Future Wei Technologies, Inc.

Tencent Technology (shenzhen) Company Limited

Kui Fang

Qiang Wu

Haibo Liu

Chen-Xiong Zhang

Jian Zhang

Jingsong Xu

Ying Cui

Peng Zhang

Yecheng Xian

Yu Ding

Peiqiu Wu

A system and method for virtual clothes fitting based on video augmented reality in a mobile wireless device is disclosed. In an embodiment, a method for virtual cloth-fitting with video augmentation in a mobile wireless device includes receiving a video stream of an upper body of a user; detecting a face in the video stream; detecting a shoulder contour; determining keypoints of the shoulder and neck portions of the video stream of the upper body of the user according to the detected face and the detected shoulder contour; mapping an image of clothes to the video stream of the upper body of the user according to the keypoints; and displaying an augmented video stream of the upper body of the user with the image of the clothes overlaid over a portion of the video stream of the upper body of the user.

System and method for virtual clothes fitting based on video augmented reality in mobile phone

A method for switching an audio output device includes after a predetermined event is captured on the information output interface, detecting whether a voice interface object representing a voice message is currently displayed on the information output interface. The method further includes detecting whether an external audio output device is currently connected to the mobile electronic apparatus. If it is detected that a voice interface object is currently displayed, and it is not detected that an external audio output device is connected to the mobile electronic apparatus, displaying an interface switching object on the information output interface, to correspondingly switch an audio output device of the mobile electronic apparatus according to an input operation of a user.

Method and apparatus for switching audio output device

A device is configured to perform a method for neck and shoulder detection. The method includes receiving an image that includes a face. The method also includes performing a neck localization operation on the image. The neck localization operation is performed using results from a pre-trained regression model. The method further includes performing a shoulder localization operation on the image. The method still further includes estimating a plurality of shoulder and neck keypoints using results of the neck localization operation and the shoulder localization operation.

Apparatus and method for neck and shoulder landmark detection

Growing community of inventors

Shenzhen, China

Kui Fang