Peking University

Huawei Technologies Co., Limited

Shenzhen University

Zte Corporation

Other

Tencent Technology (shenzhen) Company Limited

Future Wei Technologies, Inc.

Ping an Technology (shenzhen) Co., Ltd.

Southern University of Science and Technology

Xi'an Zte New Software Company Limited

Huawei Device Co., Ltd.

Honor Device Co., Ltd.

Huawei Digital Power Technologies Co., Ltd.

Ying Li

Wen Gao

Ge Li

Ronggang Wang

Zhenyu Wang

Shengfu Dong

Hui Zhao

Haizhe Zhong

Dianyuan Fan

Yihao Zhang

Bin Li

Hao Li

Jin Yang

Wenmin Wang

Chi Zhang

Liming Fang

Xiang Wang

Guozhu Long

Xiaojun Zhang

Peng Wu

Tao Xu

Lifu Zhang

Amir H Fazlollahi

Raphael Jean Cendrillon

Ji Wang

Zihuan Chen

Zhengquan Huang

Ke Liu

Qihong Fu

Long Xu

Sanjay Gupta

Kejia Lan

Zhilei Zhao

Huan Xiong

Linzhi Fang

Tao He

Donghao Yu

Mengdi Fan

Peilei Dong

Mingmin Zhen

Dahua Dai

Ruonan Zhang

Zhihao Li

Yuan Zhu

Chunpeng Wang

Hongmeng Song

Liang Han

Changwen Xu

Jianlong Yang

Shiwei Wang

Chengchuan Liang

Zhaoxing Liang

Botian Wang

Shaojian Tang

Wenfeng He

Chen Deng

Lu Ran

Shuangchun Wen

Jianjun Qiu

Qinan Xiong

Yuhai Liang

Yushan Song

Chen Qian

Tianxi Qu

Baoling Sheen

Wenwen Zhao

Genmao Xie

Hai Tang

Shujuan Zhu

Xian Luo

Disclosed are an antenna number change method, apparatus and device, and a storage medium. The antenna number change method, applied to a base station, may include: determining a number of uplink receiving antennas of the base station; determining, based on the number of uplink receiving antennas of the base station and a number of uplink transmitting antennas of a terminal device, whether the number of uplink receiving antennas of the base station is limited; and in response to the number of uplink receiving antennas of the base station being limited, transmitting an antenna number change instruction to the terminal device, the antenna number change instruction is used for instructing the terminal device to change the number of uplink transmitting antennas.

Antenna number change method and apparatus, device, and storage medium

An atmospheric pollution emission control effect evaluation method, device and storage medium, including: carrying out meteorological condition frequency statistics of data collected from meteorological station, obtaining meteorological condition frequency distribution information; obtaining pollutant concentration information, performing pollutant concentration distribution statistics to obtain pollution concentration distribution information and pollution concentration variation information; decomposing effects of meteorological factors and non-meteorological factors according to meteorological condition frequency distribution information, pollution concentration distribution information and pollution concentration variation information, to obtain meteorological and non-meteorological contribution information; constructing source emission control effect evaluation data set according to meteorological condition frequency distribution information, pollution concentration distribution information, meteorological and non-meteorological contribution information. Accordingly, emission control effect can be quantitatively evaluated based on observation data. Emission increasing effect and contribution of meteorological changes to variation of average pollution level can be quantified.

Evaluation method for impact of emission control on air quality, device and storage medium thereof

The present application discloses a cross-media retrieval method based on deep semantic space, which includes a feature generation stage and a semantic space learning stage. In the feature generation stage, a CNN visual feature vector and an LSTM language description vector of an image are generated by simulating a perception process of a person for the image; and topic information about a text is explored by using an LDA topic model, thus extracting an LDA text topic vector. In the semantic space learning phase, a training set image is trained to obtain a four-layer Multi-Sensory Fusion Deep Neural Network, and a training set text is trained to obtain a three-layer text semantic network, respectively. Finally, a test image and a text are respectively mapped to an isomorphic semantic space by using two networks, so as to realize cross-media retrieval. The disclosed method can significantly improve the performance of cross-media retrieval.

