Abstract: One embodiment provides a method, the method including: receiving a query from a user at a first query response system; creating, using the first query response system, a refined query by iteratively receiving, from the user, refinements to the query subsequent to responses provided by the first query response system; and transferring, responsive to receiving an indication from the user to transfer the refined query, the refined query from the first query response system to a second query response system. Other aspects are claimed and described.

Abstract: In one aspect, a device includes a processor system and storage. The storage includes instructions executable by the processor system to receive a prompt, and to provide the prompt as first input to a first large language model (LLM). Based on providing the prompt as first input to the first LLM, the instructions are executable to receive a first output from the first LLM that indicates first generative text. The instructions are further executable to provide the prompt as second input to a second LLM, and to receive a second output from the second LLM based on providing the prompt as second input to the second LLM. The second output also indicates second generative text. The instructions are then executable to concurrently present, on a display, the first and second generative texts. Present principles may also be applied to generative image and generative audio models.

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.

Abstract: One embodiment provides a method, the method including: receiving, at an information handling device of a user during a video session, a video feed occurring in substantially real-time and displaying at least one object; receiving, from the user, input adjusting at least one characteristic of the video feed via adjustment of a parameter of a device capturing the at least one video feed; and providing, from the information handling device, instructions to a remote information handling device capturing the video feed to adjust the at least one characteristic of the video feed Other aspects are claimed and described.

Abstract: In one aspect, a first device includes a processor assembly, a display, and storage. The storage includes instructions executable by the processor assembly to receive video from a second device different from the first device, determine whether a user is looking at the display, and process the video a first way for presentation on the display based on a determination that the user is not looking at the display. The instructions are also executable to process the video a second way for presentation on the display based on a determination that the user is looking at the display. The first way may include using a lower resolution or slower frame rate than the second way. The first way may also include using a CPU little core rather than a GPU.

Abstract: In one aspect, a first device includes a processor assembly, a display, and storage. The storage includes instructions executable by the processor assembly to receive video from a second device different from the first device, determine whether a user is looking at the display, and process the video a first way for presentation on the display based on a determination that the user is not looking at the display. The instructions are also executable to process the video a second way for presentation on the display based on a determination that the user is looking at the display. The first way may include using a lower resolution or slower frame rate than the second way. The first way may also include using a CPU little core rather than a GPU.

Abstract: Apparatuses, methods, systems, and program products are disclosed to securely erase user data using storage regions on a shared computing device. Memory stores code executable by the processor. The code is executable to configure a nonvolatile storage device of a shared device that may be used by multiple users but is exclusively used by one user at a time. The nonvolatile storage device has shared files storing system data and a data region storing user data associated with a user. The code executes to assign read-only privileges to the system region and read-write privileges to the data region before sharing the device with the user. Requests to write data to the nonvolatile storage device while the device is shared are serviced on the data region. When the user returns the shared device to the originator the code executes to erase the data region.

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: One embodiment provides a method, the method including: receiving, at a color tone adjustment system, an image of a scene; identifying, using the color tone adjustment system, a light source providing illumination within the image; and adjusting, using the color tone adjustment system, a color tone of the image based upon characteristics of the light source. 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 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: 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: 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.