Tencent Technology (shenzhen) Company Limited

Tencent Technology Company Limited

Wenhan Luo

Yan Zhang

Lin Ma

Kaihao Zhang

Hao Wang

Xiaolong Zhu

Wei Liu

Haozhi Huang

Peng Yang

Wenhao Jiang

Yaodong Wang

Zhenfang Chen

Yuan Gao

Linchao Bao

Hongdong Li

This application discloses a video clip positioning method performed at a computer device. In this application, the computer device acquires a plurality of video frame features of a target video and a text feature of a target text using a video recognition model to determine a candidate clip that can be matched with the target text. The candidate clip is finely divided based on a degree of matching between a video frame in the candidate clip and the target text to acquire a plurality of sub-clips, and a sub-clip that has the highest degree of matching with the target text is used as a target video clip. According to this application, the video recognition model does not need to learn a boundary feature of the target video clip, and during model training, or precisely label a sample video, thereby shortening a training period of the video recognition model.

Video clip positioning method and apparatus, computer device, and storage medium

Embodiments of this application disclose a microexpression-based image recognition method and apparatus, and a related device. The method includes: obtaining an original expression image belonging to a first expression type, and inputting the original expression image into an image augmentation model; the original expression image belonging to the first expression type being an image including a microexpression; the image augmentation model being obtained by training with a sample expression image belonging to the first expression type and a sample expression images belonging to a second expression type; augmenting, in the image augmentation model, an expression feature of the microexpression in the original expression image to obtain a target expression image belonging to the second expression type; recognizing an expression attribute type corresponding to the target expression image, and determining the expression attribute type corresponding to the target expression image as an expression attribute type corresponding to the original expression image.

Microexpression-based image recognition method and apparatus, and related device

This application discloses a video sequence selection method, applicable to a computer device, the method including: receiving a to-be-matched video and a to-be-matched text, the to-be-matched text having a to-be-matched text feature sequence; invoking a spatiotemporal candidate region generator to extract a spatiotemporal candidate region set from the to-be-matched video, the spatiotemporal candidate region set including N spatiotemporal candidate regions; performing feature extraction on each spatiotemporal candidate region by using a convolutional neural network, to obtain N to-be-matched video feature sequences; invoking an attention-based interactor to obtain a matching score corresponding to each spatiotemporal candidate region, the matching score being used for representing a matching relationship between the spatiotemporal candidate region and the to-be-matched text; and selecting a target spatiotemporal candidate region from the spatiotemporal candidate region set according to the matching score corresponding to each spatiotemporal candidate region, and outputting the target spatiotemporal candidate region. In this application, an association between the video and the text in time sequence is considered during matching, thereby increasing a degree of matching between a video sequence and the text.

Video sequence selection method, computer device, and storage medium

The present disclosure describes methods, devices, and storage medium for generating a time-lapse photography video with a neural network model. The method includes obtaining a training sample. The training sample includes a training video and an image set. The method includes obtaining through training according to the training sample, a neural network model to satisfy a training ending condition, the neural network model comprising a basic network and an optimization network, by using the image set as an input to the basic network, the basic network being a first generative adversarial network for performing content modeling, generating a basic time-lapse photography video as an output of the basic network, using the basic time-lapse photography video as an input to the optimization network, the optimization network being a second generative adversarial network for performing motion state modeling, and generating an optimized time-lapse photography video as an output of the optimization network.

Neural network model training method and device, and time-lapse photography video generating method and device

An image processing method comprises training an initial network to obtain a first network. The method also comprises training the first network to obtain a second network. The method also comprises training the second network to obtain a third network. The method also comprises processing an original image according to the third network in response to receiving an image processing instruction, to obtain a plurality of target images from the original image.

Image processing method and apparatus, computer device, and storage medium

Embodiments of this application provide a living body detection method that can include traversing a plurality of images of a to-be-detected object, and using a currently traversed image as a current image, performing face feature extraction on the current image to obtain an eigenvector corresponding to the current image, the eigenvector describing a structure of a face feature of the object in the current image. The method can further include capturing an action behavior of the to-be-detected object according to a change of the eigenvector corresponding to the current image relative to an eigenvector corresponding to a historical image in a feature sequence, the historical image being a traversed image in the plurality of images, and the feature sequence including an eigenvector corresponding to at least one historical image, and determining the to-be-detected object as a living body in response to capturing the action behavior of the object.

