Intel Corporation

Baidu Online Network Technology (beijing) Co., Ltd.

Boe Technology Group Co., Ltd.

Apple Inc.

Nec Corporation

K-tronics (suzhou) Technology Co., Ltd.

Boe Optical Science and Technology Co., Ltd.

Baidu Online Network Technology Co., Ltd.

Feng Zhou

Guangjie Li

Hao Sun

Xiao Tan

Yuan Zhu

Errui Ding

Jong-Kae Fwu

Zhou Lu

Rath Vannithamby

Hujun Yin

Wenting Chang

Yang Gao

Kuilin Clark Chen

Hongmei Sun

Yunben Shen

Lihua Sheng

Jeong Julie Lee

Yushu Zhang

Qinghua Li

Xintian Eddie Lin

Xu Zhang

Changlong Xu

Peng Cheng

Qian Li

Xiao Xi Liu

Xiang Yu

Yuanqing Lin

Shanshan Zheng

Xiaoxin Wu

May Wu

Chunlei Cao

Xuebin Yang

Xiaofeng Liu

Ye Wu

Xiaowen Zhang

Jiacheng Wang

Hongyun Wang

Zhangyong Ma

Yongfeng Zhong

Yujun Chen

Yuchen Yuan

Ming Sun

Jiansong Tian

Manmohan Chandrakar

Keping Cao

Shichao Zhao

Chaozong Chen

Jiangfan Deng

The present disclosure relates to a backlight module, a display module and an assembling method thereof. The backlight module includes: a backplane; a fixing member fixedly connected to the backplane; and an insertion clamp including a mounting portion fixedly connected to the fixing member, and a clamping portion for clamping to a circuit board inserted between the fixing member and the insertion clamp.

Backlight module including fixing member, display module and assembling method thereof

Backlight module, display module and assembling method thereof

A method and an apparatus for generating vehicle damage information are provided. The method includes: acquiring a to-be-processed vehicle image; for a target detection model in at least one pre-trained target detection model: inputting the vehicle image to the target detection model to generate a suspected damage area detection result; and determining a location of a suspected damage area in the vehicle image based on the generated suspected damage area detection result. A mechanism for detecting a suspected damage area is provided based on the target detection model, improving the vehicle damage assessment efficiency.

Method and apparatus for generating vehicle damage information

A method and an apparatus for generating vehicle damage information are provided. The method includes: acquiring a damage area image of a target vehicle; performing image segmentation on the damage area image to obtain a first suspected damage area; inputting the damage area image to a pre-trained detection model to obtain a second suspected damage area, the detection model being configured to detect a location of the suspected damage area in the image; determining a damage image feature based on the first suspected damage area and the second suspected damage area; and inputting the damage image feature to a pre-trained classification model to generate a damage type, the classification model being configured to characterize a corresponding relationship between the image feature and the damage type.

Provided are a measuring method and apparatus for a damaged part of a vehicle includes: acquiring an image to be processed of a vehicle; acquiring the damaged part of the vehicle in the image to be processed according to the image to be processed; acquiring first position information of key points in the image to be processed according to the image to be processed; determining a transformation relation between the image to be processed and a first fitting plane according to the key points included in the image to be processed and the first position information, where the first fitting plane is a fitting plane determined according to the key points included in the image to be processed on the 3D model; acquiring a projection area of the damaged part in the first fitting plane according to the transformation relation; and measuring the projection area to acquire a measuring result.

Measuring method and apparatus for damaged part of vehicle

The present disclosure provides a method and apparatus for training a fine-grained image recognition model, a device and a storage medium. The method comprises: obtaining images as training samples, and respectively obtaining a tag corresponding to each image, the tag including a class to which the image belongs; training according to the training samples and corresponding tags to obtain a fine-grained image recognition model, and performing constraint at a feature level from two dimensions, namely, the class and object parts, during the training, so that the fine-grained image recognition model learns key object parts in the images; upon performing the fine-grained image recognition, inputting a to-be-recognized image to the fine-grained image recognition model, so that the fine-grained image recognition model positions key object parts in the image, and completes fine-grained image classification according to the key object parts, and outputs a classification result. The solution of the present disclosure can be applied to save manpower costs and improve the model training efficiency.

Method and apparatus for training fine-grained image recognition model, fine-grained image recognition method and apparatus, and storage mediums

The present disclosure provides a method and apparatus for recognizing video fine granularity, a computer device and a storage medium, wherein the method comprises: performing sampling processing for video to be recognized to obtain n frames of images, n being a positive integer larger than one; respectively obtaining a feature graph of each frame of image, and determining a summary feature according to respective feature graphs; determining a fine granularity recognition result of a target in the video according to the summary feature. The solution of the present disclosure may be applied to enhance the accuracy of recognition result.

