Abstract: A human-computer interaction method based on in-video advertisements, including steps of: S1. detecting a user's action of activating an in-video advertisement in the process of playing a main video, wherein the in-video advertisement is in an in-video advertisement layer, and the in-video advertisement layer is a logical layer above the main video, and the in-video advertisement layer is logically transparent to the main video except for pixels occupied by the in-video advertisement; and S2. triggering an advertisement action when the user's action of activating the in-video advertisement is detected.

Abstract: A method for searching an AD insertion position includes following steps: S1. identifying a human body area in a video image; S2. identifying a blank wall area in the video image; and S3. determining the AD insertion position in the blank wall area in the video image, so that the AD insertion position intersects the human body area. A method for automatically inserting an advertisement AD in a video includes following steps: determining an AD insertion position in the video by searching a product AD insertion position based on deep learning, and inserting the AD on the position. Through the method, an appropriate position for an AD can be automatically searched on a blank wall part in the video. In addition, the inserted AD can be presented in the video in a natural way, and thereby avoiding or reducing the impact of AD insertion on impression of the video.

Abstract: Disclosed herein are methods for pasting an object to a video. A method may include receiving the video having a plurality of video frames, in which an ending video frame is included; scanning a first video frame of the plurality of video frames, wherein the first video frame has one or more first target objects and one or more second target objects; determining whether a corresponding predetermined video frame information associated with the first video frame is identified in database; if so, segmenting the one or more second target objects; extracting the one or more segmented second target objects from the first video frame; pasting one or more predetermined objects to the one or more first target objects in the video frame, based on the predetermined video frame information associated with the first video frame; and pasting the extracted one or more second target objects to the video frame.

Abstract: An electronic device having a display on one side of the device and one or more image sensors on the opposite side of the device captures image data using the one or more image sensors. The display displays a portion of the captured image data on the display and a first graphical object overlaid on the displayed portion of the captured image data. A user gesture is detected using the one or more image sensors. In accordance with a determination that the detected user gesture meets a set of criteria, a position of the graphical object is updated based on the user gesture or is the first graphical object is replaced with a second graphical object. In accordance with a determination that the detected user gesture does not meet a set of criteria, the display of the first graphical object is maintained.

Abstract: Systems and methods for gesture recognition based on depth information from a camera include, at an electronic device having a camera system, capturing a video frame and depth information associated with the video frame, identifying a foreground portion of the video frame based on the depth information, and determining whether the foreground portion matches a predefined gesture in a database. In accordance with a determination that the foreground portion matches a predefined gesture in the database, the device determines whether one or more subsequent video frames matches the one or more predefined gestures to produce a recognized gesture.

Abstract: Described herein are methods and systems for receiving a plurality of live video frames; identifying one or more target objects and one or more non-target objects in a first live video frame of the plurality of live video frames, by at least one trained deep neural network; identifying one or more sets of pixels belonging to the one or more target objects; identifying an area on a surface of the one or more target objects, based on the identified one or more sets of pixels belonging to the one or more target objects; overlaying one or more predetermined graphical images onto the area on the surface of the one or more target objects in the plurality of live video frames; and overlaying the one or more non-target objects onto the one or more predetermined graphical images in the plurality of live video frames to form a processed live video.

Abstract: An electronic device having a display, memory, and an image sensor captures image data from the image sensor. The device receives a selection of a background image from a user of the electronic device. The background image 100is not based on image data from the image sensor. The device displays a view on the display or view-fmder. The view is based on the captured image data and the selected background image. The device receives first user input at the electronic device. The displayed view is updated by modifying the background image in accordance with the first user input while maintaining the display of the captured image data. The device stores the view as image data in the memory.

Abstract: At an electronic device coupled to a display, a communication interface, and a first image sensor, first image data is captured from the first image sensor. Second image data is received over the communication interface from a first remote device. The display displays a portion of the second image data with a portion of the first image data. The displayed portion of the second image data obscures some of the first image data.

Abstract: Systems and methods are directed to augmented reality (AR) environments where AR objects, such as intelligent virtual objects, interactively respond to ambient environmental changes. Image data are captured from one or more sensors, augmented reality environments are generated based on the image data, environmental parameters are detected from one or more environmental sensors, and views of the generated AR environment are displayed. Some views include the AR object existing therein, for instance when the detected environmental parameters satisfy certain criteria. Other views do not include the AR object while such criteria are not met.

