Abstract: An electronic device and a method for controlling thereof are provided. A method for controlling an electronic device according to the disclosure includes obtaining a plurality of images for performing clustering, obtaining a plurality of target areas corresponding to each of the plurality of images, obtaining a plurality of feature vectors corresponding to the plurality of target areas, obtaining a plurality of central nodes corresponding to the plurality of feature vectors, obtaining neighbor nodes associated with each of the plurality of central nodes, obtaining a subgraph based on the plurality of central nodes and the neighbor nodes, identifying the connection probabilities between the plurality of central nodes of the subgraph and the neighbor nodes of each of the plurality of central nodes based on a graph convolutional network, and clustering the plurality of target areas based on the identified connection probabilities.

Abstract: Optical flow information is determined and used to identify a video clip from among a sequence of frames. The video clip may be identified based on motion features derived in part from the optical flow information. In some embodiments, semantic information is concatenated with the motion features derived from the optical flow information.

Abstract: The present disclosure provides methods, apparatuses, and computer-readable mediums for image processing. In some embodiments, a method of image processing includes acquiring, from a user, a first image. The method further includes removing, using an image de-filter network, a filter effect applied to the first image to generate a second image. The method further includes obtaining, based on the first image and the second image, an image filter corresponding to the filter effect. The method further includes rendering a third image using the obtained image filter to output a fourth image.

Abstract: An action localization method, device, electronic equipment, and computer-readable storage medium are provided. The action localization method includes: identifying at least one target video segment containing a target object in a video; acquiring a first action recognition result of at least one image frame in the at least one target video segment and a second action recognition result of the target video segment; and acquiring an action localization result of the video based on the first action recognition result and the second action recognition result.

Abstract: An image processing method, an image processing apparatus, an electronic device, and a computer-readable storage medium, relating to the technical field of image processing are provided. The image processing method may include performing blur classification on pixels of an image to obtain a classification mask image; and determining a blurred area of the image based on the classification mask image.

Abstract: An electronic device and a method for controlling thereof are provided. A method for controlling an electronic device according to the disclosure includes obtaining a plurality of images for performing clustering, obtaining a plurality of target areas corresponding to each of the plurality of images, obtaining a plurality of feature vectors corresponding to the plurality of target areas, obtaining a plurality of central nodes corresponding to the plurality of feature vectors, obtaining neighbor nodes associated with each of the plurality of central nodes, obtaining a subgraph based on the plurality of central nodes and the neighbor nodes, identifying the connection probabilities between the plurality of central nodes of the subgraph and the neighbor nodes of each of the plurality of central nodes based on a graph convolutional network, and clustering the plurality of target areas based on the identified connection probabilities.

Abstract: A display control apparatus includes the following elements. An accepting unit accepts selection of one of objects displayed in a window in either a cursor mode, in which a cursor is moved to select an object, or a pointer mode, in which a pointer is moved to select an object, one of the modes being selected by a user. When an instruction to switch the pointer mode to the cursor mode is given, a display control unit erases the pointer and displays the cursor such that the cursor selects an object closest to a position where the pointer was displayed just before being erased.

Abstract: An information processing apparatus includes a detector and a display controller. The detector detects a user operation performed by using a first input interface and a user operation performed by using a second input interface. When the detector detects that an operation using the second input interface has been performed while a predetermined screen is displayed on the basis of detection of an operation using the first input interface, the display controller changes the predetermined screen to a screen containing an object indicating that the object can be operated by an operation using the second input interface.

Abstract: An information processing apparatus that allows a display to show a plurality of windows on a same screen is disclosed. The information processing apparatus includes: a detecting means for detecting a signal sent in response to a press of a button allocated on a remote controller; a control means for outputting to an operating system a signal indicating that a first key and a second key provided on a keyboard are pressed and allowing the operating system to switch a representation on the display when the detecting means detects that a first button provided on the remote controller is pressed in accordance with a state of the representation on the display; and a measuring means for measuring a time period from the detection of a signal corresponding to the press of the first button.

Abstract: An information processing apparatus that allows a display to show a plurality of windows on a same screen is disclosed. The information processing apparatus includes: a detecting means for detecting a signal sent in response to a press of a button allocated on a remote controller; a control means for outputting to an operating system a signal indicating that a first key and a second key provided on a keyboard are pressed and allowing the operating system to switch a representation on the display when the detecting means detects that a first button provided on the remote controller is pressed in accordance with a state of the representation on the display; and a measuring means for measuring a time period from the detection of a signal corresponding to the press of the first button.

Abstract: An information processing apparatus includes a detector and a display controller. The detector detects a user operation performed by using a first input interface and a user operation performed by using a second input interface. When the detector detects that an operation using the second input interface has been performed while a predetermined screen is displayed on the basis of detection of an operation using the first input interface, the display controller changes the predetermined screen to a screen containing an object indicating that the object can be operated by an operation using the second input interface.

Abstract: A display control apparatus includes the following elements. An accepting unit accepts selection of one of objects displayed in a window in either a cursor mode, in which a cursor is moved to select an object, or a pointer mode, in which a pointer is moved to select an object, one of the modes being selected by a user. When an instruction to switch the pointer mode to the cursor mode is given, a display control unit erases the pointer and displays the cursor such that the cursor selects an object closest to a position where the pointer was displayed just before being erased.

Abstract: An information processing apparatus including recording section for recording information on a feed of an RSS format, converting section where a picture contained in each feed whose information is recorded in the recording means is converted into a picture having a predetermined size on a basis of the number of vertical pixels, and display controlling section for displaying, for each feed, a title and a main text by predetermined numbers of rows, and a picture obtained through conversion by the converting means at a predetermined position, when a predetermined operation is performed in a state where a list of feed titles is displayed.