Hulu, LLC

Joyce Zhang

Dong Wang

Zhibing Wang

Tao Xiong

Hua Zheng

Jean-Paul Colaco

Heng Su

Cailiang Liu

Xuan Wei

Noelle Huynh

Effectiveness of video content is predicted using an automated or semi-automated analysis process operating on a computer. Video content is analyzed using image and audio data processing to assign a collection of attributes to a video ad. The collection of attributes is correlated to a historical effectiveness (e.g., click-thru rate) of past video ads in the same or similar attribute space to obtain predicted ad effectiveness. Differences between the collection of attributes and historical attribute spaces of greater effectiveness may also be determined and reported in the form of suggestions for improving the effectiveness of the ad.

Predictive video advertising effectiveness analysis

A method for annotating general objects contained in video content is provided. The method sends video data to a client device and receives a first annotation from the client device defining a boundary around a portion of a first frame of the video data. Then, the first annotation is tracked through multiple frames of the video content. Other annotations determined to be associated with annotation that match the first annotation within a threshold are determined where the other annotations are received from other client devices and located in the first frame or other frames from the first frame. The method combines the other annotations and the first annotation into an object track and associates a tag with the object track. The tag is input by at least one of the client devices.

Annotating general objects in video

Growing community of inventors

Beijing, China

Joyce Zhang