Abstract: Systems, methods, and non-transitory media are provided for adjusting a posture of a subject being photographed. An example method can include obtaining, via a camera of a mobile device, an image depicting a subject posing in a first posture; determining a match between the first posture of the subject depicted in the image and a second posture from a set of stored user postures; and based on the match, generating a recommendation indicating one or more suggested adjustments to the first posture of the subject, the one or more suggested adjustments being estimated to increase a matching amount between the first posture of the subject and the second posture from the set of stored user postures.

Abstract: A device includes one or more processors configured to obtain an audio stream and to detect one or more keywords in the audio stream. The one or more processors are also configured to adaptively classify one or more objects associated with the one or more keywords. The one or more processors are further configured to insert the one or more objects into a video stream.

Abstract: Systems, methods, and non-transitory media are provided for adjusting a posture of a subject being photographed. An example method can include obtaining, via a camera of a mobile device, an image depicting a subject posing in a first posture; determining a match between the first posture of the subject depicted in the image and a second posture from a set of stored user postures; and based on the match, generating a recommendation indicating one or more suggested adjustments to the first posture of the subject, the one or more suggested adjustments being estimated to increase a matching amount between the first posture of the subject and the second posture from the set of stored user postures.

Abstract: The present disclosure generally relates to techniques for video recording. Some aspects of the present disclosure include systems and techniques for automatically initiating video recording. One example recording device may include at least one memory, and one or more processors coupled to the at least one memory and configured to: receive sensor data indicating an orientation associated with the recording device; detect a difference between statistical information associated with a first frame captured by a first video recording element and statistical information associated with a second frame captured by the first video recording element; determining whether to initiate video recording via the first video recording element based on the orientation and the detected difference; initiate the video recording based on the determination; and save the video recording to the at least one memory.

Abstract: Systems, methods, and non-transitory media are provided for adjusting a posture of a subject being photographed. An example method can include obtaining, via a camera of a mobile device, an image depicting a subject posing in a first posture; determining a match between the first posture of the subject depicted in the image and a second posture from a set of stored user postures; and based on the match, generating a recommendation indicating one or more suggested adjustments to the first posture of the subject, the one or more suggested adjustments being estimated to increase a matching amount between the first posture of the subject and the second posture from the set of stored user postures.