Abstract: Methods and systems for image deblurring are described. The weights of a deblurring network are first trained by meta-training the deblurring network on both a primary deblurring task and an auxiliary reconstruction task. Application-time training of the deblurring network is then performed, using an application-time blurry input image, to obtain values of application-time trained weights. Application-time training includes performing the auxiliary reconstruction task on the application-time blurry input image, and updating the weights of the deblurring network based on an auxiliary loss computed from the auxiliary reconstruction task. A deblurred output image is generated from the application-time blurry input image, using the application-time trained weights in the deblurring network.

Abstract: Devices and methods for extracting motion vector data during decoding compressed of video data are described. At a video decoder, an encoded video data for a frame of video from an input buffer is obtained. The encoded video data is decoded to obtain decoded image data for a decoded frame, where the decoding includes extracting corresponding motion vector data for the decoded frame. The decoded image data is stored in a temporary storage indexed with a given index, and the corresponding motion vector data is stored in a same or different temporary storage indexed with the given index. An output buffer indexed with the given index is filled with the decoded image data and the corresponding motion vector data stored in the respective temporary storage indexed with the given index.

Abstract: Methods, devices and computer-readable media for processing a compressed video to perform an inference task are disclosed. Processing the compressed video may include selecting a subset of frame encodings of the compressed video, or zero or more modalities (RGB, motion vectors, residuals) of a frame encoding, for further processing to perform the inference task. Pre-existing motion vector and/or residual information in frame encodings of the compressed video are leveraged to adaptively and efficiently perform the inference task. In some embodiments, the inference task is an action recognition task, such as a human action recognition task.

Abstract: Devices and methods for extracting motion vector data during decoding compressed of video data are described. At a video decoder, an encoded video data for a frame of video from an input buffer is obtained. The encoded video data is decoded to obtain decoded image data for a decoded frame, where the decoding includes extracting corresponding motion vector data for the decoded frame. The decoded image data is stored in a temporary storage indexed with a given index, and the corresponding motion vector data is stored in a same or different temporary storage indexed with the given index. An output buffer indexed with the given index is filled with the decoded image data and the corresponding motion vector data stored in the respective temporary storage indexed with the given index.

Abstract: This disclosure provides for methods and system for meta few-shot class incremental learning. According to an aspect a method is provided. The method includes obtaining at least one weight attention map of a first network and updating weights of a second network using the at least one weight attention map, where the second network is a modulatory network. The method further includes generating at least one feature attention map of the second network based on the at least one weight attention map of the first network and a set of input images of at least one class. The method further includes generating at least one feature map of the first network based on the set of input images of the at least one class, and updating the at least one feature map of the first network based on the feature attention map of the second network.

Abstract: There is provided a method, apparatus and system for adapting a machine learning model for optical flow prediction. A machine learning model can be trained or adapted based on compressed video data, using motion vector information extracted from the compressed video data as ground-truth information for use in adapting the model to a motion vector prediction task. The model so adapted can accordingly be adapted for the similar task of optical flow prediction. Thus, the model can be adapted at test time to image data which is taken from an appropriate distribution. A meta-learning process can be performed prior to such model adaptation to potentially improve the model's performance.

Abstract: A system and a method for performing 2D on-screen user gaze estimation using an input facial image of a user captured using a camera associated to a processing device having a display. The method and system allow automated user calibration through automatic recording of calibration samples each including a calibration facial image of the user and an interaction point corresponding to a point on the display where an occurrence of a user interaction was detected when the corresponding calibration image was captured. The system and method also optimize user-specific parameters using the calibration samples by iteratively minimizing a total difference between the interaction points of a plurality of the calibration samples and corresponding 2D gaze estimation results and convert an estimated 3D gaze direction into a 2D gaze estimation result corresponding to a point on the display, by applying the users-specific parameters.

Abstract: A method, device and computer-readable medium for generating a super-resolution version of a compressed video stream. By leveraging the motion information and residual information in compressed video streams, described examples are able to skip the time-consuming motion-estimation step for most frames and make the most use of the SR results of key frames. A key frame SR module generates SR versions of I-frames and other key frames of a compressed video stream using techniques similar to existing multi-frame approaches to VSR. A non-key frame SR module generates SR version of the non-key inter frames between these key frames by making use of motion information and residual information used to encode the inter frames in the compressed video stream.

Abstract: Methods and devices for generating a slow motion video segment are described. A first set of video frames captures a video view at a first resolution and at a first frame rate. A second set of video frames captures the video view at a second lower resolution, and at a second frame rate that is greater for at least a portion of the second set. At least two high resolution frames are identified in the first set for generating the slow motion video segment. One or more low resolution frames are identified in the second set corresponding to an inter-frame time period between the identified high resolution frames. The slow motion video segment is generated by generating at least one high resolution frame corresponding to the inter-frame time period using interpolation based on the identified high resolution frames and the identified low resolution frames.

Abstract: One or more techniques and/or systems are disclosed for interrupting fluid flow when experiencing fuel leaking conditions, such as an out of specification connection between the fuel source and a device utilizing the fluid. A distal end of a valve body has interfaces with at least a portion of a connection to a fluid supply; and a proximal end interfaces with at least a portion of a fuel intake. An internal passage runs between the proximal end and distal ends of. A displacement member in the internal passage comprises a distal portion that extends out of the valve to engage a valve to the fuel supply. A retention cap selectably engaged with the valve body can comprise a material that deforms under force at a predetermined temperature, resulting in a release of the displacement member under a biasing force form a biasing component between the cap and displacement member.

