Abstract: Provided is a method, a system, and a program product for determining a policy using semi-supervised reinforcement learning. The method includes observing a state of an environment by a learning agent. The method also includes taking an action by the learning agent. The method further includes observing a new state of the environment and calculating a reward for the action taken by the learning agent. The method also includes determining whether a policy related to the learning agent should be changed. The determination is conducted by a teaching agent that inputs the state of the environment and the reward as features. The method can also include changing the policy related to the learning agent upon a determination that a label outputted by the teaching agent exceeds a reward threshold.

Abstract: An approach is provided in which the approach displays a main video feed and multiple secondary video feeds on a display. The multiple secondary video feeds are embedded in the main video feed at multiple locations based on visual characteristics sets of the multiple secondary video feeds. The approach dynamically detects a level of interest of a user at a first one of the locations in the main video feed based on a set of physical characteristics of the user. The approach identifies a first one of secondary video feeds that corresponds to the first location and, in turn, resizes the first secondary video feed based on the detected level of interest.

Abstract: Determining and/or adjusting cache expire times (sometimes herein referred to as “cache expires”) based, at least in part to how much excitement a live event, such as a live sporting event, is generating in its audience. After the excitement from the live event has dissipated, the cache expires can be reset to the values that they would otherwise have during normal operations.

Abstract: Techniques for padding audiovisual clips (for example, audiovisual clips of sporting events) for the purpose of causing the clip to have a predetermined duration so that the padded clip can be evaluated for viewer interest by a machine learning (ML) algorithm. The unpadded clip is padded with audiovisual segment(s) that will cause the padded clip to have a level of viewer interest that it would have if the unpadded clip had been longer. In some embodiments the padded segments are synthetic images generated by a generative adversarial network such that the synthetic images would have the same level of viewer interest (as adjudged by an ML algorithm) as if the unpadded clip had been shot to be longer.

Abstract: An approach is provided in which the approach displays a main video feed and multiple secondary video feeds on a display. The multiple secondary video feeds are embedded in the main video feed at multiple locations based on visual characteristics sets of the multiple secondary video feeds. The approach dynamically detects a level of interest of a user at a first one of the locations in the main video feed based on a set of physical characteristics of the user. The approach identifies a first one of secondary video feeds that corresponds to the first location and, in turn, resizes the first secondary video feed based on the detected level of interest.

Abstract: A method and system for improving automated video detection and correction is provided. The method includes retrieving a portion of a video stream and dividing the portion into video frames and an audio file. The video frames and audio file are analyzed, and a speech polarity of the audio file is detected. Likewise, a visual action epicenter of the portion of the video stream is detected and a fade portion of the portion of the video stream is removed. An edited fade portion associated with the fade portion is generated and patched into the video stream. The edited fade portion patched into the video stream is presented via a display device.

Abstract: Techniques for padding audiovisual clips (for example, audiovisual clips of sporting events) for the purpose of causing the clip to have a predetermined duration so that the padded clip can be evaluated for viewer interest by a machine learning (ML) algorithm. The unpadded clip is padded with audiovisual segment(s) that will cause the padded clip to have a level of viewer interest that it would have if the unpadded clip had been longer. In some embodiments the padded segments are synthetic images generated by a generative adversarial network such that the synthetic images would have the same level of viewer interest (as adjudged by an ML algorithm) as if the unpadded clip had been shot to be longer.

Abstract: A reflection is captured of a subsonic signal reflected by a contact surface. The contact surface is contacting a simulated surface of an object projected from a midair interface (MAI) device. A difference between the subsonic signal and the reflection is converted into a measurement of a flow in the contact surface. When the measurement is in a range of measurements, a change is caused in a temperature of a volume of a medium, the simulated surface being projected in volume of the medium, where the change in the temperature causes a second change in the flow in the contact surface.

Abstract: Fair deep reinforcement learning is provided. A microstate of an environment and reaction of items in a plurality of microstates within the environment are observed after an agent performs an action in the environment. Semi-supervised training is utilized to determine bias weights corresponding to the action for the microstate of the environment and the reaction of the items in the plurality of microstates within the environment. The bias weights from the semi-supervised training are merged with non-bias weights using an artificial neural network. Over time, it is determined where bias is occurring in the semi-supervised training based on merging the bias weights with the non-bias weights in the artificial neural network. A deep reinforcement learning model that decreases reliance on the bias weights is generated based on determined bias to increase fairness.

