Abstract: A method for performing audio inpainting, wherein missing portions in an input audio signal are recovered and a recovered audio signal is obtained, comprises computing a Short-Time Fourier Transform (STFT) on portions of the input audio signal, computing conditional expectations of the source power spectra of the input audio signal, wherein estimated source power spectra P(f, n, j) are obtained and wherein the variance tensor V and complex Short-Time Fourier Transform (STFT) coefficients of the input audio signals are used, iteratively re-calculating the variance tensor V from the estimated power spectra P(f, n, j) and re-calculating updated estimated power spectra P(f, n, j), computing an array of STFT coefficients ? from the resulting variance tensor V according to ?(f, n, j)=E{S(f, n, j)|x, Is, IL, V}, and converting the array of STFT coefficients ? to the time domain, wherein coefficients {tilde over (s)}1, {tilde over (s)}2, . . . , {tilde over (s)}j of the recovered audio signal are obtained.

Abstract: A method of reducing a large amount of media into a sub-group of high quality images in order to capture the diversity of an event. The present invention teaches a method of reducing a plurality of media into clusters in response to time and place. The clusters are further reduced in response to content in said media, including color and facial recognition to transmit still generate highlights. Near duplicate images are then removed from each highlight and then a high quality image is selected from each highlight. The high quality image is selected from each highlight and combined into an event overview to represent the diversity of an event.

Abstract: A method for encoding multiple audio signals comprises random sampling and quantizing each of the multiple audio signals, and encoding the sampled and quantized multiple audio signals as side information that can be used for decoding and separating the multiple audio signals from a mixture of said multiple audio signals. A method for decoding a mixture of multiple audio signals comprises decoding and demultiplexing side information, the side information comprising quantized samples of each of the multiple audio signals, receiving or retrieving from any data source a mixture of said multiple audio signals, and generating multiple estimated audio signals that approximate said multiple audio signals, wherein said quantized samples of each of the multiple audio signals are used.

Abstract: A method is proposed for encoding at least two signals. The method includes mixing the at least two signals in a mixture; sampling a map Z representative of locations of the at least two signals in a time-frequency plane at sampling locations, the sampling delivering a first list of values Z?; and transmitting the mixture of the at least two signals and information representative of the first list of values Z?. The disclosure also relates to the corresponding method for separating signals in a mixture, and corresponding computer program products, devices and bitstream.

Abstract: A method to determine a chromatic component of illumination sources of an image is described. The method includes segmenting the image into segmenting areas and clustering representative color variations into chrominance clusters. For each segmenting area at least one representative color variation is computed between pixels positioned in the segmenting area. In each chrominance cluster, a principal direction along which representative color variations of this chrominance cluster have the highest luminance variation components, the chromatic components of the intersection of this principal direction with the plane of highest luminance being then considered as the chromatic component of the illumination source of this chrominance cluster.

Abstract: The present disclosure relates to image recognition or image searching. More precisely, the present disclosure relates to pruning local descriptors extracted from an input image. The present disclosure proposes a system, method and device directed to the pruning of local descriptors extracted from image patches of an input image. The present disclosure prunes local descriptors assigned to a codebook cell, based on a relationship of the local descriptor and the assigned codebook cell. The present disclosure includes assigning a weight value for use in pruning based on the relationship of the local descriptor and the assigned codebook cell. This weight value is then used during the encoding of the local descriptors for use in image searching or image recognition.

Abstract: A method for retrieving at least one search image matching a query image commences by first extracting a set of search images. The query image is encoded into a query image feature vector and the search images are encoded into search image feature vectors using an optimized encoding process that makes use of learned encoding parameters. The Euclidean distances between the query image feature vector and the search image feature vectors are then computed. The search images are ranked based on the computed distances; and at least one highest-ranked search image is retrieved.

Abstract: The invention concerns a method for determining zones in images captured by the camera embedded in a handheld mobile device. An object in front of the camera is captured and a stream of images captured by said camera is generated, said object appearing in the visual content of said images stream. The method comprises a step of analysis the visual content of the image stream and a step of determining at least one zone in each analyzed image, the zone said “stable” having visual similarity with a zone in each or most of the other images in the stream, said stable zone identifying the object taken by the mobile device. In this manner, the number of zone identifying the object decreases and the matching between a query image and images read from databases is quicker. Moreover, the processing and storage complexity of the index system is more efficient, as well as the geometric verification performed during the matching of images.

