Microsoft Technology Licensing, LLC

Beijing Sensetime Technology Development Co., Ltd.

Huawei Technologies Co., Limited

The Chinese University of Hong Kong

Microsoft Corporation

Shenzhen Sensetime Technology Co., Ltd.

Sensetime Group Limited

Xiaoou Tang

Zhouchen Lin

Qiong Yang

Jian Qiao Sun

Heung-Yeung Shum

Xiaogang Wang

Ping Luo

Weiwei Zhang

Rong Xiao

Chen Change Loy

Deli Zhao

Fang Wen

Qiang Wang

Yasuyuki Matsushita

Ziwei Liu

Jian Wang

Sing Bing Kang

Yue Zhao

Qi Yin

Lifeng Wang

Jianping Shi

David Patrick Vronay

Xiaoxiao Li

Chunjing Xu

Dahua Lin

Yu Qiao

Wei Zhang

Wei Li

Zhe Wang

Ying Li

Li Erran Li

Xu Yang

Kai Chen

Takaaki Shiratori

Jian Sun

Jianzhuang Liu

Yi Sun

Chaochao Lu

Limin Wang

Ta Bao

Leizhong Zhang

Guangcan Liu

Shi Qiu

Zhenyao Zhu

Yin Li

Zhirong Wu

Chen Huang

Wenqi Ju

Yi Deng

Junfeng He

Rongrong Wang

Eric Picard

Chao Wang

Zhongfu Ye

Yuanjun Xiong

Chao Dong

Tak Wai Hui

Dian Shao

Zhanpeng Zhang

Kam Fai Wong

Kwok Yiu Leung

Yu Xiong

Hoi Chung Chu

Ying Fai Ho

Yunbo Wang

Michael Hurt

Yining Li

Xuan Yu

Tian Fang

Francois Alter

Xiaohang Zhan

Xingang Pan

Tie Liu

Dian Gong

Hong-Wen Kang

Qingqiu Huang

Yuankai Qi

Xueyin Lin

A semantic segmentation model training method includes: performing, by a semantic segmentation model, image semantic segmentation on at least one unlabeled image to obtain a preliminary semantic segmentation result as the category of the unlabeled image; obtaining, by a convolutional neural network based on the category of the at least one unlabeled image and the category of at least one labeled image, sub-images respectively corresponding to the at least two images and features corresponding to the sub-images, where the at least two images comprise the at least one unlabeled image and the at least one labeled image, and the at least two sub-images carry the categories of the corresponding images; and training the semantic segmentation model on the basis of the categories of the at least two sub-images and feature distances between the at least two sub-images.

Semantic segmentation model training methods and apparatuses, electronic devices, and storage media

A method and an apparatus for segmenting a video object, an electronic device, a storage medium, and a program include: performing, among at least some frames of a video, inter-frame transfer of an object segmentation result of a reference frame in sequence from the reference frame, to obtain an object segmentation result of at least one other frame among the at least some frames; determining other frames having lost objects with respect to the object segmentation result of the reference frame among the at least some frames; using the determined other frames as target frames to segment the lost objects, so as to update the object segmentation results of the target frames; and transferring the updated object segmentation results of the target frames to the at least one other frame in the video in sequence. The accuracy of video object segmentation results can therefore be improved.

Method and apparatus for segmenting video object, electronic device, and storage medium

An image disambiguation method includes: performing image feature extraction and semantic recognition on at least two images in an image set including similar targets to obtain N K-dimensional semantic feature probability vectors, where the image set includes N images, N and K are both positive integers, and N is greater than or equal to 2; determining a differential feature combination according to the N K-dimensional semantic feature probability vectors, the differential feature combination indicating a difference between the similar targets in the at least two images in the image set; and generating a natural language for representing or prompting the difference between the similar targets in the at least two images in the image set according to the differential feature combination and image features of the at least two images in the image set.

Image disambiguation method and apparatus, storage medium, and electronic device

The present disclosure relates to a method and device for video processing, an electronic device, and a storage medium. The method comprises: determining, on the basis of paragraph information of a query text paragraph and video information of multiple videos in a video library, preselected videos associated with the query text paragraph in the multiple videos; and determining a target video in the preselected videos on the basis of video frame information of the preselected videos and of sentence information of the query text paragraph. The method for video processing of the embodiments of the present disclosure indexes videos by means of the relevance between the videos and the query text paragraph, allows the pinpointing of the target video, avoids search result redundancy, allows the processing of the query text paragraph in a natural language form, and is not limited by the inherent contents of content labels.

Method and device for video processing, electronic device, and storage medium

A method and device for image recognition and a storage medium are provided. The method includes: a target image is acquired; feature extraction processing is performed on the target image through convolutional layers in a neural network model to obtain feature maps, and Instance Normalization (IN) and Batch Normalization (BN) processing is performed on the feature maps to obtain a recognition result of the target image; and the recognition result of the target image is output.

Method and device for image processing, and computer storage medium

Time domain action detecting methods and systems, electronic devices, and computer storage medium are provided. The method includes: obtaining a time domain interval in a video with an action instance and at least one adjacent segment in the time domain interval; separately extracting action features of at least two video segments in candidate segments, where the candidate segments comprises video segment corresponding to the time domain interval and adjacent segments thereof; pooling the action features of the at least two video segments in the candidate segments, to obtain a global feature of the video segment corresponding to the time domain interval; and determining, based on the global feature, an action integrity score of the video segment corresponding to the time domain interval. The embodiments of the present disclosure benefit accurately determining whether a time domain interval comprises an integral action instance, and improve the accuracy rate of action integrity identification.

