Abstract: A panoramic surveillance video generating apparatus includes: a plurality of image sensors configured to acquire a plurality of surveillance videos; and at least one processor configured to: generate a panoramic video by combining the plurality of surveillance videos, detect an event occurring in the panoramic video, set a partial region of the panoramic video as a surveillance region, output a video of the surveillance region to a virtual channel, and adjust at least one of a quantity of the surveillance region, a size of the surveillance region, and a position of the surveillance region based on an event detection result.

Abstract: Embodiments described herein provide systems and methods for gesture generation from multimodal input. A method includes receiving a multimodal input. The method may further include masking a subset of the multimodal input; generating, via an embedder, a multimodal embedding based on the masked multimodal input; generating, via an encoder, multimodal features based on the multimodal embedding, wherein the encoder includes one or more attention layers connecting different modalities; generating, via a generator, multimodal output based on the multimodal features; computing a loss based on the multimodal input and the multimodal output. The method may further include updating parameters of the encoder based on the loss.

Abstract: Embodiments described herein provide systems and methods for gesture generation from text. A method for gesture generation includes receiving an input text. The method may further include generating, via an encoder, an action representation in an action representation space based on the input text. The method may further include generating, via a first motion decoder, a first body configuration based on the action representation. The method may further include generating, via a second motion decoder, a second body configuration based on the first body configuration. The method may further include generating, via a token decoder, a first stop token based on the first body configuration.

Abstract: A video capturing system includes: a storage medium to store a plurality of image information sets corresponding to a plurality of reference images, respectively; and a video processing device to selectively control video capture and at least one other operation associated with video capture according to a privacy level selected from a privacy mode, wherein the video processing device includes a face detector to sense a face image from the captured video, and a privacy level controller to select one of a plurality of privacy levels according to an image information set matched with the face image sensed from the plurality of image information sets.

Abstract: A video capturing system includes: a storage medium to store a plurality of image information sets corresponding to a plurality of reference images, respectively; and a video processing device to selectively control video capture and at least one other operation associated with video capture according to a privacy level selected from a privacy mode, wherein the video processing device includes a face detector to sense a face image from the captured video, and a privacy level controller to select one of a plurality of privacy levels according to an image information set matched with the face image sensed from the plurality of image information sets.