-
11.发明专利
公开(公告)号：GB2541912A
公开(公告)日：2017-03-08
申请号：GB201515631
申请日：2015-09-03
Applicant: NOKIA TECHNOLOGIES OY
Inventor： FRANCESCO CRICRI , JUSSI ARTTURI LEPPANEN , ANTTI JOHANNES ERONEN , ARTO JUHANI LEHTINIEMI
IPC: G06F3/01
Abstract: A method comprising: receiving a request to create a virtual communication channel between the real world and a virtual reality environment, the virtual reality environment comprising both audio and visual content; in response to receiving the request, causing a virtual window to be displayed in the virtual reality environment; and causing distorted audio from real world surroundings of a user making the request to emanate from the virtual window. Further claimed is an apparatus comprising: at least one processor; and at least one memory including computer program code which, when executed by the at least one processor, cause the apparatus to undertake the method described. A further apparatus is claimed comprising the means for undertaking the described method. Yet further claimed is a computer-readable medium having a computer-readable code stored thereon; the computer readable code, when executed by at least one processor, causes performance of at least the method described previously.
-
公开(公告)号：GB2532966A
公开(公告)日：2016-06-08
申请号：GB201421465
申请日：2014-12-03
Applicant: NOKIA TECHNOLOGIES OY
Inventor： ANTTI ERONEN , LIXIN FAN , FRANCESCO CRICRI , SOUNAK BHATTACHARYA
Abstract: A pilotless drone 110 has a wireless transceiver configured to relay information between a user equipment 120 and a base station130, a memory configured to store at least one parameter relating to at least one of: at least one wireless connection, a location of the user equipment, a location of the base station, a geographic feature and an audio signal emitted by the user equipment, and at least one processing core configured to determine navigation information for the pilotless drone based at least in part on the at least one parameter. The drone may navigate to a position based on signal strength of signals from user equipment and/or base station and may take into account stored map information. It may maintain a line of sight communications. Where simultaneous connection to user equipment and base station is not possible the drone may move to alternately enable each wireless connection.
-
公开(公告)号：GB2603515A
公开(公告)日：2022-08-10
申请号：GB202101657
申请日：2021-02-05
Applicant: NOKIA TECHNOLOGIES OY
Inventor： ANTTI JOHANNES ERONEN , FRANCESCO CRICRI
IPC: H04S7/00
Abstract: Apparatus, methods and computer programs for enabling spatial audio rendering that can accommodate movement of a user. This comprises obtaining audio content representing an audio space before enabling a digital signal processing operation to render the audio content such that the rendered audio content comprises at least one target response. The enabling of the digital signal processing operation to render the audio content is controlled based on obtaining the target response for the audio space. When the obtained target response is known the means are for obtaining at least one parameter for the digital signal processing operation and using the obtained parameter to enable the digital signal processing operation to reproduce an acoustic effect with the target response for a user position within audio space. When the obtained target response is unknown the means are for obtaining a separate parameter for a neural network, and using the neural network to determine the parameter for the digital signal processing operation, and using the determined parameter to enable the digital signal processing operation to reproduce an acoustic effect with the target response for the user position within the audio space.
-
公开(公告)号：GB2572537A
公开(公告)日：2019-10-09
申请号：GB201804866
申请日：2018-03-27
Applicant: NOKIA TECHNOLOGIES OY
Inventor： FRANCESCO CRICRI , CAGLAR AYTEKIN , LIXIN FAN
IPC: G06N3/02
Abstract: A method or apparatus of obtaining an updated neural network from a base neural network by obtaining an order of unit (e.g. layer, filter, node) updates and providing the update information to another neural network. The update is based on a metric which may improve the accuracy of a NN task (e.g. NN learning). Identical base neural networks may reside on a server and a remote device (e.g. a mobile phone or an IoT device). The method may be implemented using algorithm 40 which updates each of an i-unit of the n-unit base NN by incrementing the value i and updating the weights of each unit. At each iteration, the units of the NN may be frozen and only the i-th unit is fine tuned. After this step the update information may be sent to the remote device (step 48). The method may provide an improvement in communications and/or data privacy and may be implemented using a cloud-hosted application. A second invention concerns an n-unit NN from an n-unit base NN by updating at least one of a plurality of the n-units.
-
公开(公告)号：GB2558582A
公开(公告)日：2018-07-18
申请号：GB201700265
申请日：2017-01-06
Applicant: NOKIA TECHNOLOGIES OY
Inventor： FRANCESCO CRICRI
IPC: G06F17/30 , H04N21/8543
Abstract: A method of creating a video summary, comprising: analysing, using a neural network, a text description of an input video and an input question; causing production of an attention map based on the text description and the input question; and determining locations of the attention map having the highest attention value. The attention map may be a temporal attention map in that the locations correspond to temporal locations of the map having the highest attention value, a spatial map where the locations correspond to spatial locations with the highest attention value, or a combination thereof. A summary video may then be output with video portions corresponding to the locations with the highest attention values. The text description summary and input questions may be converted into vectors which can be input into the neural network.