Abstract: The present disclosure relates to a method, adapted to be implemented in an electronic device, for selecting a content, during a backup operation, amongst a plurality of contents coding audiovisual data and being accessible by the electronic device. According to one embodiment, the method includes obtaining, for each accessible content, one audiovisual descriptor derived from the audiovisual data, and selecting the accessible content according to one backup rule taking into account the obtained audiovisual descriptor. The present disclosure also relates to corresponding electronic device, system, computer readable program product and computer readable storage medium.

Abstract: A computer-implemented method of characterizing molecular diffusion within a body from a set of diffusion-weighted magnetic resonance signals by computing a weighted average of a plurality of multi-compartment diffusion models comprises a same number of compartments, fitted to a set of diffusion-weighted magnetic resonance signals, the weighted average being computed using weights representative of a performance criterion of each of the models; wherein each of the multi-compartment diffusion models comprises a different number of subsets of compartments, the compartments of a same subset being identical to each other.

Abstract: A method and an apparatus for determining an orientation of a video are suggested. The method comprises the steps of: estimating a motion of the video; extracting translation-based parameters from the estimated motion of the video; and computing at least one feature giving the evolution of the horizontal translation over time against the evolution of the vertical translation according to the translation based parameters, the feature being used for determining the orientation of the video.

Abstract: A device and a method for online storage, device and method for searching for similar content, a device and a method of transmission and a device and a method. Encrypted data is saved at a provider of online services. With the encrypted data, encrypted hashing data is saved with a public key and the content to save is encrypted with the encrypted hash. This advantageously enables data duplication at the online service provider to be prevented while preserving the private life of the users of the service. In order to search for content similar to reference multimedia data, fingerprints are also saved at the service provider. In order to limit the number of false positives returned, the fingerprint can further contain a search fingerprint, an encrypted selection fingerprint.

Abstract: The invention relates to a method for inpainting a target area in a target video. The method comprises obtaining a multi-resolution representation of the target video, comprising for each resolution, a first video representative of the colors of the target video and a second video representative of the textures of the target video; and for each resolution, reconstructing first and second video in the target area using an information representative of both colors and textures such as to inpaint the target area. The method also relates to a graphics processing unit and to a computer program product for implementing the inpainting method.

Abstract: A method and apparatus for controlling example-based image manipulation are disclosed where selection of example imagery and workpiece imagery is done with a pointing device and an act of motion thereof. For increasing the efficiency of controlling, selection of an image characteristic to be transferred is derived from an interaction sensed on a second input device during a time interval of the act of motion of the pointing device.

Abstract: A temporal section that is defined by boundary images is selected in a video sequence. A maximum of k stable image frames are selected in the temporal section of image frames having a lowest temporal activity. Image fingerprints are computed from the selected stable image frames. A mega-frame image fingerprint data structure is constructed from the computed fingerprints.

Abstract: A method and a module for segmenting a foreground region from a background region in a 3D scene captured by n capturing devices. A reduced number of 3D samples are selected in the scene. These 3D samples are projected in each captured image. Foreground probability and background probabilities are computed for each selected 3D sample based on color models and the projection of these samples in the images These probabilities are used to update the color models. These probabilities are then re-computed based on the updated color models. These steps are reiterated until the color models or the foreground and background probabilities of the selected 3D samples converge. A final segmentation is computed using foreground color models and foreground and background probabilities.

Abstract: A method and a system of audio retrieval and source separation are described. The method comprises the steps of: receiving a textual query; retrieving a preliminary audio sample from an auxiliary audio database; retrieving a target audio sample from a target audio database; and separating the retrieved target audio sample into a plurality of audio source signals. The corresponding system comprises an input unit, a storing unit and a processing unit to implement the method.

Abstract: The present invention relates to a method for providing a summary of an audiovisual object. The method comprises the steps of: capturing information from the audiovisual object; identifying the audiovisual object; determining the time index of the captured information relative to the audiovisual object; and providing a summary of a portion of the identified audiovisual object, the portion being comprised between the beginning and the determined time index of the identified audiovisual object.

Abstract: A method for generating image descriptors for media content of images represented by a set of key-points, fn, is recommended which determines for each key-point of the image, designated as a central key-point, a neighbourhood of other key-points, fml, whose features are expressed relative to those of the central key-point. A sparse photo-geometric descriptor, SPGD, of each key-point in the image being a representation of the geometry and intensity content of a feature and its neighbourhood is provided to perform an efficient image querying for efficient searches. The approach demonstrates that incorporating geometrical constraints in image registration applications does not need to be a computationally demanding operation carried out to refine a query response short-list.

Abstract: A ballot processing device flashes one or more lights of the ballot processing device in a first color when the ballot processing device is ready to receive a ballot. The ballot processing device lights a portion of the one or more lights of the ballot processing device in a second color when the ballot processing device is not ready to receive a ballot.