Abstract: A method, apparatus and computer program product are provided for varying panning speeds of images based on saliency such that 360-degree images, panoramic images, video images and/or other wide view area images may be efficiently displayed by varying the panning speed such that the user focuses on salient portions of the image. A panning speed is determined based on the currently displayed area and its saliency relative to the saliency of non-displayed or peripheral portions. As a user pans from one area to another, while the user pans over a salient portion of the image, the actual reflected panning may occur at a relatively slower speed than when the user pans over an area not including a salient portion, or a less salient portion.

Abstract: A method, apparatus and computer program product facilitate the viewing of a storyline defined in a video. In regards to a method, viewing by a user of different sequential areas of a video over time is monitored. The different sequential areas of the video over time define a storyline. If the storyline is followed, the video continues to be presented. However, if the storyline is not followed in that a next sequential area of the video is not viewed, a portion of the video prior to the next sequential area is caused to be repeatedly replayed in a loop. Following this repeated replay of the portion of the video, the repeated replay of the portion of the video is ceased and the presentation of the video is resumed if the storyline is followed and the next sequential area of the video in the storyline is viewed.

Abstract: A method, apparatus and computer program product are provided in order to create and/or decode video content of a scene that includes regions having looping video of different loop lengths with the video content of the scene being configured to be repeatedly looped, such as in the form of a cinemagraph, without any temporal discontinuity. In the context of a method, the video content of a scene is encoded. The video content includes at least two regions having looping videos of different loop lengths. The method also includes constructing metadata in association with the video content. The metadata comprises information identifying a location of each region within the scene. The metadata further comprises a loop length for each of the at least two regions. The method further includes causing provision of the video content as encoded and the metadata.

Abstract: A method, apparatus and computer program product are provided for improving the efficiency of content delivery based on consumption data. Consumption data may be collected from various users and/or devices describing frequently viewed areas in the content. The consumption data may be represented as a heat map. Variable encoding properties, caching priorities, and/or rendering priorities may be determined based on the consumption data. Content encoding and delivery may therefore be optimized accordingly. Machine learning may be applied to create predicted consumption data for content which lacks actual consumption data, allowing optimizations to be applied in advance of any actual consumption. Some concepts may be applied to unviewed video to optimize live streaming or the like.

Abstract: A method, apparatus and computer program product facilitate the viewing of a storyline defined in a video. In regards to a method, viewing by a user of different sequential areas of a video over time is monitored. The different sequential areas of the video over time define a storyline. If the storyline is followed, the video continues to be presented. However, if the storyline is not followed in that a next sequential area of the video is not viewed, a portion of the video prior to the next sequential area is caused to be repeatedly replayed in a loop. Following this repeated replay of the portion of the video, the repeated replay of the portion of the video is ceased and the presentation of the video is resumed if the storyline is followed and the next sequential area of the video in the storyline is viewed.

Abstract: A method, apparatus and computer program product are provided in order to create and/or decode video content of a scene that includes regions having looping video of different loop lengths with the video content of the scene being configured to be repeatedly looped, such as in the form of a cinemagraph, without any temporal discontinuity. In the context of a method, the video content of a scene is encoded. The video content includes at least two regions having looping videos of different loop lengths. The method also includes constructing metadata in association with the video content. The metadata comprises information identifying a location of each region within the scene. The metadata further comprises a loop length for each of the at least two regions. The method further includes causing provision of the video content as encoded and the metadata.

Abstract: Embodiments herein select first and second panoramic images from respective first and second video streams, each comprising a series of stitched images captured by multiple cameras of respective first and second non-co-located video camera arrays. These arrays may be capturing live video for virtual reality rendering. A rotation is computed between the first and second panoramic images such that, when applied, the first and/or the second panoramic images are rotated relative to one another such that at least one common object is oriented to a common field of view position in both those panoramic images. The output can be variously manifested for different embodiments, for example the output can include a) the first video stream, the second video stream, and an indication of the computed rotation; and/or b) the first video stream and the second video stream with the computed rotation applied thereto.

Abstract: A method, apparatus and computer program product are provided for improving the efficiency of content delivery based on consumption data. Consumption data may be collected from various users and/or devices describing frequently viewed areas in the content. The consumption data may be represented as a heat map. Variable encoding properties, caching priorities, and/or rendering priorities may be determined based on the consumption data. Content encoding and delivery may therefore be optimized accordingly. Machine learning may be applied to create predicted consumption data for content which lacks actual consumption data, allowing optimizations to be applied in advance of any actual consumption. Some concepts may be applied to unviewed video to optimize live streaming or the like.

Abstract: A method, apparatus and computer program product are provided for varying panning speeds of images based on saliency such that 360-degree images, panoramic images, video images and/or other wide view area images may be efficiently displayed by varying the panning speed such that the user focuses on salient portions of the image. A panning speed is determined based on the currently displayed area and its saliency relative to the saliency of non-displayed or peripheral portions. As a user pans from one area to another, while the user pans over a salient portion of the image, the actual reflected panning may occur at a relatively slower speed than when the user pans over an area not including a salient portion, or a less salient portion.

Abstract: Methods, systems, and computer program products for parsing objects are provided herein. A method includes producing a plurality of versions of an image of an object derived from an input, wherein each version comprises one of one multiple resolutions of said image of said object; computing an appearance probability at each of a plurality of regions on the one or more lowest resolution versions of said plurality of versions of said image for at least one attribute for said object; determining a configuration of the at least one attribute in the one or more lowest resolution versions based on at least the appearance probability in each of the plurality of regions; and outputting said configuration.