Abstract: Systems and methods for gesture recognition based on depth information from a camera include, at an electronic device having a camera system, capturing a video frame and depth information associated with the video frame, identifying a foreground portion of the video frame based on the depth information, and determining whether the foreground portion matches a predefined gesture in a database. In accordance with a determination that the foreground portion matches a predefined gesture in the database, the device determines whether one or more subsequent video frames matches the one or more predefined gestures to produce a recognized gesture.

Abstract: An electronic device having a display on one side of the device and one or more image sensors on the opposite side of the device captures image data using the one or more image sensors. The display displays a portion of the captured image data on the display and a first graphical object overlaid on the displayed portion of the captured image data. A user gesture is detected using the one or more image sensors. In accordance with a determination that the detected user gesture meets a set of criteria, a position of the graphical object is updated based on the user gesture or is the first graphical object is replaced with a second graphical object. In accordance with a determination that the detected user gesture does not meet a set of criteria, the display of the first graphical object is maintained.

Abstract: At an electronic device coupled to a display, a communication interface, and a first image sensor, first image data is captured from the first image sensor. Second image data is received over the communication interface from a first remote device. The display displays a portion of the second image data with a portion of the first image data. The displayed portion of the second image data obscures some of the first image data.

Abstract: At an electronic device having a display, a first sensor, and a second sensor different than the first sensor, a view is displayed on the display. The view includes an interface object at a first location. A first gesture is detected based on first data from the first sensor, wherein the first gesture identifies the interface object. A second gesture is detected based on second data from the second sensor. A second location is determined for the interface object based on the second gesture. The display of the interface object is updated from the first location to the second location in the view.

Abstract: At an electronic device having a display and one or more image sensors, a view of an augmented reality (AR) environment is displayed, wherein the AR environment includes a background based on captured image data from the one or more image sensors and a first virtual object at a first location and the view includes display of the first virtual object. Movement data indicating movement of a remote user is received. A property is determined of the first virtual object in the AR environment based on the received data. The display of the view is updated based on the determined property.

Abstract: At an electronic device having a display, a first sensor, and a second sensor different than the first sensor, a view is displayed on the display. The view includes an interface object at a first location. A first gesture is detected based on first data from the first sensor, wherein the first gesture identifies the interface object. A second gesture is detected based on second data from the second sensor. A second location is determined for the interface object based on the second gesture. The display of the interface object is updated from the first location to the second location in the view.

Abstract: A network relaying device facilitates communication among a plurality of network nodes. When the network relaying device receives a data packet from a first network node, it determines whether a historical transmission rate of the first network node exceeds a threshold rate. Based on this determination, the network relaying device determines whether to associate the data packet with a first queue or a second queue for transmission to a second network node.

Abstract: A mesh network relaying device includes at least a first radio, a second radio, and a third radio. During normal operation, the device communicates with other network nodes via the first and second radios, the radios operating at the best available bandwidth. When the device identifies a communication link failure in one of the first and second radios, the device activates the third radio and operates the first, second, and/or third radios at narrower bandwidths. When the communication link failure is resolved, the device deactivates the third radio, and resumes communication via the first and second radios at wider bandwidth.

Abstract: In a computer-enabled method, at a wireless network access point configured to operate in a wireless network, wherein the wireless network access point comprises a plurality of radios, a load on the wireless network access point is determined, while at least two radios of the plurality of radios are powered on. In response to the load transitioning from above a threshold to below the threshold, at least one of the powered-on radios is powered off while leaving the remaining radios of the plurality of radios powered-on.

Abstract: A network relaying device facilitates communication among a plurality of network nodes. When the network relaying device receives a data packet from a first network node, it determines whether a historical transmission rate of the first network node exceeds a threshold rate. Based on this determination, the network relaying device determines whether to associate the data packet with a first queue or a second queue for transmission to a second network node.

Abstract: A mesh network relaying device includes at least a first radio, a second radio, and a third radio. During normal operation, the device communicates with other network nodes via the first and second radios, the radios operating at the best available bandwidth. When the device identifies a communication link failure in one of the first and second radios, the device activates the third radio and operates the first, second, and/or third radios at narrower bandwidths. When the communication link failure is resolved, the device deactivates the third radio, and resumes communication via the first and second radios at wider bandwidth.