With the widespread availability of video cameras, we are facing an ever-growing enormous collection of unedited and unstructured video data. Due to lack of an automatic way to generate highlights from this large collection of video streams, these videos can be tedious and time consuming to index or search. The present invention is a novel method of online video highlighting, a principled way of generating a short video highlight summarizing the most important and interesting contents of a potentially very long video, which is costly both time-wise and financially for manual processing. Specifically, the method learns a dictionary from given video using group sparse coding, and updates atoms in the dictionary on-the-fly. A highlight of the given video is then generated by combining segments that cannot be sparsely reconstructed using the learned dictionary. The online fashion of the method enables it to process arbitrarily long videos and starts generating highlights before seeing the end of the video, both attractive characteristics for practical applications.

With the widespread availability of video cameras, we are facing an ever-growing enormous collection of unedited and unstructured video data. Due to lack of an automatic way to generate highlights from this large collection of video streams, these videos can be tedious and time consuming to index or search. The present invention is a novel method of online video highlighting, a principled way of generating a short video highlight summarizing the most important and interesting contents of a potentially very long video, which is costly both time-wise and financially for manual processing. Specifically, the method learns a dictionary from given video using group sparse coding, and updates atoms in the dictionary on-the-fly. A highlight of the given video is then generated by combining segments that cannot be sparsely reconstructed using the learned dictionary. The online fashion of the method enables it to process arbitrarily long videos and starts generating highlights before seeing the end of the video, both attractive characteristics for practical applications.

Disclosed herein are methods and systems for new analytic pathways for collecting information regarding video playback by human (and automated) users. This is achieved in part by placing certain elements (Vixels) within the code of a video file prior to it being uploaded by a user who shares the video. Whenever and wherever the video is played, whether it is streamed once, downloaded and played several times thereafter, or played for a mass audience, the analytic pathway is triggered each and every time the video file is played because the elements triggering the collection of analytics exist in the video file itself. By embedding Vixels into video files at or before upload, the analytics mechanisms are triggered by the embedded Vixel regardless of how, where, when, and by whom the video is played back, forming the framework for a simpler and more accurate analytics network.

Disclosed herein are methods and systems for new analytic pathways for collecting information regarding video playback by human (and automated) users. This is achieved in part by placing certain elements (Vixels) within the code of a video file prior to it being uploaded by a user who shares the video. Whenever and wherever the video is played, whether it is streamed once, downloaded and played several times thereafter, or played for a mass audience, the analytic pathway is triggered each and every time the video file is played because the elements triggering the collection of analytics exist in the video file itself. By embedding Vixels into video files at or before upload, the analytics mechanisms are triggered by the embedded Vixel regardless of how, where, when, and by whom the video is played back, forming the framework for a simpler and more accurate analytics network.

Video and corresponding metadata is accessed. Events of interest within the video are identified based on the corresponding metadata, and best scenes are identified based on the identified events of interest. A video summary can be generated including one or more of the identified best scenes. The video summary can be generated using a video summary template with slots corresponding to video clips selected from among sets of candidate video clips. Best scenes can also be identified by receiving an indication of an event of interest within video from a user during the capture of the video. Metadata patterns representing activities identified within video clips can be identified within other videos, which can subsequently be associated with the identified activities.

Video and corresponding metadata is accessed. Events of interest within the video are identified based on the corresponding metadata, and best scenes are identified based on the identified events of interest. A video summary can be generated including one or more of the identified best scenes. The video summary can be generated using a video summary template with slots corresponding to video clips selected from among sets of candidate video clips. Best scenes can also be identified by receiving an indication of an event of interest within video from a user during the capture of the video. Metadata patterns representing activities identified within video clips can be identified within other videos, which can subsequently be associated with the identified activities.

The present technology relates to a reproducing device, a reproducing method, an information processing device, an information processing method, a program, and a recording medium, which are capable of reproducing an appropriate HDR video. The reproducing device of the present technology acquires reproduction management information in which a first flag indicating whether or not encoded data of a first HDR video which is mandatory when a video of a luminance range wider than a standard luminance range is included in content is included in the content and a second flag indicating whether or not encoded data of a second HDR video that is likely to be included in the content is included in the content are described. Further, the reproducing device reproduces the encoded data of the first HDR video or the encoded data of the second HDR video on the basis of the details of the first flag and the second flag and performance of a display serving as an output destination. The present technology can be applied to a Blu-ray disc player.

The present technology relates to a reproducing device, a reproducing method, an information processing device, an information processing method, a program, and a recording medium, which are capable of reproducing an appropriate HDR video. The reproducing device of the present technology acquires reproduction management information in which a first flag indicating whether or not encoded data of a first HDR video which is mandatory when a video of a luminance range wider than a standard luminance range is included in content is included in the content and a second flag indicating whether or not encoded data of a second HDR video that is likely to be included in the content is included in the content are described. Further, the reproducing device reproduces the encoded data of the first HDR video or the encoded data of the second HDR video on the basis of the details of the first flag and the second flag and performance of a display serving as an output destination. The present technology can be applied to a Blu-ray disc player.

Methods and systems for analyzing video-game videos in connection with facilitating video editing and creation and performing automated extraction of information of interest to facilitate labeling of and/or highlight generation for such videos is provided. According to one embodiment, a video, containing content pertaining to a video game, is received by a video-game video analysis system. Information regarding the status of the video game over time is received by retrieving game metadata through an API of the video game or by analyzing audio or visual features within the content. Multiple clips are automatically identified within the video for proposed inclusion within an edited version of the video based on the status of the video game over time. The edited version of the video is then generated by (i) joining the automatically identified clips or (ii) joining multiple user-selected clips, including at least one clip selected from the automatically identified clips.

A video processing method and a video processing system for processing an original video are provided. The original video includes a plurality of original frames. The video processing method includes the following steps: A dynamic object is detected in the original video and a plurality of interesting regions in some of the original frames is obtained according to the dynamic object. Some of the original frames are cropped to obtain a plurality of cropped sub-frames according to the interesting regions. Each of the cropped sub-frames is resized to obtain a plurality of resized sub-frames whose resolutions are identical. The resized sub-frames are compressed to be an interesting video.