Abstract: A hierarchy of computing modules is configured to learn a cause of input data sensed over space and time. The hierarchy is further configured to determine a cause of novel sensed input data dependent on the learned cause. Further, the hierarchy has at least one interface associated with an operation of the hierarchy, where the operation is extensible via the interface.

Abstract: The invention facilitates and enhances review of a body of information (that can be represented by a set of audio data, video data, text data or some combination of the three), enabling the body of information to be quickly reviewed to obtain an overview of the content of the body of information and allowing flexibility in the manner in which the body of information is reviewed. In a particular application of the invention, the content of audiovisual news programs is acquired from a first set of one or more information sources (e.g., television news programs) and text news stories are acquired from a second set of one or more information sources (e.g., on-line news services or news wire services). In such a particular application, the invention can enable the user to access the news stories of audiovisual news programs in a random manner so that the user can move quickly among news stories or news programs.

Abstract: A hierarchical temporal memory (HTM) based system may be provided as a software platform. The software platform includes: a runtime engine arranged to run an HTM network; a first interface accessible by a set of tools to configure, design, modify, train, debug, and/or deploy the HTM network; and a second interface accessible to extend a functionality of the runtime engine.

Abstract: The invention indexes an audiovisual recording to enable navigation within the audiovisual recording. In particular, the invention provides indexing within a “show” of a recording of an audiovisual broadcast (e.g., a television broadcast or a radio/satellite audio broadcast) that enables navigation within the show, in contrast to indexing among shows (i.e., identification of locations corresponding to the start and/or end of shows) that can enable navigation between shows. The invention also enables navigation among one or more intelligently selected segments of the recording in a non-linear manner. A graphical user interface can be implemented to effect navigation in accordance with the invention of a recording of audiovisual content.

Abstract: A method is provided for conducting commerce over a network via vision-enabled content. First, content is encoded to convert it into vision-enabled content. Payment is received for vision-enabling the content. Also, a program to decode the vision-enabled content is provided. Finally, the vision-enabled content is sent to a user over a network. The program decodes the vision-enabled content and receives an image of the user. The vision-enabled content may include advertising content, entertainment content, and educational or instructional content. In one embodiment, the program combines the image of the user with the vision-enabled content. In another embodiment, the program utilizes the image of the user to control the vision-enabled content.

Abstract: Digitally compositing an object from an input image onto a destination image is disclosed. The object is composited from an image having an arbitrary or non-uniform colored background containing some non-static elements onto a destination image with reduced effects from shadows cast by the object and with reduced gaps or holes within the object. The effect of shadows emanating from the object is reduced so that the composited object in the destination image contains only the object clearly outlined by the object's physical boundaries without the effect of shadows cast by the object.

Abstract: A method is provided for conducting commerce over a network via vision-enabled content. First, content is encoded to convert it into vision-enabled content. Payment is received for vision-enabling the content. Also, a program to decode the vision-enabled content is provided. Finally, the vision-enabled content is sent to a user over a network. The program decodes the vision-enabled content and receives an image of the user. The vision-enabled content may include advertising content, entertainment content, and educational or instructional content. In one embodiment, the program combines the image of the user with the vision-enabled content. In another embodiment, the program utilizes the image of the user to control the vision-enabled content.

Abstract: The invention provides a method and apparatus for detecting a scene transition in digitized video data. The method includes determining if a gradual transition is detected in the video data that ends with a current frame based at least on the current frame and one or more previous frames in the digitized video data. The gradual transition has a length. The method includes comparing the gradual transition to a synthetically produced gradual transition spanning a same length and generated from starting and ending frames associated with the detected gradual transition and marking the detected gradual transition only if the detected gradual transition is sufficiently similar to the synthetically produced gradual transition.

Abstract: A system and method are disclosed for digitally compositing an object from an input image onto a destination image. The object is composited from an image having an arbitrary or non-uniform colored background containing some non-static elements onto a destination image with reduced effects from shadows cast by the object and with reduced gaps or holes within the object. Various improvements in the compositing procedure such as shadow reduction and hole filling, and less restrictive requirements regarding the object's surroundings are disclosed. A background model is created and a frame of an input image containing the object is obtained. An alpha image is created in which each pixel is either a zero, indicating it is not part of the object, or a one, indicating that it is part of the object.