Living body detection method and apparatus, electronic device, storage medium, and related system to which living body detection method is applied

A method of video deblurring by an electronic device is described. The processing circuitry of the electronic device acquires N continuous image frames from a video clip the N being a positive integer, and the N continuous image frames including a blurry image frame to be processed. The processing circuitry of the electronic device performs three-dimensional (3D) convolution processing on the N continuous image frames with a generative adversarial network model, to acquire spatio-temporal information corresponding to the blurry image frame. The spatio-temporal information includes spatial feature information of the blurry image frame, and temporal feature information between the blurry image frame and a neighboring image frame of the N continuous image frames The processing circuitry of the electronic device performs deblurring processing on the blurry image frame by using the spatio-temporal information corresponding to the blurry image frame through the generative adversarial network model, to output a sharp image frame.

Video deblurring method and apparatus, storage medium, and electronic apparatus

A method, apparatus, and storage medium for training a neural network model used for image processing are described. The method includes: obtaining a plurality of video frames; inputting the plurality of video frames through a neural network model so that the neural network model outputs intermediate images; obtaining optical flow information between an early video frame and a later video frame; modifying an intermediate image corresponding to the early video frame according to the optical flow information to obtain an expected-intermediate image; determining a time loss between an intermediate image corresponding to the later video frame and the expected-intermediate image; determining a feature loss between the intermediate images and a target feature image; and training the neural network model according to the time loss and the feature loss, and returning to obtaining a plurality of video frames continue training until the neural network model satisfies a training finishing condition.

Method and apparatus for training neural network model used for image processing, and storage medium

Exemplary embodiments of this disclosure provide a living body detection method and apparatus, an electronic device, a storage medium, and a payment system, a video surveillance system, and an access system to which the living body detection method is applied, and generally belong to the field of biometric recognition technologies. The living body detection method can include obtaining an image of a to-be-detected object performing key point detection on a biometric feature corresponding to the to-be-detected object in the image, and constructing a constraint box in the image according to detected key points. Further, the method can include capturing a shape change of the constraint box constructed in the image, and determining the to-be-detected object as a prosthesis in response to capturing an abnormal deformation of the constraint box or detecting no key points.

An image recognition method is provided, including: obtaining a target video including a target object; extracting a target video frame image from the target video; generating a key point video frame sequence comprised of a plurality of key point video frames according to key point information of the object and a plurality of video frames in the target video; extracting dynamic timing feature information of the key point video frame sequence; extracting static structural feature information of the target video frame image; and recognizing an attribute type corresponding to the target object in the target video according to the dynamic timing feature information of the key point video frame sequence and the static structural feature information of the target video frame image.

Image recognition method and apparatus, terminal, and storage medium

Provided is a video processing method, including: obtaining a to-be-processed video and generating a first gait energy diagram, the to-be-processed video including an object with a to-be-recognized identity; obtaining a second gait energy diagram, the second gait energy diagram being generated based on a video including an object with a known identity; inputting the first gait energy diagram and the second gait energy diagram into a deep neural network; extracting respective identity information of the first gait energy diagram and the second gait energy diagram, and determining a fused gait feature vector from gait feature vectors of the first gait energy diagram and the second gait energy diagram; and calculating a similarity based on at least the fused gait feature vector. The identity information of the first gait energy diagram includes gait feature vectors, and the identity information of the second gait energy diagram includes gait feature vectors.

Media processing method, related apparatus, and storage medium

This application discloses a method of generating a negative sample for face recognition performed at a computer device. The method includes: obtaining a positive sample of a face from a training sample library required for machine learning of face recognition; embedding the obtained positive sample in a selected negative sample template, to obtain an intermediate sample of the face that simulates displaying of the positive sample in a display region of the negative sample template; and fusing the intermediate sample in a selected scenario sample, to obtain a negative sample of the face required for machine learning of face recognition.

Method and apparatus for generating negative sample of face recognition, and computer device

Aspects of the disclosure provide an apparatus for target tracking including processing circuitry that obtains a plurality of target instances according to a target detection on image data. Each of the plurality of target instances corresponds to one of a plurality of tracked targets. The processing circuitry determines a plurality of trajectory segments, each of which indicates a trajectory of a subset of the target instances corresponding to a same tracked target. The processing circuitry determines feature information of the plurality of trajectory segments. The processing circuitry performs clustering on specified trajectory segments of the plurality of trajectory segments according to the feature information of the specified trajectory segments, to obtain a type distribution of the specified trajectory segments. The processing circuitry determines, according to the type distribution of the specified trajectory segments, a target tracking result including a same type of the specified trajectory segments.

Growing community of inventors

Shenzhen, China

Wenhan Luo