in the videos to train the prediction network to predict images in a same scene to have similar feature descriptors. The first prediction network generates feature descriptors that describe library images from videos in a video library offered to users of a video delivery service. A search image is received and the prediction network predicts one or more library images for one or more videos that are predicted to be similar to the received image. The one or more library images for the one or more videos are provided as a search result.

Abstract: In one embodiment, a system detects objects in an image and generates attention regions that are positioned in the image based on first positions of the objects in the image. Focus points for the objects are generated for the attention regions at one or more second positions. Focus boxes are generated using the second positions of the focus points. Then, the system generates information for a motion effect using content of the image based on a number of the focus boxes and third positions of the focus boxes.

Abstract: In some embodiments, a method trains a first prediction network to predict similarity between images in videos. The training uses boundaries detected in the videos to train the prediction network to predict images in a same scene to have similar feature descriptors. The first prediction network generates feature descriptors that describe library images from videos in a video library offered to users of a video delivery service. A search image is received and the prediction network predicts one or more library images for one or more videos that are predicted to be similar to the received image. The one or more library images for the one or more videos are provided as a search result.

Abstract: In one embodiment, a method receives a set of frames from a video at a first classifier. The first classifier classifies the set of frames with classification scores that indicate a confidence that a frame contains end credit content using the first classifier using a first model that classifies content from the set of frames. A second classifier then refines the classification scores from neighboring frames in the set of frames using a second classifier using a second model that classifies classification scores from the first classifier. A boundary point is selected between a frame in the set of frames considered not including end credit content and a frame in the set of frames including end credit content based on the refined classification scores.

Abstract: In one embodiment, a system detects objects in an image and generates attention regions that are positioned in the image based on first positions of the objects in the image. Focus points for the objects are generated for the attention regions at one or more second positions. Focus boxes are generated using the second positions of the focus points. Then, the system generates information for a motion effect using content of the image based on a number of the focus boxes and third positions of the focus boxes.

Abstract: One embodiment provides a device, including a processor; a plurality of storage units operatively coupled to the processor; and a memory device that stores instructions executable by the processor to: determine a first storage unit from the plurality of storage units; select at least one second storage unit from among the remaining other storage units that comprises a parameter that satisfies a predetermined condition, the predetermined condition being related to the first storage unit; transfer data from at least one of the first and second storage units to at least one the remaining other first and second storage units; and delete data from said at least one of the first and second storage units from which the data was transferred. Other aspects are described and claimed.

Abstract: An apparatus, method and computer program product are caused at least to perform: controlling a touch sensitive display to display a first graphical item at a first position and a second graphical item at a second position, the second graphical item being separated from the first graphical item by a first distance; detecting a first user digit at the first position and a second user digit at the second position; reducing the first distance by moving at least one of the first and second graphical items across the touch sensitive display, in response to detecting movement, across the touch sensitive display, of at least one of the first and second user digits; and controlling the touch sensitive display to display a third graphical item, after determining the first distance has been reduced such that the first graphical item is proximate the second graphical item.

Abstract: An apparatus, a method, a computer program and a graphical user interface is provided.

Abstract: An operation processing method and an operation processing device applied in an electronic apparatus include a display unit in which a first interactive interface having a first size is displayed. The method includes displaying a second interactive interface having a second size which is different from the first size and having a mapping relation with the first interactive interface in the display unit, detecting a first action executed by the user in the second interactive interface; and executing a first operation in the first interactive interface according to the first action. Thus, the first interactive interface can be mapped into the second interactive interface and the first operation that the user expects to execute in the first interactive interface can be implemented by the first action executed in the second interactive interface, so that the user can conveniently operate the electronic apparatus.

Abstract: One embodiment provides a device, including a processor; a plurality of storage units operatively coupled to the processor; and a memory device that stores instructions executable by the processor to: determine a first storage unit from the plurality of storage units; select at least one second storage unit from among the remaining other storage units that comprises a parameter that satisfies a predetermined condition, the predetermined condition being related to the first storage unit; transfer data from at least one of the first and second storage units to at least one the remaining other first and second storage units; and delete data from said at least one of the first and second storage units from which the data was transferred. Other aspects are described and claimed.

Abstract: A storage device and an information processing method are provided. The storage device has a first power supply unit and at least one first storage cell. The at least one first storage cell stores first data which are associated with a number of charges within the first storage cell. The first power supply unit is electrically connected to the at least one first storage cell. The storage device further has a first control unit configured for controlling the first power supply unit to supply power to the at least one first storage cell according to a predetermined policy, so that the number of charges within the first storage cell satisfies a first preset condition.

Abstract: A storage device and an information processing method are provided. The storage device has a first power supply unit and at least one first storage cell. The at least one first storage cell stores first data which are associated with a number of charges within the first storage cell. The first power supply unit is electrically connected to the at least one first storage cell. The storage device further has a first control unit configured for controlling the first power supply unit to supply power to the at least one first storage cell according to a predetermined policy, so that the number of charges within the first storage cell satisfies a first preset condition.

Abstract: Apparatus, a method and a computer program are provided.

Abstract: Apparatus, a method and a computer program are provided.

Abstract: An example apparatus is caused to receive a video sequence of a plurality of frames, and perform a number of operations as each of at least some of the frames is received but before all of the frames are received. The apparatus is caused to calculate a score for the frame, and compare the score for the frame to a predefined threshold. The apparatus is caused to cause output of the frame as a key frame in an instance in which the frame is received within a specified period of time and the score for the frame is above the predefined threshold. Otherwise, in an instance in which none of the scores for frames received within the specified period of time is above the predefined threshold, the apparatus is caused to cause output of one of the frames received within the specified period of time as a key frame.