Abstract: Video decoder adapted for decoding video based on decoder parameters selected from variable decoder parameters, the decoder comprising an estimator adapted to estimate user viewing experience based on sensor data and comprising a constraint analyzer adapted to analyze constraints when using the decoder parameters, the video decoder further comprising a selector adapted to select said decoder parameters from the variable decoder parameters, wherein the selector is coupled to the estimator and the constraint analyzer.

Abstract: A transmitter for generating a set of encoded prioritized video streams from an incoming video stream (Vin) comprises: —a video decomposition module (VD) for decomposing said incoming video stream in at least two independent video components in spectral or time-spatial/spectral domain (Vd1, . . . , Vdn), —a compression module for compressing said at least two independent video components, thereby obtaining at least two compressed independent video components (Vde1, . . . , Vden), —a multi-stream packetization and prioritization module (MPP) for generating for each of said at least two compressed independent video components a respective set of packet streams in respective different qualities Vde1q1, . . . , Vde1q1, . . . , Vdenq1, . . .

Abstract: Video decoder adapted for decoding video based on decoder parameters selected from variable decoder parameters, the decoder comprising an estimator adapted to estimate user viewing experience based on sensor data and comprising a constraint analyzer adapted to analyze constraints when using the decoder parameters, the video decoder further comprising a selector adapted to select said decoder parameters from the variable decoder parameters, wherein the selector is coupled to the estimator and the constraint analyzer.

Abstract: The present invention relates to a method, system and related devices for annotating an object in a multimedia asset, where the multimedia asset comprises at least one image. The method comprises the steps of first determining a category of the object in an image of the multimedia asset by means of classifying the object and subsequently selecting based on the category of the object an appropriate object detector model from at least one object detector model associated with said category. Thereafter a location of the object in the image of the multimedia asset is determined based on the object detector model that is selected, where the object detector model corresponds to the object which step is followed by segmenting the object detected in the image of the multimedia asset based on the location of the object within the said image and optionally based on the object detector. Finally, the object within the image being segmented is annotated with a hyperlink.

Abstract: A method and device for determining at least one set of matching attributes between a plurality of images is disclosed. Two dimensional images are projected to a three dimensional space then searched for matching attributes. Searching for corresponding attributes is much easier and computationally less intensive in the 3D space compared to a search in the 2D space. The method includes steps of projecting at least part of the images of said plurality to a 3-dimensional space resulting in a plurality of 3-D projected images (image1_3D, image2_3D), searching for at least one corresponding set of elements within the 3D projected images of the plurality of 3-D projected images, and calculating back said corresponding elements within the original images of the plurality and providing said corresponding elements within said original images as said at least one set of matched attributes.

Abstract: The present invention relates to a method, system and related devices for annotating an object in a multimedia asset, where the multimedia asset comprises at least one image. The method comprises the steps of first determining a category of the object in an image of the multimedia asset by means of classifying the object and subsequently selecting based on the category of the object an appropriate object detector model from at least one object detector model associated with said category. Thereafter a location of the object in the image of the multimedia asset is determined based on the object detector model that is selected, where the object detector model corresponds to the object which step is followed by segmenting the object detected in the image of the multimedia asset based on the location of the object within the said image and optionally based on the object detector.

Abstract: The invention relates to a system and method for tag based access to auxiliary information during a video- and/or audio-conference. The system comprises a mapping between tags and associated portions of auxiliary information. The method may comprise transmitting video data and/or or audio data from the video- and/or audio-conferencing system to participants of the video-conference. During the transmission tags may be extracted from the video data and/or audio data. As soon as a request for auxiliary information is received from a participant, the method may comprise selecting at least one of the tags extracted from the transmitted video data and/or audio data, retrieving at least one auxiliary information portion associated with the selected at least one tag, and transmitting the at least one retrieved auxiliary information portion to the participant that has requested the auxiliary information.

Abstract: Embodiments relates to a method for rotating a multidimensional space and a device for rotating a multidimensional space. The method may comprise:—obtaining (S1) 2D coordinates of a first point (p1) and a second point (p2) of a 2D visualization space input by a user,—determining (S2) a first D-dimensional vector (p1) and a second D-dimensional vector (p2) by projecting said first point (p1) and said second point (p2) into a D-dimensional space, wherein D is equal to or greater than 4,—determining (S3) a rotation matrix (R) in function of said first D-dimensional vector (p1) and said second D-dimensional vector (p2). The D-dimensional space has a first dimension, a second dimension and D-2 other dimensions, and the 2D visualization space has D-2 predefined regions associated with respective dimensions among said D-2 other dimensions.

