Abstract: The present invention relates to a process for manufacturing a silver-plated copper or a copper alloy blank wire, having a silver layer thickness of 1.5 ?m to 15 ?m, comprising the step of electrolytically depositing silver on the copper or copper alloy blank wire, said electrolytic deposition being performed at a pulsating current with reversal in a silver-plating bath under particular electrolytic conditions. It also relates to the silver-plated copper or copper alloy blank wire obtainable by said process, a process for manufacturing a silver-plated copper or copper alloy strand, the strand obtainable by said process, a silver-plated conductor and an electromagnetic shielding layer comprising the silver-plated strand, an electric wire comprising the silver-plated conductor and an electric cable comprising the electric wire and uses thereof.

Abstract: Embodiments described herein provide a diffusion-based framework that is trained on a dataset with limited text labels, to generate a distribution of data samples in the dataset given a specific text description label. Specifically, firstly, unlabeled data is used to train the diffusion model to generate a data distribution of data samples given a specific text description label. Then text-labeled data samples are used to finetune the diffusion model to generate data distribution given a specific text description label, thus enhancing controllability of training.

Abstract: The present disclosure provides a vehicle control method, an apparatus, an electronic device and a vehicle, which relates to a technical field of artificial intelligence, such as automatic driving, intelligent transportation and computer vision, etc. The specific implementation solution is that: when passing a traffic light intersection, a vehicle can acquire a traffic light image of the intersection at a driving direction of the vehicle, identify the traffic light image, determine a first light color of a target traffic light corresponding to a lane on which the vehicle is located; and acquire light color change information of the target traffic light latest recorded; determine remained duration of the first light color according to the light color change information, then determine a driving strategy at the intersection of the vehicle according to the first light color and the remained duration of the first light color.

Abstract: Embodiments described herein provide a method of image generation. The method includes a fixed diffusion model, and a trainable diffusion model. The fixed diffusion model may be pretrained on a large training corpus. The trainable diffusion model may be used to control the image generation of the fixed diffusion model by modifying internal representations of the fixed diffusion model. A task instruction may be provided in addition to a text prompt, and the task instruction may guide the trainable diffusion model together with the visual conditions. The visual conditions may be adapted according to the task instruction. During training, a fixed number of task instructions may be used. At inference, unseen task instructions may be used by combining convolutional kernels of the visual condition adapter.

Abstract: Embodiments described herein provide a method of generating a multi-modal task output to a text instruction relating to inputs of multiple different modalities (e.g., text, audio, video, 3D). The method comprises receiving, via a data interface, a first input of a first modality, a second input of a second modality and the text instruction relating to the first and the second inputs; encoding, by a first multimodal encoder adapted for the first modality, the first input of the first modality into a first encoded representation conditioned on the text instruction; encoding, by a second multimodal encoder adapted for the second modality, the second input of the second modality into a second encoded representation conditioned on the text instruction; and generating, by a neural network based language model, the multi-modal task output based on an input combining the first encoded representation, the second encoded representation, and the text instruction.

Abstract: In response to a request to park an ADV in a parking lot, a set of parking-trajectories associated with a set of predetermined locations near one or more parking spots in the parking lot may be obtained, where the set of parking-trajectories was previously generated based on prior collected planning and control data of the parking lot. Each parking-trajectory of the set of parking-trajectories may correspond to one parking spot of the one or more parking spots in the parking lot. A parking-trajectory may be selected from the set of parking-trajectories based on a current location of the ADV. The ADV may be controlled to park in a corresponding parking spot according to the selected parking-trajectory.

Abstract: A method of training a neural network based three-dimensional (3D) encoder is provided. A first plurality of samples of a training dataset are generated using a first 3D model. An image generator with multi-view rendering is used to generate a plurality of two-dimensional (2D) images having different viewpoints of the first 3D model. A first language model is used to generate a plurality of texts corresponding to the plurality of 2D images respectively. A first text for a first image is generated by using one or more text descriptions generated by the first language model. A point cloud is generated by randomly sampling points in the 3D model. The first plurality of samples are generated using the plurality of 2D images, the corresponding plurality of texts, and the point cloud. The neural network based 3D encoder is trained using the training dataset including the first plurality of samples.

Abstract: Embodiments described herein provide a feedback based instructional image editing framework that employs a diffusion process to follow user instruction for image editing. A diffusion model is fine-tuned using a reward model, which may be trained via human annotation. The training of the reward model may be done by having the image editing model output a number of images, which a human annotator ranks based on their alignment with the original image and a given instruction.