Cross-media retrieval method based on deep semantic space

A video action detection method based on a convolutional neural network (CNN) is disclosed in the field of computer vision recognition technologies. A temporal-spatial pyramid pooling layer is added to a network structure, which eliminates limitations on input by a network, speeds up training and detection, and improves performance of video action classification and time location. The disclosed convolutional neural network includes a convolutional layer, a common pooling layer, a temporal-spatial pyramid pooling layer and a full connection layer. The outputs of the convolutional neural network include a category classification output layer and a time localization calculation result output layer. The disclosed method does not require down-sampling to obtain video clips of different durations, but instead utilizes direct input of the whole video at once, improving efficiency. Moreover, the network is trained by using video clips of the same frequency without increasing differences within a category, thus reducing the learning burden of the network, achieving faster model convergence and better detection.

Video action detection method based on convolutional neural network

A method and a device for MCMC framework-based sub-hypergraph matching are provided. Matching of object features is performed by constructing sub-hypergraphs. In a large number of actual images and videos, objects vary constantly, and contain various noise points as well as other interference factors, which makes image object matching and searching very difficult. Perform object feature matching by representing the appearance and positions of objects by sub-hypergraphs allows for faster and more accurate image matching. Furthermore, a sub-hypergraph has several advantages over a graph or a hypergraph: on one hand, a sub-hypergraph has more geometric information (e.g. angle transformation, rotation, scale, etc.) than a graph, and has a lower degree of difficulty and better extensibility than a hypergraph. On the other hand, the disclosed method and device have stronger capabilities to resist interference and good robustness, and are adaptable to more complex settings, especially with outliers.

MCMC framework-based sub-hypergraph matching method and device

An image feature extraction method for person re-identification includes performing person re-identification by means of aligned local descriptor extraction and graded global feature extraction; performing the aligned local descriptor extraction by processing an original image by affine transformation and performing a summation pooling operation on image block features of same regions to obtain an aligned local descriptor; reserving spatial information between inner blocks of the image for the aligned local descriptor; and performing the graded global feature extraction by grading a positioned pedestrian region block and solving a corresponding feature mean value to obtain a global feature. The method can resolve the problem of feature misalignment caused by posture changes of pedestrian, etc., and eliminate the effect of unrelated backgrounds on re-recognition, thus improving the precision and robustness of person re-identification.

Image feature extraction method for person re-identification

The present disclosure relates to a broadband optical parametric chirped pulse amplifier insensitive to temperature comprises the first pulsed laser, the second pulsed laser, a pulse stretcher and a periodically poled nonlinear crystal. Via the proper arrangement of the non-collinear angles between the transmission directions of the signal light, the pump light and the idler light, to simultaneously satisfy the angular relationship required for constructing the non-collinear phase-matching configuration insensitive to wavelength and that required for constructing the non-collinear phase-matching configuration insensitive to temperature, the optical parametric chirped pulse amplifier not only can realize a broadband parametric amplification of the signal light (insensitive to wavelength), but also can effectively alleviate the phase mismatch in nonlinear crystal resulted from the excessively high local temperature (insensitive to temperature).

Broadband optical parametric chirped pulse amplifier insensitive to temperature

A bidirectional image-text retrieval method based on a multi-view joint embedding space includes: performing retrieval with reference to a semantic association relationship at a global level and a local level, obtaining the semantic association relationship at the global level and the local level in a frame-sentence view and a region-phrase view, and obtaining semantic association information in a global level subspace of frame and sentence in the frame-sentence view, obtaining semantic association information in a local level subspace of region and phrase in the region-phrase view, processing data by a dual-branch neural network in the two views to obtain an isomorphic feature and embedding the same in a common space, and using a constraint condition to reserve an original semantic relationship of the data during training, and merging the two semantic association relationships using multi-view merging and sorting to obtain a more accurate semantic similarity between data.

Method of bidirectional image-text retrieval based on multi-view joint embedding space

Disclosed is a deep discriminative network for person re-identification in an image or a video. Concatenation are carried out on different input images on a color channel by constructing a deep discriminative network, and an obtained splicing result is defined as an original difference space of different images. The original difference space is sent into a convolutional network. The network outputs the similarity between two input images by learning difference information in the original difference space, thereby realizing person re-identification. The features of an individual image are not learnt, and concatenation are carried out on input images on a color channel at the beginning, and difference information is learnt on an original space of the images by using a designed network. By introducing an Inception module and embedding the same into a model, the learning ability of a network can be improved, and a better differentiation effect can be achieved.

