18336596. Systems and Methods for Video Encoding and Segmentation (Comcast Cable Communications, LLC)
Contents
Systems and Methods for Video Encoding and Segmentation
Organization Name
Comcast Cable Communications, LLC
Inventor(s)
Md Mahmudul Hasan of Arlington VA (US)
Md Mohaiminul Islam of Raleigh NC (US)
Kishan Shamsundar Athrey of Chicago IL (US)
Anthony J. Braskich of Kildeer IL (US)
Systems and Methods for Video Encoding and Segmentation
This abstract first appeared for US patent application 18336596 titled 'Systems and Methods for Video Encoding and Segmentation
Original Abstract Submitted
Systems, apparatuses, and methods are described for segmenting a video content item (e.g., movie, TV-show) into a collection of scenes. Video frames may be grouped into shots, and visual relationships between image portions within each shot are identified by a self-attention model. The output may be further processed by a gated state space model to identify visual relationships between features in different shots. Multiple instances of the self-attention model and the gated state space model may be used to focus on different aspects of the video content item, for finding the relationships. An aggregated output may be provided to a prediction model and processed by the prediction model to determine scene boundaries. The determined scene boundaries or segmented scenes may be used for various user applications such as ad insertion, chapter selection, content searching, browsing, etc.