Abstract: A system and a method for performing 2D on-screen user gaze estimation using an input facial image of a user captured using a camera associated to a processing device having a display. The method and system allow automated user calibration through automatic recording of calibration samples each including a calibration facial image of the user and an interaction point corresponding to a point on the display where an occurrence of a user interaction was detected when the corresponding calibration image was captured. The system and method also optimize user-specific parameters using the calibration samples by iteratively minimizing a total difference between the interaction points of a plurality of the calibration samples and corresponding 2D gaze estimation results and convert an estimated 3D gaze direction into a 2D gaze estimation result corresponding to a point on the display, by applying the users-specific parameters.

Abstract: System and method for managing a user interface for a foldable device are disclosed. The method includes: determining a folding state of the foldable device based on a folding angle of the foldable device; detecting an input gesture on one or more touch-sensitive display segments of a flexible display screen of a foldable device; determining a gesture type corresponding to the detected input gesture; determining whether the detected input gesture is a valid gesture or invalid gesture; and responsive to determining that the detected input gesture is a valid gesture, providing the gesture type corresponding to the detected gesture, the folding state of the foldable device, and display information to a software application or an operating system of the foldable device.

Abstract: Systems, methods and computer-readable medium for predicting a depth for a video frame are disclosed. An example method may include steps of: receiving a plurality of training data, each comprising a set of consecutive video frames and a depth representation of a subsequent video frame to the consecutive video frames; receiving a pre-trained neural network model f? having a plurality of weights ?; while the pre-trained neural network model f? has not converged: computing a plurality of second weights ?i?, based on each set of consecutive video frames, and updating the plurality of weights ?, based on the plurality of training data and the plurality of second weights ?i?; receiving a plurality of new consecutive video frames with consecutive timestamps; and predicting a depth representation of video frame immediately subsequent to the new consecutive video frames based on the updated plurality of weights ?.

Abstract: Systems and methods for multi-frame video frame interpolation. Higher-order motion modeling, such as cubic motion modeling, achieves predictions of intermediate optical flow between multiple interpolated frames, assisted by relaxation of the constraints imposed by the loss function used in initial optical flow estimation. A temporal pyramidal optical flow refinement module performs coarse-to-fine refinement of the optical flow maps used to generate the intermediate frames, focusing a proportionally greater amount of refinement attention to the optical flow maps for the high-error middle frames. A temporal pyramidal pixel refinement module performs coarse-to-fine refinement of the generated intermediate frames, focusing a proportionally greater amount of refinement attention to the high-error middle frames.

Abstract: A method, device, apparatus and computer-readable storage medium for mining an enterprise relationship. The method can include acquiring Internet data of multiple types, identifying enterprise names from the Internet data by an enterprise name identification model, performing data mining to the Internet data in a frequent item mining algorithm to obtain relational degrees among the enterprise names, and according to the relational degrees among the enterprise names, extracting the enterprise relationship from the Internet data by an extractor. A deeper and more comprehensive enterprise relationship can be obtained by performing data mining to Internet data of multiple types by using an enterprise name recognition model. By using the frequent items mining algorithm, enterprises among which there are higher relational degrees can further be obtained, so as to obtain a more accurate enterprise relationship.

Abstract: Methods and systems for determining a surface color of a target surface under an environment with an environmental light source. A plurality of images of the target surface are captured as the target surface is illuminated with a variable intensity, constant color light source and a constant intensity, constant color environmental light source, wherein the intensity of the light source on the target surface is varied by a known amount between the capturing of the images. A color feature tensor, independent of the environmental light source, is extracted from the image data, and used to infer a surface color of the target surface.

Abstract: Methods and systems for image deblurring are described. The weights of a deblurring network are first trained by meta-training the deblurring network on both a primary deblurring task and an auxiliary reconstruction task. Application-time training of the deblurring network is then performed, using an application-time blurry input image, to obtain values of application-time trained weights. Application-time training includes performing the auxiliary reconstruction task on the application-time blurry input image, and updating the weights of the deblurring network based on an auxiliary loss computed from the auxiliary reconstruction task. A deblurred output image is generated from the application-time blurry input image, using the application-time trained weights in the deblurring network.

Abstract: One or more techniques and/or systems are disclosed for interrupting fluid flow when experiencing fuel leaking conditions, such as an out of specification connection between the fuel source and a device utilizing the fluid. A distal end of a valve body has interfaces with at least a portion of a connection to a fluid supply; and a proximal end interfaces with at least a portion of a fuel intake. An internal passage runs between the proximal end and distal ends of. A displacement member in the internal passage comprises a distal portion that extends out of the valve to engage a valve to the fuel supply. A retention cap selectably engaged with the valve body can comprise a material that deforms under force at a predetermined temperature, resulting in a release of the displacement member under a biasing force form a biasing component between the cap and displacement member.

Abstract: Embodiments of the present disclosure disclose a method and apparatus for recommending a video. A specific implementation of the method includes: finding a recommended video corresponding to a target video from all candidate videos based on similarities of content characteristics of the videos, the target video being a video to be played on a terminal of a user; and sending play information of the recommended video corresponding to the target video to the terminal of the user. The method finds a video similar on video content to the target video that the user desires to view based on the content characteristic of the video, and recommends the video similar on video content to the target video that the user desires to view to the user.

Abstract: A method and an apparatus for inspecting a corrosion defect of a ladle are provided. The method includes: acquiring images from various angles using an image acquisition apparatus inside a to-be-inspected ladle; and inputting the acquired images into a defect inspection system to obtain a label representing a defect category, the defect inspection system including: a deep convolutional neural network that predicts a category of a corrosion defect of the ladle included in the images based on the input images. This method has the advantages of high safety, high accuracy and high real-time performance in inspecting the ladle status.