Abstract: An application server may receive an input document including a set of input text fields and an input key phrase querying a value for a key-value pair that corresponds to one or more of the set of input text fields. The application server may extract, using an optical character recognition model, a set of character strings and a set of two-dimensional locations of the set of character strings on a layout of the input document. After extraction, the application server may input the extracted set of character strings and the set of two-dimensional locations into a machine learned model that is trained to compute a probability that a character string corresponds to the value for the key-value pair. The application server may then identify the value for the key-value pair corresponding to the input key phrase and may out the identified value.

Abstract: Provided is a system that includes at least one processor programmed or configured to receive an XML data file, wherein the XML data file includes data associated with one or more input parameters of a machine learning model, generate a code generation template based on the data associated with one or more input parameters of the machine learning model included in the XML file, where the code generation template includes one or more keys associated with one or more parameters of a transaction aggregate for an account of a user, and generate a file of executable code based on the code generation template, wherein the file of executable code includes instructions that, when executed by at least one processor, causes at least one processor to retrieve transaction aggregate data associated with the transaction aggregate for the account of the user. A method and computer program product are also provided.

Abstract: Embodiments described herein provide a mechanism for replacing existing text encoders in text-to-image generation models with more powerful pre-trained language models. Specifically, a translation network is trained to map features from the pre-trained language model output into the space of the target text encoder. The training preserves the rich structure of the pre-trained language model while allowing it to operate within the text-to-image generation model. The resulting modularized text-to-image model receives prompt and generates an image representing the features contained in the prompt.

Abstract: Systems and methods for training a neural network based three-dimensional (3D) encoder for 3D classification are provided. A training dataset including a plurality of samples is received, wherein a first sample includes an image, a text, and a point cloud. An image encoder of a pretrained vision and language model is used to generate image representations for the image of the first sample. A text encoder of the pretrained vision and language model is used to generate text representations for the text of the first sample. The neural network based 3D encoder is used to generate 3D representations for the point cloud of the first sample. A loss objective is computed based on the image representations, text representations, and 3D representations. Parameters of the neural network based 3D encoder are updated based on the computed loss objective via backpropagation.

Abstract: Embodiments described herein provide a system for three-dimensional (3D) object detection. The system includes an input interface configured to obtain 3D point data describing spatial information of a plurality of points, and a memory storing a neural network based 3D object detection model having an encoder and a decoder. The system also includes processors to perform operations including: encoding, by the encoder, a first set of coordinates into a first set of point features and a set of object features; sampling a second set of point features from the first set of point features; generating, by attention layers at the decoder, a set of attention weights by applying cross-attention over at least the set of object features and the second set of point feature, and generate, by the decoder, a predicted bounding box among the plurality of points based on at least in part on the set of attention weights.

Abstract: A method of training a neural network based three-dimensional (3D) encoder is provided. A training dataset is generated using a plurality of 3D models of a 3D model dataset. To generate a first sample of the training dataset, an image generator with multi-view rendering is used to generate a plurality of image candidates of a first 3D model. A word is chosen from metadata associated with the first 3D model. A language model is used to generate one or more text descriptions using the selected word and a plurality of prompts. A point cloud is generated by randomly sampling points in the 3D model. The first sample is generated to include a first image randomly selected from the plurality of image candidates, one or more text descriptions, and the point cloud is generated. The 3D encoder is trained using the training dataset including the first sample.

Abstract: This application discloses a shard adjustment method for a time series database, belongs to the field of data processing technologies. First, feature information of an access request of at least one user for a data table of a time series database is obtained. The data table is divided into a plurality of shard groups according to a predetermined rule, and each shard group can be further divided into a plurality of shards. Each shard group is set in a different time period, and each shard is set in a different node. Then, the predetermined rule is adjusted based on the feature information, and a new shard group and/or a new shard that match/matches the access habit are/is generated according to an adjusted rule.

Abstract: Provided is a system that includes at least one processor programmed or configured to receive an XML data file, wherein the XML data file includes data associated with one or more input parameters of a machine learning model, generate a code generation template based on the data associated with one or more input parameters of the machine learning model included in the XML file, where the code generation template includes one or more keys associated with one or more parameters of a transaction aggregate for an account of a user, and generate a file of executable code based on the code generation template, wherein the file of executable code includes instructions that, when executed by at least one processor, causes at least one processor to retrieve transaction aggregate data associated with the transaction aggregate for the account of the user. A method and computer program product are also provided.

Abstract: Embodiments described herein provide systems and methods for multimodal layout generations for digital publications. The system may receive as inputs, a background image, one or more foreground texts, and one or more foreground images. Feature representations of the background image may be generated. The foreground inputs may be input to a layout generator which has cross attention to the background image feature representations in order to generate a layout comprising of bounding box parameters for each input item. A composite layout may be generated based on the inputs and generated bounding boxes. The resulting composite layout may then be displayed on a user interface.

Abstract: Embodiments described herein provide an open-vocabulary instance segmentation framework that adopts a pre-trained vision-language model to develop a pipeline in detecting novel categories of instances.

