Abstract: One embodiment provides a method, the method including: receiving, from a first processor in communication with an image capture device of an image adjustment system and at a second processor, a frame including a scene; identifying, using the second processor, a region of interest within the frame; providing, from the second processor to the first processor, feedback identifying the region of interest; and adjusting, using the first processor and in view of characteristics of the region of interest, a parameter of the image capture device for subsequent frames captured by the image capture device. Other aspects are claimed and described.

Abstract: An image alteration system includes a memory and one or more processors. The processors receive input image data that depicts a background environment, and segment the input image data to locate objects depicted in the background environment. The processors identify a set of one or more of the objects to modify, and generate output image data that depicts a modified version of the background environment for display on a display device. The processors change an appearance of the one or more objects in the set as depicted in the output image data, relative to the appearance of the one or more objects as depicted in the input image data, without changing an appearance of one of more other objects located in the background environment. The input image data and the output image data represent video streams.

Abstract: A computer implemented method, system and computer program product are provided that receive video feeds from corresponding cameras distributed at different positions and orientations throughout a physical environment, and obtain location data associated with the cameras. The location data is indicative of at least one of the position or orientation for the corresponding camera. The method, system and computer program product identify, from the multiple cameras, a camera combination that includes first and second cameras that have overlapping fields of view (FOV) based on the location data and form a panoramic video of at least a portion of the environment by combining the content from the first and second cameras identified based on the location data.

Abstract: One embodiment provides a method, the method including: receiving, at a remote video feed fusion system, an indication of a meeting facilitated through a meeting application allowing access to participants in a location other than a location of a host of the meeting and supporting video transmissions between connected participants; identifying, using the remote video feed fusion system, a plurality of devices each having at least one image capture device and within the location of the host; capturing, using the remote video feed fusion system, a plurality of video feeds of the location of the host using the plurality of devices; creating, using the remote video feed fusion system, a fused video feed of the location of the host from the plurality of video feeds; and transmitting, using the remote video feed fusion system, the fused video feed to at least one participant accessing the meeting from a location other than the location of the host.

Abstract: Apparatuses, methods, and program products are disclosed for autonomously making image modifications. One apparatus includes at least one memory and at least one processor coupled with the at least one memory and configured to cause the apparatus to receive first image data from a first camera. The at least one processor is further configured to cause the apparatus to determine a modification based at least partly on the first image data, second image data from a second camera, or a combination thereof. The at least one processor is also configured to cause the apparatus to initiate the modification based at least partly on the first image data, the second image data, or the combination thereof.

Abstract: In one aspect, a first device includes at least one processor and storage with instructions executable by the processor to receive input from a camera and to identify, based on the input from the camera, a first lighting condition of a scene showing a user. Responsive to the first lighting condition satisfying a first criterion, the instructions are executable to transmit a first video stream showing the user's face as captured by the camera to a second device. Responsive to the first lighting condition not satisfying the first criterion, the instructions are executable to use a model to generate a 3D representation of the user's face according to one or more parameters related to the user and to transmit a second video stream to the second device that shows the 3D representation. The model is also trained under lighting conditions satisfying one or more criteria.

Abstract: In one aspect, a first device includes a processor, a camera, and storage. The storage includes instructions executable by the processor to auto-crop base images from the camera to render respective first auto-cropped images having a first field of view that is smaller than a second field of view of the respective base images themselves. The instructions are also executable to receive input from a motion sensor on the first device and, based on the input from the motion sensor, adjust the auto-cropping of the base images from the camera to render second auto-cropped images having a third field of view that is smaller than the second field of view and that is different from the first field of view. In various examples, the first and second auto-cropped images can be provided to a second device as part of a video conference.

Abstract: One embodiment provides a method, the method including: capturing, utilizing at least one image capture device coupled to an information handling device, video image data of a user; identifying, utilizing a gesture detection system and within the video image data, a location of hands of the user in relation to a gesture zone; and performing, utilizing the gesture detection system and based upon the location of the hands of the user in relation to the gesture zone, an action, wherein the producing the framed video stream comprises performing an action based upon the location of the hands of the user in relation to the gesture zone. Other aspects are claimed and described.

Abstract: An electronic device is provided that includes an input device configured to receive sound, a processor, and a memory storing program instructions accessible by the processor. Responsive to execution of the program instructions, the processor is configured to identify a third party application that accesses the electronic device, and vary sound characteristics obtained by the input device based on the third party application identified to prevent a biometric algorithm from obtaining user information.

