Tencent Technology (shenzhen) Company Limited

Shenzhen Goodix Technology Co., Ltd.

Tencent Technology Company Limited

Xinliang Wang

Bin Li

Jun Liu

Jingchang Chen

Tieming Huang

Mengran Lin

Jingcong Chen

A face detection method for a computer device includes: obtaining a to-be-detected image; obtaining an initial shape of a current regression tree in a pre-constructed probability regression model; extracting image features from the to-be-detected image and respectively calculating a probability of each of leaf nodes of the current regression tree according to the image features; extracting an error of each of the leaf nodes; determining a shape error of the current regression tree according to the probability and the error of each of the leaf nodes; calculating an estimated shape of the current regression tree according to the initial shape and the shape error; and performing iterative calculation by using the estimated shape as an initial shape of a neighboring next regression tree until a last regression tree in the probability regression model, to obtain an estimated shape of the last regression tree as a detected face shape.

Face detection method and apparatus, computer device, and storage medium

This application relates to a voice encoding and sending method performed at a mobile terminal that is communicatively connected to a plurality of mobile terminals via a computer server. The method includes sending voice data to the plurality of mobile terminals; receiving, from one or more of the plurality of mobile terminals, one or more paths of Real-Time Transport Control Protocol (RTCP) packets based on the voice data received by the one or more mobile terminals; parsing the one or more paths of RTCP packets and generating current network status information from the RTCP packets; adjusting a quality of service (QoS) parameter according to the current network status information; and encoding and sending new voice data according to the adjusted QoS parameter.

Voice encoding and sending method and apparatus

This application provides a facial animation implementation method performed at a computing device. The method includes: capturing a facial image; extracting facial feature points in the facial image; comparing the facial feature points with standard feature points, to obtain a first deformation coefficient corresponding to a geometrical feature; extracting a local region according to the facial feature points for processing, to obtain a second deformation coefficient corresponding to an appearance feature; and driving a three-dimensional virtual object according to the first deformation coefficient and the second deformation coefficient to perform a corresponding expression.

Facial animation implementation method, computer device, and storage medium

In a method for facial feature point tracking, facial feature points of a face in a previous image of a to-be-tracked image are acquired in an image sequence. Facial feature point errors between the to-be-tracked image and the previous image are determined based on a preset error model and pixels in the to-be-tracked image. The facial feature point errors indicate differences between first coordinates of facial feature points in the to-be-tracked image, and second coordinates of facial feature points at corresponding positions in the previous image. The preset error model is trained based on facial feature points in a plurality of pairs of adjacent reference images. Further, the facial feature points of the face in the to-be-tracked image are determined based on the facial feature points of the face in the previous image and the facial feature point errors between the to-be-tracked image and the previous image.

Facial feature point tracking method, apparatus, storage medium, and device

A method, information processing apparatus, and a non-transitory computer-readable storage medium are provided. In the method, a location of an edge of an eye in a first image of a face is determined. An area of the first image based on the determined location is determined. The area of the first image is divided into first and second subareas based on pixel values of the area of the first image. The first subarea includes the pixel values of a first range and the second subarea includes the pixel values of a second range, and an average pixel difference of the first and second ranges is greater than a threshold. The location of the pupil is determined based on a location of one of the first and second subareas when the average pixel difference of the first and second ranges is greater than the threshold.

Pupil localizing method and system

This application relates to a voice encoding and sending method performed at a computer implemented system. The method includes sending voice data from at least one mobile terminal to at least one different mobile terminal; receiving at least one path of Real-Time Transport Control Protocol (RTCP) packet based on the voice data; parsing the at least one path of the RTCP packet, to obtain network status information; obtaining comprehensive network status information by means of statistics of the network status information; and adjusting a quality of service (QoS) parameter according to the comprehensive network status information, and encoding and sending the voice data according to the adjusted QoS parameter.

