International Business Machines Corporation

Xiaoli Duan

Dong Chen

Peng Hui Jiang

Wei Qin

Jun Su

Jing Jing Zhang

Yue Chen

Dong Jun Zong

Ting Ting Zhan

Jing Bai

Xi Juan Men

Embodiments of the invention are directed to synchronous multi-point update of associated text. Aspects include receiving, from a user, a request to associate a first text with one or more other instances of the first text and looking up the first text in a text association table. Based on determining that no entry in the text association table corresponds to the first text, aspects include creating an entry in the text association table corresponding to the first text. Aspects also include adding an address of the first text to the entry in the text association table. Based on detecting a change to one of the first text and one of the one or more other instances of the first text, aspects further include updating the first text and each of the one or more other instances of the first text that was not changed.

Multi-text interconnection

In an approach for detecting key messages for a video, a processor builds a role model based on data from one or more data sources, with an identification feature of each role in a video. A processor samples a plurality of frames of the video. A processor identifies a key object presented in the plurality of frames. The key object is a role in the video. A processor recognizes a movement scenario associated with the role. A processor dynamically updates the role model based on the movement scenario. A processor identifies a role name based on the movement scenario. A processor generates a description script associated with the movement scenario for the role. A processor outputs the description script.

Cognitively generating information from videos

Growing community of inventors

Beijing, China

Xiaoli Duan