-
Patent Agency Ranking
公开(公告)号：GB2545661A
公开(公告)日：2017-06-28
申请号：GB201522482
申请日：2015-12-21
Applicant: NOKIA TECHNOLOGIES OY
Inventor： FRANCESCO CRICRI
Abstract: The invention is directed towards computer vision and machine learning applied to the analysis of media content. A method claim applies to operating a computer graphic system, the method comprising: inputting a media content object (MCO) into a feature extractor comprising semantic abstraction levels; extracting feature maps from said MCO on each of the semantic layers; selecting at least a portion of the MCO to be analysed; determining, based on the analysis of the feature maps from the portion of the MCO and the analysis of a previous state of a recognition unit, one or more feature maps selected from the feature maps of the semantic layers (i.e. focusing attention on a certain maps); determining a weight for each feature map; repeating the determining steps N times, each time processing, based on the analysis, each feature map by applying the corresponding weight; inputting said processed feature maps to the recognition unit; and analysing a number of said processed feature maps until a prediction about the portion of the MCO is output. The feature extractor could be a convolutional neural network.
-
公开(公告)号：GB2590718A
公开(公告)日：2021-07-07
申请号：GB201919440
申请日：2019-12-31
Applicant: NOKIA TECHNOLOGIES OY
Inventor： JUSSI LEPPANEN , MIIKKA VILERMO , FRANCESCO CRICRI , ARTO LEHTINIEMI
IPC: G06F1/16 , A63F13/5378 , G02B27/01 , G06F3/01
Abstract: An apparatus comprising means for: in a first-person perspective mediated reality state (e.g. video game or motion video), rendering mediated reality content as content distributed across a first area of a user’s field of view, wherein a point of view of a user determines a point of view within a three-dimensional virtual space and determines at least part of the content distributed across the first area of a user’s field of view as a virtual scene; responding to at least one user gesture to enter a spatially consolidated state; and in the spatially consolidated state, rendering the mediated reality content as content distributed across a second area of a user’s field of view, wherein the second area is smaller than the first area and the point of view of the user does not determine the content distributed across the second area of a user’s field of view.
-
公开(公告)号：GB2589340A
公开(公告)日：2021-06-02
申请号：GB201917244
申请日：2019-11-27
Applicant: NOKIA TECHNOLOGIES OY
Inventor： JUSSI LEPPÃNEN , MIIKKA VILERMO , ARTO JUHANI LEHTINIEMI , FRANCESCO CRICRI
Abstract: A method, apparatus and computer program is described comprising: generating or obtaining an augmented reality image for presentation to a user; attenuating real-world audio of the augmented reality system before controlling the provision of audio to the user in at least one direction relating a selected real-world object – preferably said audio is real-world audio. Preferably virtual audio is also generated and presented to the user, said virtual audio being associated with the virtual object. In a preferred embodiment, an imaging system is used to determine the dimensions of at least one of the selected real-world objects and then controlling the real-world audio in dependence upon said dimensions. The dimensions may also be input by a user. Preferably real-world objects which interact with the virtual objects are identified.
-
公开(公告)号：GB2568690A
公开(公告)日：2019-05-29
申请号：GB201719425
申请日：2017-11-23
Applicant: NOKIA TECHNOLOGIES OY
Inventor： FRANCESCO CRICRI , KIMMO ROIMELA , JOHANNES PYSTYNEN
Abstract: A method of displaying video content comprises: receiving video content comprising an area of interest 410, wherein the area of interest is received with a first quality and the area outside of the area of interest is received with a second lower quality; displaying the video content 420; receiving viewing direction of a user 430; determining a current focus area of the user based on their viewing direction 440; and decreasing the quality of a video region corresponding to the current focus area of the user if it is outside of the area of interest 450. The viewing direction data may comprise gaze direction data of the user. The video content may be 360 video content and may be displayed in a head mounted display (HMD). Decreasing the quality of a video region may comprise decreasing resolution or bitrate, or removing an object. A method of providing video for transmission comprises: obtaining information on area(s) of interest within video content and providing the video content from transmission, wherein the area(s) of interest are provided with a first quality and the area outside of the area(s) of interest is provided with a second lower quality.
-
公开(公告)号：GB2562488A
公开(公告)日：2018-11-21
申请号：GB201707792
申请日：2017-05-16
Applicant: NOKIA TECHNOLOGIES OY
Inventor： FRANCESCO CRICRI , MIIKA TUPALA
IPC: G06T15/08
Abstract: A method for analyzing a presence of objects within a space provided with a capturing system comprising a plurality of camera devices and a playback system for reproducing audio and/or visual signals in the space, the method comprising obtaining a first 3D volumetric representation of a scene within the space, generated on the basis of input streams of at least a first and a second camera device, said first 3D volumetric representation showing at least one object within the scene 500; sending probe signals to a processing unit 502; controlling the processing unit to reproduce, using the playback system, one or more audio and/or visual signals on the basis of the probe signals into the space 504; controlling the processing unit to capture a second 3D volumetric representation of the scene including reproductions of the one or more audio and/or visual signals within the space 506; and analyzing the reproductions of the one or more audio and/or visual signals captured within the first space whether they correspond to a presumed location of the at least one object shown in the first 3D volumetric representation 508. The invention addresses AI being used to in-paint non-existing objects within the volumetric reconstruction.
-
-
-
-
-
-
-
-
-
Search Results
28
records
(took 0.025 seconds)