A real-time call method performed by a calling side, the calling side being a Voice over Internet Protocol (VoIP) terminal, includes: initiating a multi-party voice call request to a signaling server, wherein terminals that are specified in the multi-party voice call request includes a telephone terminal; establishing a data channel according to a remote access address returned by the signaling server in response to the multi-party voice call request; and performing a multi-party voice call based on establishment of data channels of the terminals according to the remote access address, wherein the telephone terminal establishes a data channel according to the remote access address by using a gateway device.

Instant calling method, apparatus and system

A fingerprint recognition method capable of improving a fingerprint recognition rate includes: Step, collecting a fingerprint image, and recording the number of collecting times, and then proceeding to Step; Step, matching the fingerprint image with pre-stored fingerprint templates for recognition, where a current matching process for recognition ends if matching succeed, otherwise, the method proceeds to Step; Step, restoring the fingerprint image, and matching the restored fingerprint image with the pre-stored fingerprint templates for recognition, where the current matching process for recognition ends if matching succeed, otherwise, the method proceeds to Step; Step, comparing the number of collecting times with a preset number of times, where the current matching process for recognition ends if the number of collecting times reaches the preset number of times otherwise, the method returns back to Step

Fingerprint recognition method and system capable of improving fingerprint recognition rate

The embodiments of the present disclosure provide a method for audio mixing. At least two audio input signals are obtained. Then the at least two audio input signals are linearly superimposed. A mixed signal obtained by linearly superimposing the at least two audio input signals is divided into at least two audio mixing signal-intensity zones according to an audio intensity of the mixed signal. Audio intensity scalability is performed for respective audio mixing signal-intensity zones using corresponding scalability ratios. The at least two audio mixing signal-intensity zones after performing the audio intensity scalability is superimposed and output. The embodiments of the present disclosure further provide an apparatus for audio mixing.

Method and apparatus for audio mixing

The present invention discloses a method for media file compression, which includes: extracting the encoding parameters from an input media file, separating and decoding the audio and video stream from the input media file, and extracting an original audio stream and an original video stream; computing the transcoding parameters required for compression according to the encoding parameters; encoding the original audio stream to output a new compressed audio stream, and encoding the original video stream to output a new compressed video stream according to the transcoding parameters; synthesizing the new compressed audio stream and the new compressed video stream to create a new media file. The present invention also provides a system for media file compression. By means of the method and system of the present invention, users can realize simple and rapid compression for media files of various formats without understanding media expertise, and the storage space can be saved, so that it is convenient to carry, transfer and share the media files.

Method and system for media file compression

The embodiments of the present invention disclose a method for controlling video-audio data playing, which relates to the network communication field. The method includes: obtaining total duration of playing video-audio data in a buffer; calculating a time difference, the time difference being a difference between a current time point and a time point of receiving a latest video-audio data packet; and performing time domain stretch processing for video-audio data in the buffer when the total duration and the time difference satisfy a preset condition, and playing the processed video-audio data. The embodiments of the present invention also disclose an apparatus for controlling video-audio data playing. By using the method and apparatus, the incontinuity phenomena will be decreased when the video-audio data is played, so as to improve user experiences.

Method and apparatus for controlling video-audio data playing

Embodiments of the present invention provide a method and device for processing network time delay characteristics. The method includes: determining whether network time delay changes; if the network time delay reduces, determining whether at least one blank frame is included in received but not played media frames of a real-time media service; if at least one blank frame is included in the received but not played media frames, extracting the blank frame from the received but not played media frames, the blank frame is a media frame, information amount of which is smaller than a preset first threshold, or difference between the information amount of which and the information amount of a previous media frame is smaller than a preset second threshold; if the network time delay increases, inserting the blank frame in the received but not played media frames. According to the embodiments of the present invention, when the network time delay changes, time for playing the received media frames may be adjusted by changing number of blank frames in the received but not played media frames, so as to reduce or eliminate the effect on the real-time media service generated by the network time delay characteristics.

Growing community of inventors

Shenzhen, China

Xinliang Wang