This is provided to achieve capability of avoiding hindrance of accurate reflection of intention at the time of production due to execution of frame interpolation on the reception side. A predetermined container including a video stream obtained by performing encoding operation on moving image data of a predetermined frame rate is transmitted. Information for restricting frame interpolation is inserted into one or both of a layer of the container and a layer of the video stream. For example, the information for restricting frame interpolation includes information for prohibiting frame interpolation. Moreover, for example, the information for restricting frame interpolation includes information indicating the number of times of frame repeats.

The present disclosure provides a buffer processing method, apparatus, device and computer storage medium, where the method comprises: if it is detected that a drop of an available bandwidth of a receiving terminal exceeds a preset first threshold, detecting whether a drop of a video frame rate of the receiving terminal exceeds a preset second threshold, the second threshold being smaller than the first threshold; if YES, adjusting a buffer size of the receiving terminal; and if NO, keeping the buffer size of the receiving terminal unchanged. The manner provided by the present disclosure can optimize the buffer of the receiving terminal and reduce the delay.

A method of generating video frames for a cloud-based video game includes obtaining, via a communications network, a plurality of frames of a video game rendered at a cloud device; obtaining a player input received at an input device, the input device being used to play the video game, the player input being received in response to the display of at least one of the obtained video frames; inputting at least one of the obtained video frames and the player input to a prediction model; and synthesizing, based on the output of the prediction model, a subsequent frame for output at a display, and outputting the synthesized video frame at the display.

A method and device for controlling a frame rate of an electronic device, and an electronic device are provided. The method includes the following. A frame rate of rendering and a priority of each of target objects currently running on the electronic device are obtained. A synthesizing frame rate of the electronic device is determined according to the frame rate of rendering and the priority of each of the target objects. According to the synthesizing frame rate, respective images rendered by the target objects are synthesized to generate a to-be-displayed image.

Methods and systems provide control of media synchronization using time stamp pairs. In an embodiment, a first device may request a time stamp from a second device. The first device may determine any de-synchronization between the first and second devices based on the requested time stamp and characteristics of the request. The first device may define a rate scalar based on the determined de-synchronization. A sample rate conversion may be performed for the first device based on the rate scalar such that the outputs of the first device and the second device are synchronized.

Embodiments described herein provide systems and methods for sharing encoder output of video streams. In a particular embodiment, a method provides determining video profiles for each of a plurality of devices. The method further provides determining if two or more of the video profiles are similar by determining if parameters associated with each video profile differ by less than a threshold value. The method further provides transmitting a video stream encoded in a single format to the devices if they have similar profiles and transmitting video streams encoded in different formats to the devices if they do not have similar profiles.

Methods, apparatus, systems and articles of manufacture to generate temporal representations for action recognition systems are disclosed. An example apparatus includes an optical flow computer to compute a first optical flow based on first and second video frames separated by a first amount of time and compute a second optical flow based on third and fourth video frames separated by a second amount of time, the second amount of time different than the first amount of time, and an aggregator to combine the first optical flow and the second optical flow to form an image representing action in a video.

Techniques are disclosed for recognizing aspect ratio errors in image frames of a video and reporting the same. An aspect ratio checker application receives a video that includes multiple image frames and identifies aspect ratio changes in those image frames using a first differential of a time series that includes determined positions of the top, bottom, left, and right of content regions within the image frames. In particular, the aspect ratio checker may identify aspect ratio changes based on non-zero points of the first differential, and the aspect ratio checker further determines aspect ratios of content regions within image frames corresponding to the non-zero points of the first differential. In addition, the aspect ratio checker may generate and display a report indicating the determined aspect ratios and image frame ranges associated with those aspect ratios.

The invention discloses a method, device and system for in-sequence live streaming, belonging to the technical field of computers. The method includes receiving a terminal type of a streamer terminal sent by the streamer terminal during the in-sequence live streaming; determining a target transcoding mode corresponding to the terminal type of the streamer terminal according to the pre-stored corresponding relation between the terminal type and the transcoding mode; and receiving live streaming data sent by the streamer terminal, transcoding the live streaming data according to the target transcoding mode, and sending the transcoded live streaming data to a viewer terminal of a live streaming room to which the streamer terminal belongs. By the invention, the user can use the mobile terminal to conduct in-sequence live streaming.

Metadata and methods for variable-frame rate (VFR) video playback are presented. Proposed metadata include syntax parameters related to the presentation time duration, picture source type (e.g., original, duplicate, or interpolated), picture position in a scene (e.g., first, last, or in the middle), and motion-related information with respect to a previous picture. A decoder may use these metadata to apply appropriate frame-rate conversion techniques to reduce artifacts during VFR playback.