Abstract: Methods and systems for video action recognition using poselet keyframes are disclosed. An action recognition model may be implemented to spatially and temporally model discriminative action components as a set of discriminative keyframes. One method of action recognition may include the operations of selecting a plurality of poselets that are components of an action, encoding each of a plurality of video frames as a summary of the detection confidence of each of the plurality of poselets for the video frame, and encoding correlations between poselets in the encoded video frames.

Abstract: Mobile display device 100 for enabling a user to obtain either three-dimensional [3D] or two-dimensional [2D] viewing of content, comprising a 3D display 120 for enabling the 3D viewing of the content, a 2D display 140 for enabling the 2D viewing of the content, a display processor for displaying the content as 3D content 124 on the 3D display and for displaying the content as 2D content 144 on the 2D display, the 3D display and the 2D display being arranged on opposite faces 122, 142 of the device for enabling the user to obtain either the 3D viewing or the 2D viewing of the content by turning 102 the device about-face.

Abstract: [Object] To provide an information processing device, a storage medium, and a control method which are capable of assisting more comfortable and safer living by providing information based on real-time images collected from a plurality of imaging devices. [Solution] Provided is an information processing device, including: a search unit configured to search for an imaging device around a specific information processing device; a providing unit configured to provide information related to the searched imaging device and an angle of view of the imaging device to a user; and an acquiring unit configured to acquire an image imaged by an imaging device selected by the user. The providing unit provides the image acquired by the acquiring unit to the user.

Abstract: Systems, methods and apparatuses for handling trick mode operation using multiple video streams are provided. A media server presents a first video stream having a first level of a video characteristic for display. The media server, in response to receiving a first command, presents a second video stream having a second level of the video characteristic for display while stopping presenting the first video stream for display based on a determination determined using the first level of the video characteristic and the second level of the video characteristic. The first video stream and the second video stream are directed to the same video content.

Abstract: A method for generating a summary video sequence from a source video sequence is disclosed. The method comprises: identifying, in the source video sequence, event video sequences, wherein each event video sequence comprises consecutive video frames in which one or more objects of interest are present; extracting, from video frames of one or more event video sequences of the event video sequences, pixels depicting the respective one or more objects of interest; while keeping spatial and temporal relations of the extracted pixels as in the source video sequence, overlaying the extracted pixels of the video frames of the one or more event video sequences onto video frames of a main event video sequence of the event video sequences, thereby generating the summary video sequence. A video processing device configured to generate the summary video sequence is also disclosed.

Abstract: A lens unit and a rear-side focus adjustment system for infrared cameras capable of performing rear-side focus adjustments even when the position of the detection surface of an infrared sensor is unknown in an infrared camera. The lens unit is detachably mounted on a camera body that detects infrared light with an infrared sensor and converts the infrared light to an image signal, the lens unit including a focus adjustment lens and controller. The controller calculates a rear-side focus adjustment amount for causing a rear-side focus position to correspond to the detection surface based on an error between an actually measured focused position of the focus adjustment lens relative to an object at a particular object distance and a theoretically focused position of the focus adjustment lens calculated based on the object distance and controls the position of the focus adjustment lens based on the rear-side focus adjustment amount.

Abstract: The present technology relates to a reproduction device, reproduction method, and recording medium that enable graphics with an appropriate brightness to be displayed on a video having a wide dynamic range of brightness. A recording medium, on which the reproduction device of one aspect of the present technology performs reproduction, records coded data of an extended video that is a video having a first brightness range that is wider than a second brightness range, brightness characteristic information that represents a brightness characteristic of the extended video, and graphics data that is superimposed on the extended video and that has the second brightness range. The reproduction device converts a first pixel value of the graphics to a second pixel value in the brightness characteristic of the extended video represented by the brightness characteristic information, and synthesizes the extended video. The present technology can be applied to players that reproduce contents.

Abstract: A computing device plays at least one first video content segment. The video content segment may be a portion of an interactive video content sequence including multiple segments that may each be selected during play of one or more of the other segments. The computing device determines one or more second video content segments that are associated with the first video content segment. Such determination may be made by analyzing information describing an interactive video content sequence of which the video content segment is a part. The computing device attempts to load one or more second video content segments. In this way, play of the video content segments may reduce and/or avoid delays in changing the video content being played.

Abstract: A method for generating a summary video sequence from a source video sequence is disclosed. The method comprises: identifying, in the source video sequence, event video sequences, wherein each event video sequence comprises consecutive video frames in which one or more objects of interest are present; extracting, from video frames of one or more event video sequences of the event video sequences, pixels depicting the respective one or more objects of interest; while keeping spatial and temporal relations of the extracted pixels as in the source video sequence, overlaying the extracted pixels of the video frames of the one or more event video sequences onto video frames of a main event video sequence of the event video sequences, thereby generating the summary video sequence. A video processing device configured to generate the summary video sequence is also disclosed.

Abstract: Implementations relate to visualizations including images based on image content. In some implementations, a computer-implemented method includes obtaining a set of images, determining one or more pixel characteristics of the set of images, and determining one or more faces depicted in the plurality of images based on one or more pixel characteristics. The method selects a group of images of the set of images, where each image in the group of images depicts a different group of faces than depicted in the other images in the set of images. The method generates a visualization including the group of images, and provides the visualization to a user device in response to a user request to cause the group of images to be displayed by the user device.