Abstract: Methods, systems, and computer program products for parsing objects are provided herein. A method includes producing a plurality of versions of an image of an object derived from an input, wherein each version comprises one of one multiple resolutions of said image of said object; computing an appearance probability at each of a plurality of regions on the one or more lowest resolution versions of said plurality of versions of said image for at least one attribute for said object; determining a configuration of the at least one attribute in the one or more lowest resolution versions based on at least the appearance probability in each of the plurality of regions; and outputting said configuration.

Abstract: Techniques, systems, and articles of manufacture for multispectral detection of attributes for video surveillance. A method includes generating one or more training sets of one or more multispectral images, generating a group of one or more multispectral box features, using the one or more training sets to select one or more of the one or more multispectral box features to generate a multispectral attribute detector, and using the multispectral attribute detector to identify a location of an attribute in video surveillance, wherein using the multispectral attribute detector comprises, for one or more locations on each spectral band level of the multispectral image, applying the multispectral attribute detector and producing an output indicating attribute detection or an output indicating no attribute detection, and wherein the attribute corresponds to the multispectral attribute detector.

Abstract: Methods, systems, and computer program products for parsing objects in a video are provided herein. A method includes producing a plurality of versions of an image of an object derived from a video input, wherein each version has a different resolution of said image of said object; computing an appearance score at each of a plurality of regions on the lowest resolution version of said plurality of versions of said image for at least one attribute for said object, wherein said appearance score denotes a probability of the at least one attribute appearing in the region; determining a configuration of the at least one attribute in the lowest resolution version based on at least the appearance score in each of the plurality of regions in the lowest resolution version; and displaying said configuration.

Abstract: Methods, systems, and computer program products for parsing objects in a video are provided herein. A method includes producing a plurality of versions of an image of an object derived from a video input, wherein each version has a different resolution of said image of said object; computing an appearance score at each of a plurality of regions on the lowest resolution version of said plurality of versions of said image for at least one attribute for said object, wherein said appearance score denotes a probability of the at least one attribute appearing in the region; determining a configuration of the at least one attribute in the lowest resolution version based on at least the appearance score in each of the plurality of regions in the lowest resolution version; and displaying said configuration.

Abstract: Methods, systems, and computer program products for parsing objects in a video are provided herein. A method includes producing a plurality of versions of an image of an object, wherein each version has a different resolution of said image of said object, and computing an appearance score at each of a plurality of regions on the lowest resolution version for at least one attribute for said object. Such a method also includes analyzing one or more other versions to compute a resolution context score for each of the plurality of regions in the lowest resolution version, and determining a configuration of the at least one semantic attribute in the lowest resolution version based on the appearance score and the resolution context score.

Abstract: Methods, systems, and computer program products for parsing objects in a video are provided herein. A method includes producing a plurality of versions of an image of an object, wherein each version has a different resolution of said image of said object, and computing an appearance score at each of a plurality of regions on the lowest resolution version for at least one semantic attribute for said object. Such a method also includes analyzing one or more other versions to compute a resolution context score for each of the plurality of regions in the lowest resolution version, wherein said resolution context score denotes an extent to which finer spatial structure exists in the one or more others versions than in the lowest resolution version, and determining a configuration of the at least one semantic attribute in the lowest resolution version based on the appearance score and the resolution context score.

Abstract: Methods, systems, and computer program products for parsing objects in a video are provided herein. A method includes producing a plurality of versions of an image of an object, wherein each version has a different resolution of said image of said object, and computing an appearance score at each of a plurality of regions on the lowest resolution version for at least one attribute for said object. Such a method also includes analyzing one or more other versions to compute a resolution context score for each of the plurality of regions in the lowest resolution version, and determining a configuration of the at least one semantic attribute in the lowest resolution version based on the appearance score and the resolution context score.

Abstract: Methods, systems, and computer program products for parsing objects in a video are provided herein. A method includes producing a plurality of versions of an image of an object, wherein each version has a different resolution of said image of said object, and computing an appearance score at each of a plurality of regions on the lowest resolution version for at least one semantic attribute for said object. Such a method also includes analyzing one or more other versions to compute a resolution context score for each of the plurality of regions in the lowest resolution version, wherein said resolution context score denotes an extent to which finer spatial structure exists in the one or more others versions than in the lowest resolution version, and determining a configuration of the at least one semantic attribute in the lowest resolution version based on the appearance score and the resolution context score.

Abstract: Techniques, systems, and computer program products for parsing objects in a video are provided herein. A method includes producing and storing a plurality of versions of an image of an object derived from a video input, wherein each version of said image has a different resolution of said image; computing an appearance score at each of a plurality of regions on the lowest resolution version of said image for a plurality of semantic attributes with associated parts for said object, said appearance score denoting a probability of each semantic attribute appearing in the region; analyzing increasingly higher resolution versions than the lowest resolution version to compute a resolution context score for each region in the lowest resolution version; and ascertaining an optimized configuration of body parts and associated semantic attributes in the lowest resolution version, said ascertaining utilizing the appearance scores and the resolution context scores.

Abstract: Techniques, systems, and articles of manufacture for multispectral detection of attributes for video surveillance. A method includes generating one or more training sets of one or more multispectral images, generating a group of one or more multispectral box features, using the one or more training sets to select one or more of the one or more multispectral box features to generate a multispectral attribute detector, and using the multispectral attribute detector to identify a location of an attribute in video surveillance, wherein using the multispectral attribute detector comprises, for one or more locations on each spectral band level of the multispectral image, applying the multispectral attribute detector and producing an output indicating attribute detection or an output indicating no attribute detection, and wherein the attribute corresponds to the multispectral attribute detector.