Abstract: A method, system, apparatus, and non-transitory computer-readable medium for image processing using a multi-task neural network framework may be provided. The method be performed by one or more processors and may include receiving an input image, and performing an image processing task based on the input image using the multi-task neural network framework, wherein the multi-task neural network framework is trained using a combination of task specific losses, the task specific losses including a plurality of first losses associated with the multi-task neural network framework and a plurality of second losses associated with a plurality of single-task neural network models. The method may also include generating an output of the image processing task based on up sampling an output of the multi-task neural network framework.

Abstract: A method, system, apparatus, and non-transitory computer-readable medium for image processing using a multi-task neural network framework may be provided. The method be executed by one or more processors, and may include receiving an input image; and generating one or more image patches based on the input image. The method may include performing an image processing task based on the input image using the multi-task neural network framework, wherein the multi-task neural network framework is trained using an adaptive feature distillation function, and wherein the adaptive feature distillation function is based on a comparison of intermediate features of the multi-task neural network framework and intermediate features of a plurality of single-task neural network models. The method may include generating an output of the image processing task based on up sampling an output of the multi-task neural network framework.

Abstract: Disclosed herein is an image frame extraction apparatus that acquires a video image; extracts features of each of a plurality of image frames of the acquired video image; analyzes the extracted features of each of the plurality of image frames, and extracts candidates of a representative frame from the plurality of image frames; and, for each of the extracted candidates of the representative frame, calculates a displacement in a shape space of a pose of an object in the image frame with respect to a reference pose, and select the representative frame from the candidates of the representative frame based on the calculated displacement in the shape space.