Abstract: A computer-implement method for operating an ADV is disclosed. A starting point and an ending point of a route along which an ADV is to be driven is determined. Whether each of the starting point and the ending point is within a first driving area having a lane boundary or a second driving area as an open space is determined. The route is divided into a first route segment and a second route segment. Dependent upon whether the starting point or the ending point is within the first driving area or the second driving area, the method comprises operating in one of an on-lane mode or an open-space mode to plan a first trajectory for the first route segment and operating in one of the on-lane mode or the open-space mode to plan a second trajectory for the second route segment.

Abstract: Provided are a vehicle driving control method and apparatus. The method includes: determining, according to driving data of a vehicle, at least one piece of candidate speed information of the vehicle, the candidate speed information is used to indicate traveling speed of the vehicle at each moment in a first preset time period; predicting, according to movement data of an obstacle on a road, an obstacle trajectory of the obstacle in the first preset time period; determining right-of-way information corresponding to the obstacle trajectory, the right-of-way information is used to indicate a priority in traveling of the vehicle and the obstacle; and determining target speed information in the at least one piece of candidate speed information according to the right-of-way information corresponding to the obstacle trajectory and the obstacle trajectory, and controlling the vehicle to travel according to a route corresponding to the vehicle and the target speed information.

Abstract: Embodiments described herein provide systems and methods for training a text retrieval model. A system may generate queries associated with provided documents. The queries may be generated in one or more different manners. Examples of query generation may include extracting relevant spans of text from the documents, prompting a language model for a topic, title, abstractive summary, and/or extractive summary based on the documents. Metadata such as title or other HTML tags may be used as queries. Using the one or more queries, the text retrieval model may be trained using contrastive learning, using the generated query, and positive and negative sample documents. A fine-tuning training phase may be performed using domain-specific data which may also be done with generated query pairs, or may be done in a supervised fashion with provided queries. The text retrieval model may be used to locate documents given an input query.

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: 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 starting point, a set of one or more way points, and a destination point of a route along which the ADV is to be driven are determined. All lane segments near the starting point, the set of way points, and the destination point within a predetermined threshold distance are determined respectively. A set of route candidates are determined with an A-star (A*) searching algorithm based on a set of nodes representing all the lane segments near the starting point, the set of way points, and the destination point respectively. The route is selected from the set of route candidates based on respective costs of the set of route candidates. The ADV is being controlled to drive along the selected route autonomously.

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 computer-implement method for operating an ADV is disclosed. A first trajectory for the ADV to drive along is planned. The ADV is to autonomously drive along the first trajectory. An obstacle in an affected region of the ADV is detected based on sensor data obtained from a plurality of sensors mounted on the ADV. An expected residence time of the obstacle in the affected region is determined. Whether to plan a second trajectory or to wait for the obstacle to leave the affected region is determined based on the expected residence time of the obstacle in the affected region. A second trajectory for the ADV to drive along is planned and the ADV is to autonomously drive along the second trajectory, or the ADV is to wait for the obstacle to leave the affected region and to autonomously drive along the first trajectory afterwards.

Abstract: A method for simulating an obstacle in an unmanned simulation scene includes: for obstacle information in a three-dimensional scene map, determining Gaussian distribution information of obstacle position detected by using a perception algorithm to be tested based on actual perception performance of the perception algorithm; adjusting each position of the simulated obstacle in the initial motion trajectory sequence, such that a position deviation between each adjusted position point in the target motion trajectory sequence and the corresponding position point in the initial motion trajectory sequence follows a Gaussian distribution; and adding the target motion trajectory sequence of the simulated obstacle to the three-dimensional scene map.

Abstract: The present disclosure provides a positioning method for head and neck assessment comprising positioning a probe to the head and neck structures of a subject according to reference planes defined by light beams.

Abstract: A method and apparatus for determining a turn-round path of a vehicle, a device and a storage medium are provided. An embodiment of the method includes: determining a starting position and a target position for the vehicle to turn round on a road; determining, based at least partially on road information associated with the road and vehicle information associated with the vehicle, a candidate turn-round path between the starting position and the target position; evaluating the feasibility of the candidate turn-round path; and determining, based on the evaluation on the feasibility, a turn-round path by which the vehicle is to turn round on the road.