Abstract: Methods and apparatuses for video-based facial recognition, devices, media, and programs can include: forming a face sequence for face images, in a video, appearing in multiple continuous video frames and having positions in the multiple video frames meeting a predetermined displacement requirement, wherein the face sequence is a set of face images of a same person in the multiple video frames; and performing facial recognition for the face sequence by using a preset face library at least according to face features in the face sequence.

Abstract: Body contour key point detection methods, image processing methods, neural network training methods, apparatuses, electronic devices, computer-readable storage media, and computer programs include: obtaining an image feature of an image block including a body; obtaining a body contour key point prediction result of the body by means of a first neural network according to the image feature; and obtaining a body contour key point in the image block according to the body contour key point prediction result; where the body contour key point is used for representing an outer contour of the body.

Abstract: Image processing methods, apparatuses, and electronic devices include: extracting features of an image to be processed to obtain a first feature map of the image; generating an attention map of the image based on the first feature map; fusing the attention map and the first feature map to obtain a fusion map; and extracting the features of the image again based on the fusion map. The implementation mode introduces an attention mechanism into image processing, and effectively improves the efficiency of acquiring information from an image.

Abstract: A method for determining hand three-dimensional data includes: obtaining a first hand image and a second hand image captured by a binocular photographing system; identifying, from each of the first hand image and the second hand image, at least one key point and a region profile covering the at least one key point; determining depth information of the at least one key point and depth information of the region profile according to a photographing parameter of the binocular photographing system, the at least one key point and the region profile identified from the first hand image, and the at least one key point and the region profile identified from the second hand image; and determining hand three-dimensional data according to the at least one key point and the depth information of the at least one key point together with the region profile and the depth information of the region profile.

Abstract: Methods, apparatuses and electronic devices for identifying an object category include: determining M key point neighborhood regions from corresponding object candidate boxes according to position information of M key points in a plurality of object candidate boxes of an image to be detected, where M is less than or equal to the total number of key points of N preset object categories, and M and N are positive integers; and determining category information of at least one object in the image to be detected using a convolutional neural network model used for identifying an object category in the image according to the M key point neighborhood regions.

Abstract: A method and an apparatus for detecting an object keypoint, an electronic device, a computer readable storage medium, and a computer program include: obtaining a respective feature map of at least one local regional proposal box of an image to be detected, the at least one local regional proposal box corresponding to at least one target object; and separately performing target object keypoint detection on a corresponding local regional proposal box of the image to be detected according to the feature map of the at least one local regional proposal box.

Abstract: Methods and apparatuses for dynamically adding facial images into a database, electronic devices, media and programs include: comparing an obtained first facial image with pre-stored facial image information in an image database; and in response to a comparison result indicating that the first facial image has no matched pre-stored facial image information in the image database, determining whether to store at least one of the first facial image and feature information of the first facial image in the image database. Control of dynamically adding facial images into the database can therefore be achieved.

Abstract: Methods and apparatuses for face image deduplication as well as non-transitory computer-readable storage medium include: filtering a plurality of obtained first face images to obtain at least one second face image with image quality reaching a first preset condition; matching the second face image with at least one third face image in an image queue to obtain a matching result; and determining, according to the matching result, whether to perform deduplication operation on the second face image.

Abstract: A method and an apparatus for recognizing and training a video, an electronic device and a storage medium include: extracting features of a first key frame in a video; performing fusion on the features of the first key frame and fusion features of a second key frame in the video to obtain fusion features of the first key frame, where a detection sequence of the second key frame in the video precedes that of the first key frame; and performing detection on the first key frame according to the fusion features of the first key frame to obtain an object detection result of the first key frame. Through iterative multi-frame feature fusion, information contained in shared features of these key frames in the video can be enhanced, thereby improving frame recognition accuracy and video recognition efficiency.

Abstract: A method for scene parsing includes: performing a convolution operation on a to-be-parsed image by using a deep neural network to obtain a first feature map, the first feature map including features of at least one pixel in the image; performing a pooling operation on the first feature map to obtain at least one second feature map, a size of the second feature map being less than that of the first feature map; and performing scene parsing on the image according to the first feature map and the at least one second feature map to obtain a scene parsing result of the image, the scene parsing result including a category of the at least one pixel in the image. A system for scene parsing and a non-transitory computer-readable storage medium can facilitate realizing the method.

Abstract: A method for data transmission includes: determining first data to be sent by a node in a distributed system to at least one other node and configured to perform parameter update on a deep learning model trained by the distributed system; performing sparse processing on at least some data in the first data; and sending the at least some data on which sparse processing is performed in the first data to the at least one other node. A system for data transmission and an electronic device are also provided.

Abstract: A method and an apparatus for extracting a user attribute, and an electronic device include: receiving image data sent by a second terminal; extracting user attribute information based on the image data; and determining a target service object corresponding to the user attribute information. Current biological images of the user are obtained in real time; it is easy and convenient; authenticity of the user attribute information may be ensured; the target service object is determined by means of the user attribute information, which is more in line with current demands of the user.

Abstract: An object detection method, a neural network training method, an apparatus, and an electronic device include: obtaining, through prediction, multiple fused feature graphs from images to be processed, through a deep convolution neural network for target region frame detection, obtaining multiple first feature graphs from a first subnet having at least one lower sampling layer, obtaining multiple second feature graphs from a second subnet having at least one upper sampling layer, and obtaining fused graph by fusing multiple first feature graphs and multiple second feature graphs respectively; and obtaining target region frame data according to the multiple fused feature graphs. Because the fused feature graphs better represent semantic features on high levels and detail features on low levels in images, target region frame data of big and small objects in images can be effectively extracted according to the fused feature graphs, thereby improving accuracy and robustness of object detection.

Abstract: A method and an apparatus for recommending a business object, an electronic device, and a storage medium include: obtaining audience attribute information and business object attribute information; determining whether to display the business object according to the audience attribute information and the business object attribute information; and displaying, when determining to display the business object, the business object. By means of audience attribute information, a business object matching the audience can be determined from a business object library, and the business object is more in line with viewing interests of the audience; moreover, different business objects can be pushed to different audiences, so that the correctness and flexibility for pushing business objects are improved.

Abstract: 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.

Abstract: 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.

Abstract: Embodiments of the present disclosure disclose communication methods and systems, electronic devices, and computer clusters. The method includes: separately creating a corresponding thread for at least one of a plurality of target devices, where the created thread corresponding to the target device includes a communication thread and a message processing thread, and the message processing thread includes a message sending thread and/or a message receiving thread; and communicating with a corresponding target device on the basis of the corresponding created thread.

Abstract: 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.

Abstract: A method and an apparatus for facial age identification, an electronic device, and a computer readable medium include: obtaining estimated facial age of a person in an image to be identified; selecting N image samples from an image sample set of known age according to the estimated facial age and age of two or more preset age gaps with the estimated facial age, the N being not less than 2; obtaining a comparison result of ages between the image to be identified and the selected N image samples; and obtaining probability information for determining a person's facial age attribute information according to statistical information formed by the comparison result.

Abstract: 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.