Time domain action detecting methods and system, electronic devices, and computer storage medium

A method and system for processing an image operates by: filtering a first real image to obtain a first feature map therefor with performances of image features improved; upscaling the obtained first feature map to improve a resolution thereof, the feature map with improved resolution forming a second feature map; and constructing, from the second feature map, a second real image having enhanced performances and a higher resolution than that of the first real image.

Convolution deconvolution neural network method and system

Disclosed is a method for generating a semantic image labeling model, comprising: forming a first CNN and a second CNN, respectively; randomly initializing the first CNN; inputting a raw image and predetermined label ground truth annotations to the first CNN to iteratively update weights thereof so that a category label probability for the image, which is output from the first CNN, approaches the predetermined label ground truth annotations; randomly initializing the second CNN; inputting the category label probability to the second CNN to correct the input category label probability so as to determine classification errors of the category label probabilities; updating the second CNN by back-propagating the classification errors; concatenating the updated first and second CNNs; classifying each pixel in the raw image into one of general object categories; and back-propagating classification errors through the concatenated CNN to update weights thereof until the classification errors less than a predetermined threshold.

Apparatuses and methods for semantic image labeling

A method for identifying social relation of persons in an image, including: generating face regions for faces of the persons in the image; determining at least one spatial cue for each of the faces; extracting features related to social relation for each face from the face regions; determining a shared facial feature from the extracted features and the determined spatial cue, the determined feature being shared by multiple the social relation inferences; and predicting the social relation of the persons from the shared facial feature.

Methods and systems for social relation identification

The present disclosure relates to an image re-ranking method, which includes: performing image searching by using an initial keyword, obtaining, by calculation, an anchor concept set of a search result according to the search result corresponding to the initial keyword, obtaining, by calculation, a weight of a correlation between anchor concepts in the anchor concept set, and forming an anchor concept graph ACG by using the anchor concepts in the anchor concept set as vertexes and the weight of the correlation between anchor concepts as a weight of a side between the vertexes; acquiring a positive training sample by using the anchor concepts, and training a classifier by using the positive training sample; obtaining a concept projection vector by using the ACG and the classifier; calculating an ACG distance between images in the search result corresponding to the initial keyword; and ranking the images according to the ACG distance.

Image Re-ranking method and apparatus

A method for verifying facial data and a corresponding system, which comprises retrieving a plurality of source-domain datasets from a first database and a target-domain dataset from a second database different from the first database; determining a latent subspace matching with target-domain dataset best and a posterior distribution for the determined latent subspace from the target-domain dataset and the source-domain datasets; determining information shared between the target-domain data and the source-domain datasets; and establishing a Multi-Task learning model from the posterior distribution P and the shared information M on the target-domain dataset and the source-domain datasets.

Method and a system for verifying facial data

A visual semantic complex network system and a method for generating the system have been disclosed. The system may comprise a collection device configured to retrieve a plurality of images and a plurality of texts associated with the images in accordance with given query keywords; a semantic concept determination device configured to determine semantic concepts of the retrieved images and retrieved texts for the retrieved images, respectively; a descriptor generation device configured to, from the retrieved images and texts, generate text descriptors and visual descriptors for the determined semantic concepts; and a semantic correlation device configured to determine semantic correlations and visual correlations from the generated text and visual descriptor, respectively, and to combine the determined semantic correlations and the determined visual correlations to generate the visual semantic complex network system.

Visual semantic complex network and method for forming network

Disclosed is an apparatus for face verification. The apparatus may comprise a feature extraction unit and a verification unit. In one embodiment, the feature extraction unit comprises a plurality of convolutional feature extraction systems trained with different face training set, wherein each of systems comprises: a plurality of cascaded convolutional, pooling, locally-connected, and fully-connected feature extraction units configured to extract facial features for face verification from face regions of face images; wherein an output unit of the unit cascade, which could be a fully-connected unit in one embodiment of the present application, is connected to at least one of previous convolutional, pooling, locally-connected, or fully-connected units, and is configured to extract facial features (referred to as deep identification-verification features or DeepID2) for face verification from the facial features in the connected units. The verification unit may be configured to compare the obtained DeepID2 extracted from two face images to be compared to determine if the two face images are from the same identity or not.

Method and a system for face verification

Disclosed herein are a system and method for verifying face images based on canonical images. The method includes: retrieving, from a plurality of face images of an identity, a face image with a smallest frontal measurement value as a representative image of the identity; determining parameters of an image reconstruction network based on mappings between the retrieved representative image and the plurality of face images of the identity; reconstructing, by the image reconstruction network with the determined parameters, at least two input face images into corresponding canonical images respectively; and comparing the reconstructed canonical images to verify whether they belong to a same identity, where the representative image is a frontal image and the frontal measurement value represents symmetry of each face image and sharpness of the image. Thus, canonical face images can be reconstructed using only 2D information from face images under an arbitrary pose and lighting condition.

Methods and systems for verifying face images based on canonical images

A video classification method and apparatus relate to the field of electronic and information technologies, so that precision of video classification can be improved. The method includes: segmenting a video in a sample video library according to a time sequence, to obtain a segmentation result, and generating a motion atom set; generating, by using the motion atom set and the segmentation result, a motion phrase set that can indicate a complex motion pattern, and generating a descriptive vector, based on the motion phrase set, of the video in the sample video library; and determining, by using the descriptive vector, a to-be-detected video whose category is the same as that of the video in the sample video library. The method is applicable to a scenario of video classification.

Video classification method and apparatus

Growing community of inventors

Beijing, China

Xiaoou Tang