Abstract: A method includes obtaining image frames that comprise a video, each of the image frames having a first aspect ratio, and selecting at least one of the image frames as a condition frame. The method further includes generating, from each condition frame based on an image outpainting model, an outpainted condition frame that has a second aspect ratio different from the first aspect ratio. The method further includes generating, from at least one of remaining image frames based on a video outpainting model and the outpainted condition frames, an outpainted target frame that has the second aspect ratio, each outpainted target frame having spatial consistency with the image frame from which it was generated and temporal consistency with neighboring outpainted frames in the video.

Abstract: A method includes adding an outpaint mask to an image to generate a masked image. The method also includes processing the image using an encoder neural network to generate an image representation of the image in a latent space. The method further includes processing the masked image using a convolution neural network and adding the image representation to generate an image embedding. The method also includes processing the image representation and the image embedding using at least one of a diffusion model and an interpolation process to generate a noisy latent image representation. The method further includes using a large language model to contextualize an outpainting prompt. The method also includes denoising the noisy latent image representation based on the contextualized outpainting prompt to generate a denoised latent image representation. In addition, the method includes processing the denoised latent image representation using a decoder neural network to generate an outpainted image.

Abstract: A method includes obtaining, using at least one processing device of an electronic device, a video including multiple scenes at a first aspect ratio. The method also includes performing, using the at least one processing device, backward optical flow estimation and forward optical flow estimation for each of the multiple scenes to select an image frame having a largest missing area. The method further includes performing, using the at least one processing device, outpainting on the image frame having the largest missing area to generate a first outpainted image frame at a second aspect ratio different from the first aspect ratio. In addition, the method includes performing, using the at least one processing device, backward optical flow estimation and forward optical flow estimation using the first outpainted image frame to generate additional outpainted image frames in the multiple scenes at the second aspect ratio.

Abstract: A method includes providing a Fibonacci confidence interval level on user program viewership data to distinguish user interest level in different linear entertainment programs. The method also includes creating a behavior shift feature space for acquiring information about user behavior over time based on a behavior sequence, a first derivative on the behavior sequence, and a second derivative on the behavior sequence. The method further includes utilizing, based on a trained machine learning model, a transformer structure and attention to map user data from the behavior shift feature space into a prediction of the Fibonacci confidence interval level.

Abstract: A method includes providing a Fibonacci confidence interval level on user program viewership data to distinguish user interest level in different linear entertainment programs. The method also includes creating a behavior shift feature space for acquiring information about user behavior over time based on a behavior sequence, a first derivative on the behavior sequence, and a second derivative on the behavior sequence. The method further includes utilizing, based on a trained machine learning model, a transformer structure and attention to map user data from the behavior shift feature space into a prediction of the Fibonacci confidence interval level.

Abstract: A method includes obtaining, based on a sequential graph-based model, gaming exposure information over time, where the gaming exposure information includes device-level preferences and household-level preferences. The method also includes combining one or more raw user behavior sessions into a gameplay session based on the obtained gaming exposure information. The method further includes providing a scoring metric to (i) check an extent of multi-matching in the obtained gaming exposure information and (ii) remove untrustworthy gaming exposures from the obtained gaming exposure information. In addition, the method includes generating, based on a feature engineering pipeline, one or more game segments running in a production environment, where the one or more game segments are identified for ancillary content based on inferences by a machine learning model trained using the gaming exposure information.

Abstract: In one embodiment, a method includes receiving user behavior data and contextual information associated with the user behavior data, the contextual information including a first data portion associated with a first context type. The method includes generating, from the user behavior data and the contextual information using a hashing algorithm, a first heterogeneous hash code including a first portion representing the user behavior data and a second hash code portion representing the first data portion associated with the first context type. The method includes accessing a second heterogeneous hash code including a third hash code portion representing a second data portion associated with the first context type. The method includes comparing the first heterogeneous hash code with the second heterogeneous hash code including determining similarity between the second hash code portion of the first heterogeneous hash code and the third hash code portion of the second heterogenous hash code.

Abstract: A method includes obtaining (i) device data associated with multiple electronic devices and (ii) advertisement data associated with one or more advertisement campaigns. The method also includes identifying first features and second features, where the first features correspond to the device data and the second features correspond to the advertisement data. The method further includes generating a graph relating usage history of the multiple electronic devices and one or more advertisement genres. The method also includes identifying a specified electronic device from among the multiple electronic devices and an advertisement segment from among the one or more advertisement campaigns using the first features, the second features, and the graph. In addition, the method includes providing the advertisement segment to the specified electronic device.

Abstract: In one embodiment, a computer-implemented method includes acquiring sequential user behavior data including one-dimensional data. The user behavior data is associated with a user. The method includes abstracting features from the sequential user behavior data to cover short-term and long-term timeframes. The method includes determining one or more properties of the user based on the features.

Abstract: An electronic device includes at least one processor configured to obtain user data associated with a plurality of devices from multiple data sources. The at least one processor is also configured to determine a static weight for each of the plurality of devices based on at least one source of the multiple data sources. The at least one processor is further configured to identify a portion of the plurality of devices that represents the plurality of devices based on the static weight and a dynamic weight. In addition, the at least one processor is configured to determine the dynamic weight for each of the portion of the plurality of devices while the portion of the plurality of devices is identified, where the dynamic weight is based on one or more sources of the multiple data sources.

Abstract: In one embodiment, a computer-implemented method includes acquiring sequential user behavior data including one-dimensional data. The user behavior data is associated with a user. The method includes abstracting features from the sequential user behavior data to cover short-term and long-term timeframes. The method includes determining one or more properties of the user based on the features.

Abstract: In one embodiment, a method includes receiving user behavior data and contextual information associated with the user behavior data, the contextual information including a first data portion associated with a first context type. The method includes generating, from the user behavior data and the contextual information using a hashing algorithm, a first heterogeneous hash code including a first portion representing the user behavior data and a second hash code portion representing the first data portion associated with the first context type. The method includes accessing a second heterogeneous hash code including a third hash code portion representing a second data portion associated with the first context type. The method includes comparing the first heterogeneous hash code with the second heterogeneous hash code including determining similarity between the second hash code portion of the first heterogeneous hash code and the third hash code portion of the second heterogenous hash code.

Abstract: A data transmission method for a MIMO (Multiple-input Multiple-Output) system allowing multiple terminals to share channelization codes according to the channel states, by receiving channel information from terminals, allocating channelization codes for each transmit antenna based upon the received channel information, and transmitting data via each transmit antenna according to the allocated channelization codes. When there are many user terminals and if the number of channelization codes are limited, namely, when the total number of channel codes used to distinguish the terminals is less than the total number of terminals, channelization code sharing per transmit antenna among multiple terminals is performed, such that the throughput of data that can be sent by using each channelization code is increased.