Lemon Patente

There are provided methods, devices, and computer program products for video generation. A first video is converted into a second video to change the appearance of the first video. The first video comprises a first object that performs an action and the second video comprises the same object that performs the same action. A video generating model is determined based on the first and second videos. Specifically, A first feature is determined for the first video and a second feature is determined for the second video by the video generating model. A first motion portion in the first feature is determined for the first video based on a temporal change in the first video; the second feature is updated by aligning a second motion portion in the second feature with the first motion portion; the diffusion model is updated based on the first feature and the updated second feature.

There are provided methods, devices, and computer program products for image generation, particularly to debiasing text-to-image diffusion models. In a method, a plurality of images is obtained by an image generating model based on a prompt. The plurality of images comprises a plurality of instances of an object, respectively and the object is specified by the prompt. A plurality of attributes of the plurality of instances of the object are determined respectively. The image generating model is updated based on the plurality of attributes and a predetermined distribution of a plurality of predetermined attributes related to the object. With the above method, the images generated by the updated image generating model may follow the predetermined distribution, and the updated image generating model may output debiased results.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for synthetic data generation for service recommendation models. One of the methods includes generating a plurality of synthetic data items, each synthetic data item including user data, context data, service data of a service, and user action data characterizing one or more user actions with respect to the service; for each synthetic data item of the plurality of synthetic data items, processing the synthetic data item using an evaluator to generate a score indicating quality of the synthetic data item; selecting a subset of synthetic data items from the plurality of synthetic data items; and providing the subset of synthetic data items into a service recommendation model for recommending one or more services to one or more users based on the subset of synthetic data items.

Implementations for performing workload-aware space reclamation are provided. One example includes a computing system comprising: processing circuitry and memory storing instructions that, during execution, causes the processing circuitry to: track extent usage characteristics for each of a plurality of extents storing data for a graph database; and perform memory reclamation to reclaim storage areas corresponding to invalid data, wherein performing the memory reclamation comprises: generating a list of extents to be reclaimed based on the tracked extent usage characteristics; and reclaiming memory space on the plurality of extents in order based on the list of extents.

Implementations for I/O efficient synchronization on a graph database (102) are provided. One example includes a computing system (100) comprising: processing circuitry (104) and memory (106) storing instructions that, during execution, causes the processing circuitry to: implement the graph database (102) using at least: a read-write node (110) and a read-only node (112) operating in cache memory; and a shared storage (114) for data persistence, wherein the shared storage (114) stores a mapping table (202) of the graph database (102); receive an update query; update the read-write node (110) based on the update query; write, using the read-write node (110), a set of logs corresponding to the update query to a write-ahead log journal in the shared storage; and retrieve, using the read-only node (102), the set of logs from the write-ahead log journal.

Implementations for a space-optimized graph database system are provided. One implementation includes a computing system comprising: processing circuitry and memory storing instructions that causes the processing circuitry to: store a graph database comprising an initial tree graph storing a plurality of data entries, each data entry comprising a respective field identifier; receive a query to update the graph database, wherein the query comprises a request to add a new data entry; determine a splitting event to perform based on one or more predetermined criteria; generate a new tree graph corresponding to a field identifier of the new data entry by splitting off a subset of the plurality of data entries of the initial tree graph, wherein the subset comprises all data entries of the initial tree graph that correspond to the field identifier of the new data entry; and update the new tree graph in accordance with the query.

Described herein is an implementation of a classification of content collection using process supervision with a chain-of-thought reasoning capable machine-learned (ML) model. In an example aspect, a process supervision system includes processing circuitry and memory storing a content source of a ML model. The content source includes text-labeled content of a first type. The processing circuitry is configured to obtain a collection of multiple first-typed content items of the content source. The collection has text metadata associated therewith. The processing circuitry is further configured to produce supervised fine-tuning (SFT) queries regarding the collection based, at least in part, on one or more of the first-typed content items of the collection and/or the text metadata of the collection. The processing circuitry is still further configured to, based on the SFT queries, assemble a chain-of-thought reasoning request for submission to a chain-of-thought reasoning capable ML classifier.

Embodiments of the present disclosure provide a method and an apparatus for protecting data in an electronic device, an electronic device, and a program product. The method (200) includes: receiving (202) first data from a first application by a security service, where the security service blocks the first application from accessing a second application to protect data. The method further includes: receiving (204) second data from the second application by the security service. In addition, the method further includes: determining (206) third data for the electronic device by the security service based on the first data and the second data.

An optical system and a near-eye display apparatus are provided. The optical system includes: a lens structure; and a beam splitting film, a reflective polarizing film and a phase retardation film disposed on the lens structure, the reflective polarizing film and the phase retardation film being located at a same side of the beam splitting film, image light transmitted through the beam splitting film being configured to be reflected between the beam splitting film and the reflective polarizing film and exit from the reflective polarizing film, and the lens structure including at least one lens. The optical system further includes a light filtering structure located at a side of the reflective polarizing film that is away from the beam splitting film, the light filtering structure is configured such that, among light rays incident from the side away from the reflective polarizing film, an average transmittance of light rays having an incidence angle greater than 50 degrees is a first transmittance, an average transmittance of light rays having an incidence angle less than 30 degrees is a second transmittance, and a ratio of the first transmittance to the second transmittance is less than 1/3. By arranging the light filtering structure having different transmittances for light rays with different incidence angles, it's conductive to reduce the interference of ambient light.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining whether to generate sub-domain noise. One of the methods includes, for a message for a downstream system, determining whether to generate noise data that has the same sub-domain as a true value, the true value from a domain that has a plurality of different sub-domains including the sub-domain; using a result of the determination whether to generate noise data that has the same sub-domain as the true value, generating the message for the downstream system; and transmitting, to the downstream system, the message.

