Nanjing University of Aeronautics and Astronautics

Tencent Technology (Shenzhen) Company Limited

Black Sesame Technologies Co., Ltd.

Tencent Technology Company Limited

Shengjun Huang

Wei Chen

Di Wang

Kun Yuan

Songcan Chen

Nengneng Gao

Ling Li

Dong Liang

Implementations of the present specification provide a vehicle fault processing method and apparatus, a device, and a medium. The method includes: determining a position of a target vehicle when fault detection of the target vehicle is triggered; sending a detection instruction to a target detection device corresponding to the target vehicle based on the position, wherein the target detection device is close to the position and capable of detecting the target vehicle; receiving fault information obtained by performing fault detection on the target vehicle through the detection device in response to the detection instruction; and performing fault processing on the target vehicle based on the fault information. In a case where a faulty vehicle is unable to perform fault communication, fault information of the faulty vehicle may be collected by a nearby target detection device, ensuring the fault processing of the vehicle in a communication fault state.

Vehicle fault processing method and apparatus, server, device, and medium

Disclosed is a method for enhancement of a low-light image based on reinforcement learning and aesthetic evaluation. The method include: generating images of non-normal luminance under different lighting scenes, and constructing a training dataset for a reinforcement learning system based on the images; initializing the training dataset, a policy network, and a value network; updating, based on a no-reference reward score and an aesthetic assessment reward score, the policy network and the value network; completing model training and outputting an enhanced image result. By expanding the action space range defined in reinforcement learning, the enhancement operations for the input low-light image gain a greater dynamic range, offering higher flexibility for real-world scenarios and better meeting low-light image enhancement needs. Additionally, by incorporating the aesthetic quality assessment scores as part of the loss function, the enhanced image achieves better visual effects and higher subjective user evaluation scores.

Methods for enhancement of low-light images based on reinforcement learning and aesthetic evaluation

A sample selection method and apparatus and a server belong to the field of metric learning technologies. The method includes: selecting n sample pairs from an unlabeled sample set, each sample pair including two samples, and each sample including data in p modalities; calculating a partial similarity between data that is in each modality and that is of one sample included in the sample pair and data that is in each modality and that is of the other sample, to obtain p&#xd7;p partial similarities; calculating, according to the p&#xd7;p partial similarities, an overall similarity between the two samples included in the sample pair; obtaining a degree of difference between the p&#xd7;p partial similarities and the overall similarity; and selecting a sample pair that meets a preset condition and that is in the n sample pairs as a training sample. In this application, training samples of high quality are selected to train a metric model, so that the metric model of higher precision can be trained by using fewer training samples.

Sample selection method and apparatus and server

Growing community of inventors

Shenzhen, China

Shengjun Huang