426 results about "Object Class" patented technology

A method and apparatus for training a text-graph model, a device, and a storage medium, relating to the artificial intelligence. The method comprises: on the basis of a training set of graph-text sample pairs, performing iterative training on a model to be trained, to obtain a text-graph model; in a training process: selecting a graph-text sample pair from the training set of graph-text sample pairs, the graph-text sample pair comprising a sample image and a description text, and the sample image comprising at least two objects; obtaining mask images corresponding to the at least two objects and associated object class names, the mask images being used for distinguishing position regions of the objects in the sample image; inputting the sample image and the description text to a model to be trained, to obtain an image prediction noise of the sample image, and inputting at least two mask images and the associated object class names to the model to be trained to obtain object prediction noises respectively associated with the at least two mask images; and constructing a loss function on the basis of the image prediction noise and the object prediction noises, and by using the loss function, adjusting a parameter for the model to be trained.

Embodiments described herein provide methods and systems for open vocabulary object detection of images. given a pre-trained vision-language model and an image-caption pair, an activation map may be computed in the image that corresponds to an object of interest mentioned in the caption. The activation map is then converted into a pseudo bounding-box label for the corresponding object category. The open vocabulary detector is then directly supervised by these pseudo box-labels, which enables training object detectors with no human-provided bounding-box annotations.

The present disclosure relates to systems, methods, and non-transitory computer readable media that generate inpainted digital images utilizing class-specific cascaded modulation inpainting neural network. For example, the disclosed systems utilize a class-specific cascaded modulation inpainting neural network that includes cascaded modulation decoder layers to generate replacement pixels portraying a particular target object class. To illustrate, in response to user selection of a replacement region and target object class, the disclosed systems utilize a class-specific cascaded modulation inpainting neural network corresponding to the target object class to generate an inpainted digital image that portrays an instance of the target object class within the replacement region. Moreover, in one or more embodiments the disclosed systems train class-specific cascaded modulation inpainting neural networks corresponding to a variety of target object classes, such as a sky object class, a water object class, a ground object class, or a human object class.

A method may include applying a first machine learning model trained to perform an open-set detection by at least identifying, based at least on image data indicative of one or more objects present in at least one environment in which one or more vehicles operate, at least one new class of objects. A dataset including a plurality of classes of objects may be updated to include the at least one new class of objects. In some cases, the dataset may be further updated to include a label associated with the at least one new class of objects. A second machine learning model may be trained, or in some cases updated, based at least on the updated dataset including the at least one new class of objects. Related systems and computer program products are also provided.

A text-to-image model training method, apparatus, and computer-readable storage medium for enhancing text-to-image generation through object-aware training. The method trains a text-to-image model using cyclic iterative training with sample image and text pairs. Training involves selecting image-text sample pairs containing multiple objects, obtaining corresponding mask images and object class names that distinguish location regions of the objects, and inputting both the sample image with description text and the mask images with object class names into the model. The method obtains image predicted noise and object predicted noises, constructs a loss function based on these predictions, and performs parameter adjustment accordingly. This approach enables improved object-level understanding in text-to-image generation models.

Methods and systems for assisting a vehicle in avoiding an object in a roadway and communicating associated information to trailing vehicles. Image data is sensed by a vehicle image sensor regarding a roadway. A computing system detects an object in the roadway based on the first image data. Feature extraction is performed to extract relevant features of the object, which is fed to an object classification model to determine a class of the object. A threat analysis is performed based on the determined class of the object, outputting a risk score. The first vehicle is commanded to take an action based on the risk score. The class of the object, the risk score, and / or the commanded action taken by the vehicle is communicated to a second vehicle that is approaching the object.

Systems and methods are provided for implementing training of a pre-trained object detection model for detecting new object classes. In examples, to train an object detection model, which has been pre-trained with a first set of object classes, with a new object class, a computing system applies to each of a plurality of first images that each depicts an object corresponding to an object class among the first set of object classes, a set of data augmentations combining each first image with at least one second image among a plurality of second images that each depicts a second object corresponding to the new object class, to generate a plurality of augmented images. The computing system trains the object detection model using the plurality of augmented images. In examples, original weights corresponding to the first set of object classes are retained, while random weights are used for the new object class.

The present application provides a method for device, and computer storage medium for generating an image caption. The method comprises: obtaining an image to be processed and auxiliary caption information, wherein the image to be processed includes a main object, and the auxiliary caption information includes at least one of the following: name information corresponding to the main object, object category corresponding to the main object, an object attribute corresponding to the main object, and an image tag corresponding to the image to be processed; determining an image feature corresponding to the image to be processed, and an auxiliary feature corresponding to the auxiliary caption information; generating the caption based on the image feature and the auxiliary feature to obtain a target caption corresponding to the image to be processed, wherein the target caption includes the name information of the main object.

The disclosure includes a method (100) for classifying at least one detectable object (10) with at least one ultrasonic sensor (50). In this process, (120) object class information (12) for the at least one object (10) is determined using a neural network (9), wherein the neural network (9) generates an output (15) based on at least one first input (11), which indicates a probability value for at least one defined object class for the one object (10).

A computer-implemented method for classifying points in a point cloud obtained by an active detection and ranging system is provided. The method comprises: computing a latent representation of the point cloud, determining from the latent representation, for each point in the point cloud, a probability that the point represents an object belonging to one or more object classes, and determining from the latent representation, for each point in the point cloud, a probability the point represents a ghost object. An object classification network is used for determining the probability that the point represents an object, and a ghost classification network is used for determining the probability the point represents a ghost object.

The invention discloses a data exporting method and device based on EasyExcel annotations and a storage medium, and belongs to the technical field of computers. The method comprises the following steps: acquiring a data export template, wherein the data export template defines a data export structure; under the condition that the data export template meets a preset condition, generating a receiving object comprising the annotation according to the data export template; the receiving object comprises an object class bearing data, and the annotation is used for controlling the export behavior of the data; assembling the data to be exported into a receiving object; and exporting the to-be-exported data in the receiving object into the data exporting template based on the annotation. Through the predefined data export template, when the data export template meets the preset condition, the receiving object containing the annotation can be automatically generated, a developer only needs to pay attention to data assembly and business logic, data export can be achieved, a large number of tedious redundant codes do not need to be written, the workload of manual coding is reduced, and the data export efficiency is improved. And the data export efficiency is improved.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate and implement behavioral policy graphs for digital image editing. For instance, in some embodiments, the disclosed systems generate, for a client device, a behavioral policy graph that assigns behaviors to object classes based on object relationships. The disclosed systems receive, from the client device, a digital image portraying a plurality of objects. Further, the disclosed systems determine behaviors of the plurality of objects utilizing the behavioral policy graph by determining, for each object of the plurality of objects, a behavior based on a relationship of the object with an additional object of the plurality of objects in accordance with the behavioral policy graph. The disclosed systems modify the digital image by modifying one or more objects based on the behaviors of the plurality of objects.

Embodiments disclosed herein relate to a method, a device, and a computer program product for training an image classification model. The method includes: determining a first classification result obtained by the image classification model on pixel points of a sample image in a first training iteration, wherein the first classification result indicates that each of the pixel points belongs to one of a plurality of object classes; determining a second classification result obtained by the image classification model on the pixel points of the sample image in a second training iteration; determining, based on the first classification result and the second classification result, a first set of recall rates and a second set of recall rates for the plurality of object classes; and adjusting, based on the first set of recall rates and the second set of recall rates, the image classification model to obtain a trained image classification model.

Embodiments of the present disclosure relate to using ray tracing to simulate physical environments based on scene geometry and electromagnetic material (EM) properties (scene properties) which may be assigned to objects in the scene. The scene properties may include relative permittivity, conductivity, and permeability of the objects, as well as effective roughness, and scattering functions. Segmentation data may be used to assign materials to objects, providing additional information for calibrating a ray tracer learning the scene properties for an environment via radio propagation. The segmentation data may comprise a segmentation mask with object class identifiers associated with each pixel of an image of the scene. For example, each pixel included within a chair is associated with an object class identifier that is specific to a chair. The segmentation data enables clustering of objects in image space where the objects in each cluster share radio materials and therefore share scene properties.

Approaches presented herein provide for the unconditional generation of novel three dimensional (3D) object shape representations, such as point clouds or meshes. In at least one embodiment, a first denoising diffusion model (DDM) can be trained to synthesize a 1D shape latent from Gaussian noise, and a second DDM can be trained to generate a set of latent points conditioned on this 1D shape latent. The shape latent and set of latent points can be provided to a decoder to generate a 3D point cloud representative of a random object from among the object classes on which the models were trained. A surface reconstruction process may be used to generate a surface mesh from this generated point cloud. Such an approach can scale to complex and / or multimodal distributions, and can be highly flexible as it can be adapted to various tasks such as multimodal voxel- or text-guided synthesis.

A method of inspecting a composite structure formed of plies of tows is provided. The method involves receiving an image of an upper ply overlapping lower plies, the upper ply tow ends defining a boundary between plies, and applying extracted sub-images to a trained machine learning model to detect the upper or lower ply. Probability maps are produced in which pixels of the sub-images are associated with probabilities the pixels belong to an object class for the upper or lower ply. The method may also involve transforming the probability maps into reconstructed sub-images, stitching together a composite image, and applying the composite image to a feature detector to detect locations of tow ends of the upper ply. The method may also involve comparing the locations to as-designed locations of the tow ends, inspecting the composite structure, and indicating a result of the comparison.

The present invention relates to a method for classifying objects into object classes based on information of at least one ultrasonic sensor of a vehicle.

The invention provides an inspection standard text processing method and device, electronic equipment and a storage medium, and relates to the technical field of inspection standard processing. The method comprises the following steps: converting an inspection standard text into a natural text paragraph; splitting the natural text paragraph into a plurality of pieces of structured metadata according to text semantics, and dividing each piece of structured metadata in the plurality of pieces of structured metadata into inspection object type structured metadata, inspection item type structured metadata, inspection method type structured metadata and inspection index type structured metadata; based on the test object type structured metadata, the test item type structured metadata, the test method type structured metadata and the test index type structured metadata, establishing an association relationship corresponding to the test object type structured metadata; and establishing a tree structure corresponding to the test object class structured metadata based on the association relationship. The tree structure can be automatically established according to the inspection standard text, and efficiency and accuracy are high.

Techniques and apparatuses enabling high accuracy video object detection using reduced system resource requirements (e.g., reduced computational load, shallower neural network designs, etc.) are described. For example, a search domain of an object detection scheme (e.g., a target object class, a target object size, a target object rotation angle, etc.) may be separated into subdomains (e.g., such as subdomains of object classes, subdomains of object sizes, subdomains object rotation angles, etc.). Specialized, subdomain-level object detection / segmentation tasks may then be separated across sequential video frames. As such, different subdomain-level processing techniques (e.g., via specialized neural networks) may be implemented across different frames of a video sequence. Moreover, redundancy information of consecutive video frames may be leveraged, such that specialized object detection tasks combined with visual object tracking across consecutive frames may enable more efficient (e.g., more accurate, less computationally intensive, etc.) full domain object detection and object segmentation schemes.

A device for combined clutter detection and semantic segmentation of an input set of detection points from a lens or radar sensor is described. The device comprises a basic neural network configured to determine a feature set for the input set of detection points. Furthermore, the device comprises a clutter neural network configured to determine, based on the feature set, a clutter set corresponding to the input set, which indicates for each individual detection point whether it is clutter or not. The device also comprises a segmentation neural network configured to determine, based on the feature set, a segmentation set corresponding to the input set, which specifies an object class from a plurality of different object classes for at least some of the detection points.

The invention relates to a simulation method and device based on a universal code framework and computer equipment. The method comprises the steps of editing an object description file, dynamically generating a frame code of a universal code frame according to the object description file, generating a corresponding data structure in the frame code according to object class and interaction class information in the object description file, creating an interface class inheriting a simulation function class, and adding a simulation unit into joint simulation. The method comprises the following steps of: calling a related interface type function to send and receive object type data and interactive message data in simulation propulsion and callback, respectively serializing and deserializing simulation operation data which is accessed and output by joint simulation according to a data structure, and when simulation stops, calling a simulation stopping interface by a simulation unit to finish simulation. By the adoption of the method, a code framework which can be transformed and reused can be provided for convenient integrated development of the simulation unit, automatic calling of simulation middleware service is achieved, and the difficulty and workload of integrated development are reduced.

A computer-implemented method for building an object detection module uses mesh representations of objects belonging to specified object classes of interest to render images by a physics-based simulator. Each rendered image captures a simulated environment containing objects belonging to multiple object classes of interest placed in a bin or on a table. The rendered images are generated by randomizing a set of parameters by the simulator to render a range of simulated environments. The randomized parameters include environmental and sensor-based parameters. A label is generated for each rendered image, which includes a two-dimensional representation indicative of location and object classes of objects in that rendered image frame. Each rendered image and the respective label constitute a data sample of a synthetic training dataset. A deep learning model is trained using the synthetic training dataset to output object classes from an input image of a real-world physical environment.

