A computing system for decimating video data includes: a processor; a persistent storage system coupled to the processor; and memory storing instructions that, when executed by the processor, cause the processor to decimate a batch of frames of video data by: receiving the batch of frames of video data; mapping, by a feature extractor, the frames of the batch to corresponding feature vectors in a feature space, each of the feature vectors having a lower dimension than a corresponding one of the frames of the batch; selecting a set of dissimilar frames from the plurality of frames of video data based on dissimilarities between corresponding ones of the feature vectors; and storing the selected set of dissimilar frames in the persistent storage system, the size of the selected set of dissimilar frames being smaller than the number of frames in the batch of frames of video data.

Disclosed are computer-implemented methods, non-transitory computer-readable media, and systems for authentication. One computer-implemented method includes obtaining a first image, where the first image is an image of an identification (ID) document captured when the ID document is tilted at a first angle relative to a projected light source. A second image is obtained, where the second image is an image of the ID document captured when the ID document is tilted at a second angle relative to the projected light source. The ID document is authenticated based on identification of a first illuminated region and a second illuminated region, where the first illuminated region is associated with the first image and the second illuminated region is associated with the second image, and a comparison between a first position of the first illuminated region and a second position of the second illuminated region.

This application relates to the field of artificial intelligence technologies, and in particular, to a training method of an image-text matching model, a bi-directional search method, and a relevant apparatus. The training method includes extracting a global feature and a local feature of an image sample; extracting a global feature and a local feature of a text sample; training a matching model according to the extracted global feature and local feature of the image sample and the extracted global feature and local feature of the text sample, to determine model parameters of the matching model; and determining, by the matching model, according to a global feature and a local feature of an inputted image and a global feature and a local feature of an inputted text, a matching degree between the image and the text.

Systems and methods are provided for generating a rear view image display for a motor vehicle. A rear view system includes an optical sensor disposed at the motor vehicle and configured to capture image data, a computational unit coupled to the optical sensor by a cable connection and configured to execute program instructions stored on a computer-readable medium to modify the image data for presentation, and a display device coupled to the computational unit and configured to receive the modified image data from the computational unit and display the modified image data to a driver of the motor vehicle. The computational unit is further configured to receive software calibration to optimize modification of the image data.

A three-dimensional object reconstruction method, applied to a terminal device or a server, is provided. The method includes obtaining a plurality of video frames of an object; determining three-dimensional location information of key points of the object in the plurality of video frames and physical meaning information of the key points, the physical meaning information indicating respective positions of the object; determining a correspondence between the key points having the same physical meaning information in the plurality of video frames; and generating a three-dimensional object according to the correspondence and the three-dimensional location information of the key points.

This application relates to the field of artificial intelligence technologies, and in particular, to a training method of an image-text matching model, a bi-directional search method, and a relevant apparatus. The training method includes extracting a global feature and a local feature of an image sample; extracting a global feature and a local feature of a text sample; training a matching model according to the extracted global feature and local feature of the image sample and the extracted global feature and local feature of the text sample, to determine model parameters of the matching model; and determining, by the matching model, according to a global feature and a local feature of an inputted image and a global feature and a local feature of an inputted text, a matching degree between the image and the text.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for multi-query object matching based on inverse model frequency. The methods, systems, and apparatus include actions of obtaining images of a sample object, obtaining models of known objects, determining an image score for each pair of the images and the models, determining an inverse model frequency for each image based on the image scores, determining a model score for each model based on the inverse model frequencies and the image scores, and selecting a particular known object of the known objects as the sample object based on the model scores.

An example system includes a processor to receive a data set and similarity scores. The processor is to execute an eigen response analysis on eigenvectors calculated for a similarity matrix generated based on the similarity scores for the data set. The processor is to output an estimated number of clusters in the data set based on the eigen response analysis.

A model can be trained to detect interactions of other drivers through a window of their vehicle. A human driver behind a window (e.g., front windshield) of a vehicle can be detected in a real-world driving data. The human driver can be tracked over time through the window. The real-world driving data can be augmented by replacing at least a portion of the human driver with at least a portion of a virtual driver performing a target driver interaction to generate an augmented real-world driving dataset. The target driver interaction can be a gesture or a gaze. Using the augmented real-world driving data set, a machine learning model can be trained to detect the target driver interactions. Thus, simulation can be leveraged to provide a large set of useful training data without having to acquire real-world data of drivers performing target driver interactions as viewed from outside the vehicle.

A method displays information graphically on an image captured by a vehicular optical system. The method includes capturing the image and identifying an object in the image. The method the assigns a priority level to the object based on a predetermined criterion. The object is altered based on its priority level to create an altered object. An altered object may have a changed color, a colored halo surrounding it, or a colored object inside it. Other possible ways to alter the way the object looks are possible. The altered object is displayed in the image in place of the object on a mobile device to alert a person of its presence and the priority level associated therewith.