Abstract: An electronic device is provided that includes a processor, and a data storage device having executable instructions accessible by the processor. Responsive to execution of the instructions, the processor obtains context data, and provides a login prompt. The processor may also vary input device input configured to enter values into the login prompt based on the context data, rearrange keys of a touchscreen keyboard on a display, the displayed input configured to enter the values into the login prompt based on the context data, or vary the location of a touchscreen keyboard based on the context data.

Abstract: A method, apparatus, and computer program product for selecting a runtime configuration based on model performance. The method includes running a computing model on a computing device using a first runtime configuration among a plurality of runtime configurations that are configured for the computing model and determining, by the computing device, a reduction in model performance. The method includes identifying, among the plurality of runtime configurations, a second runtime configuration based at least in part on the determined reduction in model performance and running the computing model using the second runtime configuration in response to the determined reduction in model performance.

Abstract: In one aspect, a device may include at least one processor and storage accessible to the at least one processor. The storage may include instructions executable by the at least one processor to provide at least a first image to a model as input, where the model may have been trained using groups of training images that show respective different parts of faces of one or more people but not full faces of the one or more people. The instructions may also be executable to receive, as output from the model, an indication regarding a facial body part. Based on the indication, the instructions may be executable to present a notification during a video conference, where the notification may indicate at least one action to take for a full face to be shown in a video stream as part of the video conference.

Abstract: Methods, computing devices, and computer-readable medium storing machine-readable instructions are disclosed for rendering video images for reducing energy consumption. An exemplary method performed in a computing system includes rendering video images at a first refresh rate, sending the rendered video images to a display device, determining if a reduced refresh rate event is occurring, and rendering video images at a second refresh rate responsive to determining the reduced refresh rate event is occurring. The second refresh rate is slower than the first refresh rate.

Abstract: In one aspect, a first device may include at least one processor and storage accessible to the at least one processor. The storage may include instructions executable by the at least one processor to facilitate a video conference with a second device and to apply a virtual background for a video stream provided to the second device as part of the video conference. The video stream may also show at least one user. The virtual background may change perspective as a field of view showing the user changes and/or as an actual background behind the user changes.

Abstract: Apparatuses, methods, systems, and program products are disclosed for adjusting content of a head mounted display. An apparatus includes a processor and a memory that stores code executable by the processor to determine a field of view for a user relative to a display of a head-mounted display unit, detect that the user is attempting to look at content that is presented on the display of the head-mounted display unit but is out of the user's field of view, and adjust the content that is out of the user's field of view to make the content visible to the user.

Abstract: One embodiment provides a method, the method including: capturing, utilizing at least one image capture device coupled to an information handling device, video image data of a user; identifying, utilizing a gesture detection system and within the video image data, a location of hands of the user in relation to a gesture zone; and performing, utilizing the gesture detection system and based upon the location of the hands of the user in relation to the gesture zone, an action, wherein the producing the framed video stream comprises performing an action based upon the location of the hands of the user in relation to the gesture zone. Other aspects are claimed and described.

Abstract: Apparatuses, methods, systems, and program products are disclosed for capturing an image and determining whether a switch is in a filtering position or a non-filtering position. When the switch is in the filtering position, the camera apparatus detects a switch position and determines whether the switch is in the filtering position or the non-filtering position. The camera captures the image, including audio/visual signals, while the switch is detected to be in the filtering position and modifies the image to inhibit biometric data collection from the image in response to the switch being in the filtering position when the image is captured.

Abstract: Apparatus, methods, and computer program products that include Adaptive Gain Control with learned gains and calculated gains based on the frequency domain are disclosed. One apparatus includes a processor and a memory that stores code executable by the processor to receive an audio signal from an audio input device and implement an Adaptive Gain Control to adjust a gain of the audio signal. The gain can include a learned gain and/or a calculated gain based on the frequency domain. Methods and computer program products that include and/or perform the operations and/or functions of the apparatus are also disclosed.

Abstract: Methods, computing devices, and computer-readable medium storing machine-readable instructions are disclosed for rendering video images for reducing energy consumption. An exemplary method performed in a computing system includes rendering video images at a first refresh rate, sending the rendered video images to a display device, determining if a reduced refresh rate event is occurring, and rendering video images at a second refresh rate responsive to determining the reduced refresh rate event is occurring. The second refresh rate is slower than the first refresh rate.

Abstract: Methods, communication devices, and computer-readable medium are disclosed for preventing unintentional outgoing communications initiated from a communication device. In one embodiment, the method includes receiving a request via a first input device to initiate a communication to a contact, determining whether the request is unlikely, receiving a confirmation that the request is intentional responsive to determining the request is unlikely, and sending the communication to the contact responsive to receiving the confirmation.