The present disclosure involves methods, apparatus, and systems for processing comparison in secure multiparty computation. One example method includes, partitioning a first difference (x) between a first share of value a and a first share of value b into N sections, and determining whether a<b based on first indicators and second indicators corresponding to the N sections. The first indicators include a first indicator indicating a comparison result between xj and yj computed based on a Vector Oblivious Shift Evaluation (VOSE) protocol, where xj is a j<th> section of x, and yj is a j<th> section of N sections of a second difference (y) between a second secret share of b and a second secret share of a. The second indicators include a second indicator indicating whether xj is a most significant section among sections of the first difference where xj ≠ yj.

A video classification system receives an input video comprising video frames and video audio, generates visual tokens based on the video frames, generates audio embeddings based on the video audio, and inputs the visual tokens into a multi-modal language model to generate contextually informed answers. The contextually informed answers and the audio embeddings are concatenated to generate concatenated tokens, which are inputted into a fully connected layer to generate a vector of class probabilities. Then a video label for the input video is generated and outputted based on the vector of class probabilities.

Implementations for adaptive foveated image sensors are provided. One implementation includes an image sensor system for adaptive foveated processing, the image sensor system comprising: an image sensor (102) for generating (902)a set of signals by imaging an environment; and processing circuitry (104) configured to: receive (904) foveated region of interest (ROI) information and ambient light information; determine (906) a processing mode based on the ambient light information; compress (908) the set of signals from the image sensor based on the determined processing mode and the foveated ROI information to generate a compressed set of pixels; and output (912) the compressed set of pixels.

A method of processing media data. The method includes determining, for a conversion between the media data and a media data file, that a preselection element includes an indicator, wherein the indicator indicates that a purpose of the preselection element is for providing a picture-in-picture experience where a supplementary video appears to be overlaid on a target picture-in-picture region in a main video; and performing a conversion between the media data and the media data file based on the indicator. A corresponding video coding apparatus and non-transitory computer-readable recording medium are also disclosed.

The present disclosure provides an image processing method, a non-transitory storage medium, and an electronic device. The image processing method includes: obtaining a frame group to be processed in a target video; and processing the frame group to be processed by a saliency prediction model to obtain a detection result of the target video frame. The saliency prediction model includes a feature encoder and a feature decoder. The processing the frame group to be processed by a saliency prediction model includes: inputting the frame group to be processed into the feature encoder to perform feature extraction, and outputting multi-layer feature data corresponding to the frame group to be processed; and inputting the multi-layer feature data into the feature decoder to perform feature fusion in a temporal dimension and feature fusion in a spatial dimension, and outputting a detection result of the target video frames.

Zusammenfassung wird geladen …

The present disclosure involves methods, apparatus, and systems for processing equality testing in secure multi-party computation (MPC). In one aspect, a method includes, generating, by a first party of the secure MPC, a difference between a secret share of a first value and a secret share of a second value. During a first iteration, the difference is partitioned into N sections each including M bits. For each section, a random bit is generated, a group of 2<M> bits are generated based on the random bit, and a selected bit from the group of 2<M> bits is sent to a second party of the secure MPC based on oblivious transfer (OT) protocol. The random bits of the N sections are concatenated as an input of a second iteration. The method further includes determining whether the first value equals the second value based on performing a plurality of iterations.

The present disclosure involves methods, apparatus, and systems for processing equality testing in secure multi-party computation (MPC). In one aspect, a method includes, generating, by a first party of the secure MPC, a difference between a secret share of a first value and a secret share of a second value. During a first iteration, the difference is partitioned into N sections each including M bits. For each section, a random integer is generated, a group of 2<M> integers are generated based on the random integer, and a selected interger from the group of 2<M> integers is sent to a second party of the secure MPC based on oblivious transfer protocol. The random integers of the N sections are added as an input of a second iteration. The method further includes determining whether the first value equals the second value based on results of a plurality of iterations.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

In a method for feature learning, first and second datasets are obtained. The first dataset includes first behavior data, indicating whether an object performs click and conversion behaviors on recommended content, of a first group of objects on a target application. The second dataset includes second behavior data, indicating whether the object performs a click behavior on the recommended content, of a second group of objects on the target application. Based on a union of the first and second datasets, training samples respectively corresponding to objects are generated. Each traning sample includes attribute information of an object and labels. The first and second label respectively indicate whether the object performs a click behavior and whether the object performs a conversion behavior or indicating a predetermined indicator. An object feature extraction model is trained with training samples, and is configured to extract a feature embedding corresponding to the object.

According to embodiments of the disclosure, a method, apparatus, device, medium and program product for content recommendation for content recommendation are provided. The method includes: determining, in response to receiving a supply request for target recommended content, category information corresponding to the target recommended content, the category information indicating a target category to which the target recommended content is classified and/or at least one category related to the target category; obtaining historical behavior data associated with a category indicated by the category information, the historical behavior data indicating at least one behavior performed by an audience group on recommended content of a corresponding category in response to the recommended content being provided to the audience group; and determining, based on the historical behavior data, a target audience group corresponding to the target recommended content, to provide the target recommended content to at least a part of members in the target audience group.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …