Abstract: This Application sets forth techniques for dynamically generating media content clips based on key events that occur. In particular, the techniques enable key events to be identified among a stream of events that take place in the real world (e.g., at awards events, at social events, at sporting events, etc.) and enable media content clips to be dynamically generated for the key events. In turn, the key events and their respective media content clips can be presented to users for viewing.

Abstract: An automatic video tagging system which learns from videos, their web context and comments shared on social networks is described. Massive multimedia collections are analyzed by Internet crawling and a knowledge base is maintained that updates in real time with no need of human supervision. As a result, each video is indexed with a rich set of labels and linked with other related contents. Practical applications of video recognition require a label scheme that is appealing to the end-user (i.e. obtained from social curation) and a training dataset that can be updated in real-time to be able to recognize new actions, scenes and people. To create this dataset that evolves in real-time and uses labels that are relevant to the users, a weakly-supervised deep learning approach is utilized combining both a machine-learning pre-processing stage together with a set of keywords obtained from the internet.

Abstract: An automatic video tagging system which learns from videos, their web context and comments shared on social networks is described. Massive multimedia collections are analyzed by Internet crawling and a knowledge base is maintained that updates in real time with no need of human supervision. As a result, each video is indexed with a rich set of labels and linked with other related contents. Practical applications of video recognition require a label scheme that is appealing to the end-user (i.e. obtained from social curation) and a training dataset that can be updated in real-time to be able to recognize new actions, scenes and people. To create this dataset that evolves in real-time and uses labels that are relevant to the users, a weakly-supervised deep learning approach is utilized combining both a machine-learning pre-processing stage together with a set of keywords obtained from the internet.