Abstract: A system uses a neural network based model to perform scene text recognition. The system achieves high accuracy of prediction of text from scenes based on a neural network architecture that uses double attention mechanism. The neural network based model includes a convolutional neural network component that outputs a set of visual features and an attention extractor neural network component that determines attention scores based on the visual features. The visual features and the attention scores are combined to generate mixed features that are provided as input to a character recognizer component that determines a second attention score and recognizes the characters based on the second attention score. The system trains the neural network based model by adjusting the neural network parameters to minimize a multi-class gradient harmonizing mechanism (GHM) loss. The multi-class GHM loss varies based on a level of difficulty of the sample.

Abstract: A biometric input system for an electronic device is provided. The biometric input system may be a fingerprint sensing system. The biometric input system includes a biometric sensing component, which may be a capacitive sensing component. The biometric input system also includes a composite cover element, which may be a dielectric cap or coating, and the biometric sensing component is capable of receiving a biometric input from a user through the composite cover element. Electronic devices including the biometric input system are also provided.

Abstract: Methods and systems for object detection are disclosed. The methods and systems include: receiving a video frame, determining an execution configuration among multiple configurations at an inference time based on the video frame and multiple metrics (e.g., a latency metric, an accuracy metric, and an energy metric), and performing object detection or object tracking at the inference time based on the video frame and the execution configuration. Other aspects, embodiments, and features are also claimed and described.

Abstract: This application provides a three-dimensional road network construction method performed by an electronic device. The method includes: obtaining a two-dimensional road network, the two-dimensional road network comprising a plurality of paths, each path being formed by connecting a plurality of nodes; determining a relative elevation for a node of a current path overlapping the current path and/or another path among the nodes of the current path, the relative elevation representing a height of the current path at the node from a reference plane; determining relative elevations of nodes constituting a center line of the current path according to the relative elevations of the nodes of the current path and a width of the current path; and constructing a three-dimensional road corresponding to the current path according to the width and the relative elevations of the nodes of the center line of the current path to obtain a three-dimensional road network.

Abstract: A system may receive video information. The system may select a combination of light-weight features and heavy weight features. The light-weight features may be extracted from the video information and the heavy weight features not extracted. The system may forecast, based on the light-weight features and the heavy weight features, accuracy, and latency metrics for performing the object detection and tracking using a plurality of candidate branch configurations, respectively. The system may select a branch configuration from the plurality of candidate branch configurations in response to satisfaction of an optimization criterion. The system may perform object detection and tracking based on the selected branch configuration.

Abstract: Computing systems may support image classification and image detection services, and these services may utilize object detection/image classification machine learning models. The described techniques provide for normalization of confidence scores corresponding to manipulated target images and for non-max suppression within the range of confidence scores for manipulated images. In one example, the techniques provide for generating different scales of a test image, and the system performs normalization of confidence scores corresponding to each scaled image and non-max suppression per scaled image These techniques may be used to provide more accurate image detection (e.g., object detection and/or image classification) and may be used with models that are not trained on modified image sets. The model may be trained on a standard (e.g. non-manipulated) image set but used with manipulated target images and the described techniques to provide accurate object detection.

Abstract: An online system extracts information from non-fixed form documents. The online system receives an image of a form document and obtains a set of phrases and locations of the set of phrases on the form image. For at least one field, the online system determines key scores for the set of phrases. The online system identifies a set of candidate values for the field from the set of identified phrases and identifies a set of neighbors for each candidate value from the set of identified phrases. The online system determines neighbor scores, where a neighbor score for a candidate value and a respective neighbor is determined based on the key score for the neighbor and a spatial relationship of the neighbor to the candidate value. The online system selects a candidate value and a respective neighbor based on the neighbor score as the value and key for the field.

Abstract: Embodiments of the present application disclose a deformation control method, a deformation control apparatus, and a user equipment (UE). The method comprises: generating trigger information according to a focus behavior of a user on at least one associated region in multiple associated regions on a deformation controllable device, where the multiple associated regions are multiple regions on which the user synchronously focuses or will synchronously focus; and controlling, in response to the trigger information, the deformation controllable device to be deformed to a target shape that meets at least one shape restriction condition. The at least one shape restriction condition comprises: a value of at least one angle between at least one normal line of any associated region in the multiple associated regions and at least one normal line of any other associated region is less than an angle threshold.

Abstract: Embodiments described herein provide an online domain adaptation framework based on cross-domain bootstrapping for online domain adaptation, in which the target domain streaming data is deleted immediately after adapted. At each online query, the data diversity is increased across domains by bootstrapping the source domain to form diverse combinations with the current target query. To fully take advantage of the valuable discrepancies among the diverse combinations, a set of independent learners are trained to preserve the differences. The knowledge of the learners is then integrated by exchanging their predicted pseudo-labels on the current target query to co-supervise the learning on the target domain, but without sharing the weights to maintain the learners' divergence.