Qualcomm incorporated (20250086956). MULTI-VIEW CONVOLUTIONAL NEURAL NETWORKS FOR VIDEO PROCESSING
MULTI-VIEW CONVOLUTIONAL NEURAL NETWORKS FOR VIDEO PROCESSING
Organization Name
Inventor(s)
Amirhossein Habibian of Amsterdam (NL)
Haitam Ben Yahia of Diemen (NL)
Fatih Murat Porikli of San Diego CA (US)
MULTI-VIEW CONVOLUTIONAL NEURAL NETWORKS FOR VIDEO PROCESSING
This abstract first appeared for US patent application 20250086956 titled 'MULTI-VIEW CONVOLUTIONAL NEURAL NETWORKS FOR VIDEO PROCESSING
Original Abstract Submitted
the present disclosure relates to processing video data. some aspects involve partitioning input video data into two or more clips, each clip comprising a number of t frames, wherein each frame comprises a frame height, a frame width and a frame channel dimension c. each clip is encoded into s encoded representations comprising a code height, a code width, and a code channel dimension, wherein t and s are integers with t≥s>1. encoding each clip into the s encoded representations may comprise concatenating all t frames of the clip into an input tensor along the frame channel dimension and encoding the input tensor into the s encoded representations using a convolutional neural network (cnn) encoder.