Abstract: Systems and methods for marking an event of interest within a spherical video segment are provided. The spherical video segment may define visual content viewable from a point of view. User input designating an event of interest within the visual content may be received. The user input may indicate a point in time in the spherical video segment and a viewing angle of the event of interest. Tag information associated with the event of interest may be generated. The tag information may identify the point in time and the viewing angle such that notification of alert information is effectuated based on a determination that the viewing angle, proximate to the point in time during a subsequent presentation of the spherical video segment, is outside a display field of view. The alert information may indicate that the event of interest is located outside the display field of view.

Abstract: A method, system and computer program product for interactively identifying same individuals or objects present in video recordings is disclosed. When a thumbnail in a set of thumbnails is selected, new information is obtained. The new information may be that an individual or object is present in the portion of the video recording associated with the thumbnail. A search can be carried out for the individual or object based on the new information. The search generates new match likelihoods for each of displayed thumbnails within a user interface page. The displayed thumbnails are re-ordered based on the new match likelihoods.

Abstract: The present disclosure involves systems, software, and computer implemented methods for personalizing media content. Personalization digital media templates can be retrieved that designate (i) particular types of media content to be combined with particular preselected digital video files and (ii) particular times within particular preselected digital video files at which the particular types of media content are to be combined with the particular preselected digital video files, the particular times being relative to the times within the preselected digital video files at which emotionally impactful moments occur. Digital media content can be assembled for the personalized digital video files using particular preselected digital video files, the digital media templates, and the personal digital media file. The assembled digital media content can be encoded using a common video codec to generate the personalized digital video files.

Abstract: A stereo display device includes a light source module, an image determining array, an imaging module, and a spatial dividing element. The light source module sequentially emits first and second lights to target regions in different directions. The image determining array includes pixel units respectively disposed in the target regions, and each of the pixel units sequentially provides first and second information to the first and second lights respectively. The imaging module guides the first light having the first information to form first imaging units, and guides the second light having the second information to form second imaging units. The spatial dividing element sends the first image units to first viewing regions respectively and sends the second image units to second viewing regions respectively, and two of the first image units corresponding to adjacent two of the pixel units are transmitted to the first viewing regions in different directions.

Abstract: A method and an apparatus for playing back recorded video from a temporal position within a temporal range of the recorded video is disclosed. The recorded video including intra frames and inter frames and the recorded video including video sequences having different frame rates. The method comprises receiving a request for playing back the recorded video from a specific temporal position recorded in the recorded video, identifying an intra frame at an earlier temporal position in the recorded video than the specific temporal position received in the request, playing back the recorded video in a first mode from the identified intra frame, and playing back the recorded video in a second mode from the specific temporal position in the recorded video when the playing back of the recorded video in the first mode have arrived at the specific temporal position of in the recorded video.

Abstract: A vehicle side and rear monitoring system with a fail-safe function and a method thereof are provided. The system provides a fail-safe function for safe driving of a vehicle when an abnormality occurs in a side monitoring system of the vehicle, and a technique that provides a continuous side field of view of the vehicle when an abnormality occurs in the side monitoring system in the vehicle equipped with an AVM system. In addition, the system and provides a technique that corrects the distortion of an image captured by an AVM camera and performs an image rotation transformation to provide the image captured by the AVM camera at the same angle as that provided by side-view cameras. Therefore, when an abnormality occurs in the side monitoring system, the vehicle side and rear monitoring system with a fail-safe function continuously provides the same image as captured by the side-view cameras.

Abstract: A method and an apparatus for displaying the surroundings of a vehicle and to a driver assistance system having such an apparatus having at least one sensor for producing sensor data for the surroundings of a vehicle. In this case, the sensor data are conditioned to produce raw image data, if need be using a grid model of the surroundings of the vehicle, if need be the raw image data are processed to produce object information using a grid model of the surroundings of the vehicle, and the object information obtained is used to condition raw image data to produce image object data, and finally the image object data are displayed.

Abstract: A spherical content capture system captures spherical video content. A spherical video sharing platform enables users to share the captured spherical content and enables users to access spherical content shared by other users. In one embodiment, captured metadata or video/audio processing is used to identify content relevant to a particular user based on time and location information. The platform can then generate an output video from one or more shared spherical content files relevant to the user. The output video may include a non-spherical reduced field of view such as those commonly associated with conventional camera systems. Particularly, relevant sub-frames having a reduced field of view may be extracted from each frame of spherical video to generate an output video that tracks a particular individual or object of interest.

Abstract: A 3D display is characterized by a quality of viewing experience (QVE) mapping which represents a display-specific input-output relationship between input depth values and output QVE values. Examples of QVE mappings based on a metric of “viewing blur” are presented. Given reference depth data generated for a reference display and a representation of an artist's mapping function, which represents an input-output relationship between original input depth data and QVE data generated using a QVE mapping for a reference display, a decoder may reconstruct the reference depth data and apply an inverse QVE mapping for a target display to generate output depth data optimized for the target display.

Abstract: The disclosure relates to technology for providing determined future fields of view (FoVs) of a 360 degree video stream in a network having multiple video streams corresponding to multiple FoVs. FoV interest messages including requests for FoVs at time instants of the video stream are collected from viewers of the stream. A sequence of popular FoVs is created according to the messages, each representing a frequently requested FoV at a distinctive time instant. FoV transitions are created according to the FoV interest messages, each FoV transition including a current FoV a time instant and a next FoV of a next time instant, indicating a likely next FoV to be subsequent requested. Future FoVs of future time instants are determined for a user viewing the video stream with a history of requested FoVs of past time instants, based on the history of requested FoVs, the sequence and the transitions.