Microsoft Technology Licensing, LLC

Beijing Shunyuan Kaihua Technology Limited

Xianjun Huang

Fan Yang

Gang Chen

Matthew Robert Scott

Zheng Han

Xiaowei Dai

Dongzhi Xia

A solution is provided for detecting in real time video highlights in a sports video at a mobile computing device. A highlight detection module of the mobile computing device extracts visual features from each video frame of the sports video using a trained feature model and detects a highlight in the video frame based on the extracted visual features of the video frame using a trained detection model. The feature model and detection model are trained with a convolutional neural network on a large corpus of videos to generate category level and pair-wise frame feature vectors. Based on the detection, the highlight detection module generates a highlight score for each video frame of the sports video and presents the highlight scores to users of the computing device. The feature model and detection model are dynamically updated based on the real time highlight detection data collected by the mobile computing device.

Detect sports video highlights for mobile computing devices

Controlling assistance information comprises determining a user mode based on computer input signals generated by a user. If the user is in a passive mode and assistance information is detected, the assistance information is disabled in response to detecting a hidden signal. The assistance information is then enabled if later a reset signal is detected. If the user is in passive mode and assistance information is not detected, the assistance information is enabled in response to detecting a trigger signal. If the user is in an active mode and assistance information is detected, the assistance information is disabled.

Assistance information controlling

Growing community of inventors

Beijing, China

Xianjun Huang