Abstract: A camera array captures plural component images which are combined into a single scene from which “panning” and “zooming” within the scene are performed. In one embodiment, each camera of the array is a fixed digital camera. The images from each camera are warped and blended such that the combined image is seamless with respect to each of the component images. Warping of the digital images is performed via pre-calculated non-dynamic equations that are calculated based on a registration of the camera array. The process of registering each camera in the arrays is performed either manually, by selecting corresponding points or sets of points in two or more images, or automatically, by presenting a source object (laser light source, for example) into a scene being captured by the camera array and registering positions of the source object as it appears in each of the images.

Abstract: Process-response statistical modeling of visual images can be used in determining similarity between visual images. Evaluation of the content of visual images—and, in particular, image similarity determinations—can be used in effecting a variety of interactions (e.g., searching, indexing, grouping, summarizing, annotating, keyframing) with a collection of visual images.

Abstract: Process-response statistical modeling of visual images can be used in determining similarity between visual images. Evaluation of the content of visual images—and, in particular, image similarity determinations—can be used in effecting a variety of interactions (e.g., searching, indexing, grouping, summarizing, annotating, keyframing) with a collection of visual images.

Abstract: Process-response statistical modeling of visual images can be used in determining similarity between visual images. Evaluation of the content of visual images—and, in particular, image similarity determinations—can be used in effecting a variety of interactions (e.g., searching, indexing, grouping, summarizing, annotating, keyframing) with a collection of visual images.

Abstract: Process-response statistical modeling of visual images can be used in determining similarity between visual images. Evaluation of the content of visual images—and, in particular, image similarity determinations—can be used in effecting a variety of interactions (e.g., searching, indexing, grouping, summarizing, annotating, keyframing) with a collection of visual images.

Abstract: Process-response statistical modeling of visual images can be used in determining similarity between visual images. Evaluation of the content of visual images—and, in particular, image similarity determinations—can be used in effecting a variety of interactions (e.g., indexing, grouping, summarizing, annotating, searching keyframing) with a collection of visual images.

Abstract: Process-response statistical modeling of visual images can be used in determining similarity between visual images. Evaluation of the content of visual images—and, in particular, image similarity determinations—can be used in effecting a variety of interactions (e.g., searching, indexing, grouping, summarizing, annotating, keyframing) with a collection of visual images.

Abstract: A method and apparatus for producing video content. The method includes acquiring video data from a source. If the video data is not digitized, then the video data is digitized. The method includes generating scene indexes for the video data including a representative still image for each scene and combining the video data and scene indexes along with a media player on a video disc. The video player is operable to play the video data in accordance with the scene indexes including playing a scene from the video data on a client computer while displaying the representative stills for other of the scenes available for display on the video disc.

Abstract: An interactive karaoke system includes a microphone developing an audio input from at least one karaoke performer; a camera producing a series of video frames including the at least one karaoke performer; and a karaoke processor system including a video environment and a related audio environment for the karaoke performer. The karaoke processor system is coupled to the camera to create extracted images of the at least one karaoke performer from the series of video frames and to composite the extracted images with a background derived from the video environment. The video environment is affected by at least one of a position and a movement of the at least one karaoke performer. A karaoke network includes a local area network, a local karaoke server coupled to the local area network and storing local karaoke content; and a number of karaoke systems coupled to the local area network, each of which can request karaoke content from the local karaoke server.

Abstract: A method and apparatus for producing video content. The method includes acquiring video data from a source. If the video data is not digitized, then the video data is digitized. The method includes generating scene indexes for the video data including a representative still image for each scene and combining the video data and scene indexes along with a media player on a video disc. The video player is operable to play the video data in accordance with the scene indexes including playing a scene from the video data on a client computer while displaying the representative stills for other of the scenes available for display on the video disc.

Abstract: The invention facilitates and enhances review of a body of information, such as a set of audio, video and text data or some combination thereof, enabling the body of information to be quickly reviewed so to obtain an overview of the content of the body of information and allowing flexibility in reviewing. In on embodiment, the content is acquired from a first set of one or more sources, i.e. TV news, and text news stories are acquired from a second set of one or more sources, i.e. On-line services. The invention enables the user to access the information randomly, thereby enhancing the speed of accessing/locating among news stories/programs pertaining particular subject. Additionally, the user while observing a particular news story, the invention can identify and display related news stories.