Method of using deep discriminate network model for person re-identification in image or video

Disclosed is a method for detecting pedestrians in an image by using Gaussian penalty. Initial pedestrian boundary box is screened using a Gaussian penalty, to improve the pedestrian detection performance, especially sheltered pedestrians in an image. The method includes acquiring a training data set, a test data set and pedestrian labels of a pedestrian detection image; using the training data set for training to obtain a detection model by using a pedestrian detection method, and acquiring initial pedestrian boundary box and confidence degrees and coordinates thereof; performing Gaussian penalty on the confidence degrees of the pedestrian boundary box, to obtain confidence degree of the pedestrian boundary box after the penalty; and obtaining final pedestrian boundary boxes by screening the pedestrian boundary boxes. Thus, repeated boundary boxes of a single pedestrian are removed while reserving boundary boxes of sheltered pedestrians, thereby realizing the detection of the pedestrians in an image.

Method for detecting pedestrians in image by using Gaussian penalty

The present invention belongs to the technical field of lasers and provides a dual-chirped spectral optical parametric amplifier and an amplification method. A femtosecond laser assembly is configured to generate simultaneous pump and signal waves which successively pass through an input grating and an input collimator respectively. The various spectrum components of both the pump and the signal waves linearly disperse and focus on respective focal points, and present spatial chirps with opposite frequency gradients in the respective focal planes. A full-spectrum optical parametric amplification of the signal wave with the pump wave is performed via a fan-out periodically poled crystal, resulting an ultrabroad idler wave. The ultrabroad idler wave is separated from the hybrid waves via an optical splitter, and then passes successively through an output collimator and an output grating, and is Fourier transformed from frequency domain to temporal domain. An ultra-short pulsed laser with a long wavelength can be obtained eventually after a necessary dispersion compensation. The present invention provides a simple-structured optical parametric amplifier so as to obtain an ultra-short pulsed laser with a long wavelength.

Dual-chirped spectral optical parametric amplifier and amplification method

A Collaborative Deep Network model method for pedestrian detection includes constructing a new collaborative multi-model learning framework to complete a classification process during pedestrian detection; and using an artificial neuron network to integrate judgment results of sub-classifiers in a collaborative model, and training the network by means of the method for machine learning, so that information fed back by sub-classifiers can be more effectively synthesized. A re-sampling method based on a K-means clustering algorithm can enhance the classification effect of each classifier in the collaborative model, and thus improves the overall classification effect. By building a collaborative deep network model, different types of training data sets obtained using a clustering algorithm are used for training a plurality of deep network models in parallel, and then classification results, on deep network models, of an original data set are integrated and comprehensively analyzed, which achieves more accurate sample classification.

Collaborative deep network model method for pedestrian detection

A cross-media search method using a VGG convolutional neural network (VGG net) to extract image features. The 4096-dimensional feature of a seventh fully-connected layer (fc7) in the VGG net, after processing by a ReLU activation function, serves as image features. A Fisher Vector based on Word2vec is utilized to extract text features. Semantic matching is performed on heterogeneous images and the text features by means of logistic regression. A correlation between the two heterogeneous features, which are images and text, is found by means of semantic matching based on logistic regression, and thus cross-media search is achieved. The feature extraction method can effectively indicate deep semantics of image and text, improve cross-media search accuracy, and thus greatly improve the cross-media search effect.

Cross-media search method

A method for image matching includes acquiring a template image and a target image; acquiring a group of template features according to the template image; extracting a group of target features according to the target image; and according to template features and target features, calculating an degree of image similarity between the template image and each frame of target images, and using a target image with the maximum degree of image similarity as a matched image to the template image. In the image-matching method, image matching is performed by calculating an degree of image similarity between a template image and each target image according to a degree of image similarity between template features and target features, so that non-redundancy of features in an image matching process and correct image matching can be guaranteed, and the image matching accuracy can be improved.

Method and a device for image matching

An image representation method and processing device based on local PCA whitening. A first mapping module maps words and characteristics to a high-dimension space. A principal component analysis module conducts principal component analysis in each corresponding word space, to obtain a projection matrix. A VLAD computation module computes a VLAD image representation vector; a second mapping module maps the VLAD image representation vector to the high-dimension space. A projection transformation module conducts projection transformation on the VLAD image representation vector obtained by means of projection. A normalization processing module conducts normalization on characteristics obtained by means of projection transformation, to obtain a final image representation vector. An obtained image representation vector is projected to a high-dimension space first, then projection transformation is conducted on a projection matrix computed in advance and vectors corresponding to words, to obtain a low-dimension vector; and in this way, the vectors corresponding to the words are consistent. The disclosed method and the processing device can obtain better robustness and higher performance.

Image representation method and processing device based on local PCA whitening

Growing community of inventors

Shenzhen, China

Ying Li