Method and apparatus for recognizing video fine granularity, computer device and storage medium

Embodiments of a Generation Node-B (gNB) and methods of communication are disclosed herein. The gNB may be configured with logical nodes including a gNB central unit (gNB-CU) and a gNB distributed unit (gNB-DU). The gNB-CUmay determine a first precoding matrix and a second precoding matrix for a precoding of one or more data streams for transmission on a plurality of antennas coupled to the gNB-DU. The precoding may be in accordance with a split functionality between the gNB-CU and the gNB-DU that includes: precoding by the gNB-CU with the first precoding matrix, and precoding by the gNB-DU with the second precoding matrix.

Split precoding and split prefiltering between a central unit and a distributed unit of a generation node-B (GNB)

A method of processing signals in a radio processing apparatus of a base station may include obtaining a plurality of aggregated data symbols, wherein each of the plurality of aggregated data symbols corresponds to a receive terminal of a plurality of receive terminals of the base station and is composed of transmitted data symbols from a plurality of transmit terminals; applying a compression filter to the plurality of aggregated data symbols to reduce the plurality of aggregated data symbols into a plurality of isolated data symbols, the compression filter being based on channel estimates between the plurality of receive terminals and the plurality of transmit terminals; and transmitting the plurality of isolated data symbols to a baseband processing apparatus of the base station.

Methods of processing signals, apparatus, and base station

A system and method are provided. The system includes a processor. The processor is configured to generate a response map for an image, using a four stage convolutional structure. The processor is further configured to generate a plurality of landmark points for the image based on the response map, using a shape basis neural network. The processor is additionally configured to generate an optimal shape for the image based on the plurality of landmark points for the image and the response map, using a point deformation neural network. A recognition system configured to identify the image based on the generated optimal shape to generate a recognition result of the image. The processor is also configured to operate a hardware-based machine based on the recognition result.

Deep deformation network for object landmark localization

The present disclosure provides a picture recognition method and apparatus, a computer device and a computer-readable medium. The method comprises: obtaining a to-be-recognized picture; according to the to-be-recognized picture and a pre-trained picture recognition model, acquiring a predicted class tag of the to-be-recognized picture; the pre-trained picture recognition model employs a convolutional neural network model, and the convolutional neural network model comprises at least one layer of kernel pooling layer upgrading a dimensionality of a channel from one dimension to multiple dimensions; recognizing a class of the to-be-recognized picture according to the predicted class tag of the to-be-recognized picture. By recognizing the to-be-recognized picture by using the picture recognition model having the kernel pooling layer, the present disclosure can achieve recognition of picture classes with finer granularities and effectively improve the picture recognition accuracy and efficiency.

Picture recognition method and apparatus, computer device and computer- readable medium

Systems and methods are disclosed for deep learning and classifying images of objects by receiving images of objects for training or classification of the objects; producing fine-grained labels of the objects; providing object images to a multi-class convolutional neural network (CNN) having a softmax layer and a final fully connected layer to explicitly model bipartite-graph labels (BGLs); and optimizing the CNN with global back-propagation.

Fine-grained image classification by exploring bipartite-graph labels

A polishing clamp for clamping a work-piece to be polished and a polishing method using the same. The polishing clamp includes a fixing-block for fixing the work-piece to be polished, a recess formed on an end surface of the fixing-block and having the same shape as the work-piece to be polished, the work-piece able to be embedded in the recess, and when the work-piece is placed in the recess, a polished surface of the work-piece to be polished is flush with the end surface of the fixing-block forming the recess. Since a portion of the work-piece to be polished that does not need polish could be prevented from contacting the polishing apparatus by means of the fixing-block when being polished, the over-wearing may not occur at edges and corners of the work-piece, improving the quality of polishing. This can improve the quality of, e.g., a light guide plate.

Polishing clamp and polishing method using the same

The present invention discloses a light guide and a lighting device with parallel light source. The light guide comprises a body with a light incident side and a light emergent side. The body comprises: a light incident surface; light emergent surfaces; and a light guide surface group provided with a plurality of light guide surfaces and used for guiding at least a part of the rays of light guided into the body via the light incident surface by total reflection, and determine out-emitting positions of the part of the light rays guided by total reflection by the light guide surface group, on the light emergent surfaces, so that the body is formed with bright areas with guided-out rays of light and dark areas without guided-out rays of light on the light emergent surfaces.

Light guide and lighting device with parallel light source

An uplink feedback channel reporting method is disclosed for using the primary and secondary fast feedback channels to efficiently report the channel quality, MIMO feedback, and CQI types of data from a mobile station to a base station. The reporting method reports regular information periodically and non-regular information on demand.

Uplink feedback channel reporting mechanism in wireless systems

Growing community of inventors

Beijing, China

Feng Zhou