The present application provides a software management method, apparatus, management device and storage medium. The method obtains management information of a software management object class, wherein the software management object class includes a capability management object class and a control management object class, wherein the management information includes capability information corresponding to a managed network function set based on the capability management object class and operation information corresponding to the managed network function set based on the control management object class; and manages the software of the managed network function according to the management information of the software management object class.

The present application discloses an object category recognition model training method and apparatus, and an object category recognition method and apparatus, which can be applied to various scenarios such as cloud technology, artificial intelligence, intelligent transportation, and the Internet of vehicles. The method comprises: acquiring a newly added sample image of a sample object; on the basis of an initial object category recognition model, constructing a teacher model and a student model; inputting the newly added sample image into the teacher model for performing first object category recognition, and obtaining a first sample category; performing fusion on the first sample category and a newly added object category, and obtaining a fused category; inputting the newly added sample image into the student model for performing second object category recognition, and obtaining a second sample category; and, on the basis of a difference between the second sample category and the fused category, training the student model, so as to obtain a final object category recognition model. According to the model training method of the present application, the training duration is greatly shortened, and the model updating efficiency is improved.

Approaches presented herein provide for the unconditional generation of novel three dimensional (3D) object shape representations, such as point clouds or meshes. In at least one embodiment, a first denoising diffusion model (DDM) can be trained to synthesize a 1D shape latent from Gaussian noise, and a second DDM can be trained to generate a set of latent points conditioned on this 1D shape latent. The shape latent and set of latent points can be provided to a decoder to generate a 3D point cloud representative of a random object from among the object classes on which the models were trained. A surface reconstruction process may be used to generate a surface mesh from this generated point cloud. Such an approach can scale to complex and / or multimodal distributions, and can be highly flexible as it can be adapted to various tasks such as multimodal voxel- or text-guided synthesis.

The present application discloses a content recommendation method and apparatus, an electronic device, and a readable medium. In the method, first, a target object class is determined on the basis of historical interaction behaviors; and then a recommended media stream corresponding to the target object class is displayed on a media stream page, the recommended media stream comprising a recommended object corresponding to the target object class.

A controlling device receives from at least one sensor a first data and the controlling device uses the first data to identify at least one of a plurality of general object categories. The identified at least one of the plurality of general object categories to is used to select at least one of a plurality of heating, ventilation, and cooling (HVAC) profiles and the selected at least one of the plurality of HVAC profiles to control one of more HVAC elements.

A method and related system may analyze metadata associated with a first set of transactions to determine whether to perform a second set of transactions. The method and related system may include determining a data category based on first device-provided data of a first database transaction indicating a first record associated with a second record, and may further include obtaining, based on whether the data category satisfies a first set of criteria, an identifier and an amount based on image data using a prediction model. The method may further include querying a database based on the identifier to obtain an indication that the identifier is mapped to an object category, validating the amount based on a result indicating whether the object category satisfies a second set of criteria, and causing a second transaction that changes fields of the first and second records.

This document describes techniques and systems for fusion of object classes. Sensor data, related to an object, can be obtained from different types of sensor systems. Using techniques based on a Dempster Shafer framework, masses of each potential object class based on data from a respective sensor can be calculated. The respective masses of each potential object class, based on the different sensor systems, can be combined to generate a fused mass for each potential object class. Probabilities for each potential object class can be calculated based on the respective fused masses. An assigned object class for the object can be selected based on a probability exceeding some decision threshold. This assigned object class may then be available for an object tracker, an object fusion system, or other vehicle system resulting in a safer driving experience.

The invention provides a knowledge base retrieval method and device, electronic equipment and a storage medium, and belongs to the technical field of data processing.The method comprises the steps that a target retrieval image is obtained and input into a target retrieval model, and the target retrieval model comprises a target visual large model and a target cross-modal mapping module; performing visual feature extraction on a target retrieval image through a target visual large model to obtain target retrieval visual features, and mapping the target retrieval visual features into text features through a target cross-modal mapping module to obtain target retrieval text features; according to the target retrieval visual features and the target retrieval text features, a pre-constructed multi-modal knowledge base is retrieved, the initial object category of the target object and the retrieval score of the initial object category are obtained, the target object category of the target object is determined according to the initial object category and the retrieval score, and the accuracy of knowledge base retrieval is improved.