Abstract: A method and system for improving automated video detection and correction is provided. The method includes retrieving a portion of a video stream and dividing the portion into video frames and an audio file. The video frames and audio file are analyzed, and a speech polarity of the audio file is detected. Likewise, a visual action epicenter of the portion of the video stream is detected and a fade portion of the portion of the video stream is removed. An edited fade portion associated with the fade portion is generated and patched into the video stream. The edited fade portion patched into the video stream is presented via a display device.

Abstract: Determining and/or adjusting cache expire times (sometimes herein referred to as “cache expires”) based, at least in part to how much excitement a live event, such as a live sporting event, is generating in its audience. After the excitement from the live event has dissipated, the cache expires can be reset to the values that they would otherwise have during normal operations.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: obtaining the media file with a speech and identifying speakers on clusters separated by disfluencies and change of speakers. Clusters are re-segmented rearranged during diarization. Speaker identifications for the clusters in the media file is produced.

Abstract: Techniques for tailoring sampling rates for data from interactive digital properties on a feature-by-feature basis and collecting the data using the tailored sampling rates. Each feature may have an independent sampling rate irrespective of sampling rates assigned to other features. The independent sampling rates are determined based on at least one factor of predictive feature usage information based on historical feature usage information, predetermined rules, and current usage velocity of the feature. In some embodiments the independent sampling rate is influenced by the usage of an allocated resource provided to the digital property relative to a total allocation of that resource for a given time period. In some embodiments, the allocated resource is server calls to a digital data analytics server for the purposes of providing feature usage information from the interactive digital property for the performance of digital data analytics.

Abstract: Techniques for padding audiovisual clips (for example, audiovisual clips of sporting events) for the purpose of causing the clip to have a predetermined duration so that the padded clip can be evaluated for viewer interest by a machine learning (ML) algorithm. The unpadded clip is padded with audiovisual segment(s) that will cause the padded clip to have a level of viewer interest that it would have if the unpadded clip had been longer. In some embodiments the padded segments are synthetic images generated by a generative adversarial network such that the synthetic images would have the same level of viewer interest (as adjudged by an ML algorithm) as if the unpadded clip had been shot to be longer.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: obtaining a media file including a speech by one or more speaker. The language of the speech is identified and biographic data of a speaker of the speech is generated by analyzing semantics and vocal characteristics of the speech. The speaker is diarized and confidence in a resulting speaker label is evaluated against a threshold. The speaker label is adjusted with the language of the speech and biographic data of the speaker and produced as speaker metadata of the media file.

Abstract: In an embodiment, a method includes detecting a motion pattern in proximity to a first midair interface (MAI) device, the motion pattern being of a body part of a user. In an embodiment, the method includes converting the detected motion pattern to a simulated surface of an object projected from a shared MAI device, wherein the first MAI device and the shared MAI device each correspond to a different user. In an embodiment, the method includes causing a behavior change in the simulated surface being projected from the shared MAI device. An embodiment includes a computer usable program product. The computer usable program product includes a computer-readable storage device, and program instructions stored on the storage device.

Abstract: A method and system for auto-curating a media are provided. Media content is received over the network interface. A set of markers is identified for the media content, each marker corresponding to one of a plurality of visible and audible cues in the media content. Segments in the media content are identified based on the identified set of markers. An excitement score is computed for each segment based on the identified markers that fall within the segment. A highlight clip is generated by identifying segments having excitement scores greater than a threshold.

Abstract: Aspects of the present invention provide devices that subtitle streaming video with audio and identify a speaker in a streaming video with audio according to words spoken by the speaker matched to a cognitive print. The cognitive print includes traits classified according a hierarchical long short term model (LSTM). The hierarchical LSTM includes layers of LSTMs and each layer corresponds to the classification of one trait. A processor annotates a subtitle of the words spoken by the speaker, which decorates the subtitle with a label representative of the identified speaker, and streams the decorated subtitle with the streaming video with audio.

Abstract: Focus data of a remote user is analyzed to determine a focus shift from a first area to a second area at an event arena. A beacon density is computed at the second area, where the beacon density includes a number of physical beacons corresponding to a number of local users at the second area, a number of virtual beacons corresponding to a number of remote users focused on the second area, or a combination of thereof. When the beacon density at the second area exceeds a threshold density, an instruction to a streaming source is generated. The streaming source is caused to change a streaming content, to form changed streaming content that is related to the second area.

Abstract: A method and system for auto-curating a media are provided. Media content is received over the network interface. A set of markers is identified for the media content, each marker corresponding to one of a plurality of visible and audible cues in the media content. Segments in the media content are identified based on the identified set of markers. An excitement score is computed for each segment based on the identified markers that fall within the segment. A highlight clip is generated by identifying segments having excitement scores greater than a threshold.