Abstract: A method for constructing an image model (M1; M) from at least one image data input (IV1; IV1-IVn), comprises the steps of, in an iterative way, determining at least one state (PS1; PS1-PSn) of said at least one image data input (IV1; IV1-IVn), and a state (PSMF) of an intermediate learning model (MF; MIF) determining a target state (TSP) from said at least one state (PS1; PS1-PSn) of said at least one image data input, and from the state (PSMF) of said intermediate learning model (MF; MIF), performing at least one transformation in accordance with the determined target state (TSP) on said at least one image data input (IV1; IV1-IVn), thereby generating at least one transformed image (IV1T; IV1T-IVnT), aggregating said at least one transformed image (IV1T; IV1T-IVnt) with intermediate learning model (MF; MIF; MIT; MFT) information, thereby generating an updated estimate of said image model (M1; M), providing said updated estimate of said image model (M1; M) as said image model (M1; M) while also providing

Abstract: A method for determining calibration data for at least two cameras (camera1, camera2) in a multi view position, includes a step of determining respective parameters ((h100, . . . , h122), (h200, . . . , h222)) for identifying at least one respective homographic transformation on respective images (image1,image2) taken by said cameras of a same scene, by performing respective geometry analyses on said respective images (image1, image2), a step of performing at least one respective combined homographic transformation/feature detection step on said respective images thereby obtaining respective sets (feature set1, feature set2) of features on respective transformed images, such that said calibration data are obtained from matches (ml, . . . , mk) determined between said respective sets of features.

Abstract: Method for adapting a 3D model (m) of an object, said method comprising the steps of performing at least one projection of said 3D model to obtain at least one 2D image model projection (p1) with associated depth information (d1), performing at least one state extraction operation on said at least one 2D image model projection (p1), thereby obtaining at least one state (s1) adapting said at least one 2D image model projection (p1) and said associated depth information (d1) in accordance with said at least one state (s1) and with a target state (s), thereby obtaining at least one adapted 2D image model (p1?) and an associated adapted depth (d1?) back-projecting said at least one adapted 2D image model (p1?) to 3D, based on said associated adapted depth (d1?) for thereby obtaining an adapted 3D model (m?).

Abstract: An exemplary method of providing a virtual representation includes determining a plurality of position constraints that correspond to physical positions of individuals relative to each other. A plurality of determined viewing constraints each correspond to a position of one of the individuals relative to a display used by that individual for viewing the virtual representation. Relative positions of virtual representations of the individuals in the virtual representation are determined to correspond to the determined position and viewing constraints.

Abstract: A feedback-system for managing the position of a frontal camera provided on a portable multimedia device during video communication. The feedback-system comprises a camera image analyzer coupled to the frontal camera and adapted to detect and analyze the pose of a user facing the frontal camera, an optimal video estimator coupled to the camera image analyzer and adapted to calculate a 6-dimensional error-vector of the current position of the frontal camera with respect to an optimal position of the frontal camera, an intuitive feedback manager coupled to the optimal video estimator and adapted to generate a transformation matrix translating the error-vector into an error message for the image displayed on a screen of the portable multimedia device, the intuitive feedback manager being further coupled to the portable multimedia device which is adapted to use the error message for modifying the image displayed on the screen.

Abstract: A method for adapting video data (video room1) recorded by a camera on a location (room1) during a video conference such as to hide the presence of a participant at said location of said video conference, comprises a step of registering a predefined gesture possibly to be performed by any participant of said video conference at said location (room1), a step of detecting said gesture, and upon detection thereof, identifying the at least one participant having performed said gesture at said location (room1), adapting said video data such as to eliminate data relating to said at least one participant having performed said gesture from said video data, thereby generating adapted video data (videoa room1), for being transmitted to other participants of said video conference on other locations (room2, . . . , roomn).

Abstract: A method for generating a 3D model from at least one image data input (P1, R1(cam1); . . . ; Pn, Rn(camn)) comprising 2D+z+reliability information comprises the steps of building a 3D surface from said at least one image data input, followed by a meshing operation in 3D on said 3D surface to thereby generate said 3D model.

Abstract: The invention pertains to a method for segmenting an image from a sequence of video images into a foreground and a background, the image being composed of pixels, the method includes assigning an initial foreground probability to each of the pixels; assigning a set of probability propagation coefficients to each of the pixels; and applying a global optimizer to the initial foreground probabilities of the pixels to classify each of the pixels as a foreground pixel or a background pixel, to obtain a definitive foreground map; wherein the global optimizer classifies each processed pixel in function of the initial foreground probability of the processed pixel and the initial foreground probability of neighboring pixels, the relative weight of the initial foreground probability of neighboring pixels being determined by the probability propagation coefficients of the neighboring pixels.

Abstract: An exemplary technique is provided for obtaining an improved depth precision for a stereo image of an object of interest. The technique includes imaging a first image of the object of interest from a first position, imaging a second image of the object of interest from a second position different from the first position, determining a rough estimate of a depth for the object of interest based on the first image and the second image, determining an improved set of imaging positions corresponding to an improved depth precision for the object of interest based on the rough estimate of the depth, imaging improved images from the improved set of imaging positions, and determining an improved depth based on the improved images.

Abstract: A system and method for three-dimensional (3D) model morphing is disclosed. Morphing a standard 3D model based on 2D image data input includes the steps of performing an initial morphing of said standard 3D model using a detection model and a morphing model, thereby obtaining a morphed standard 3D model; determining the optical flow between the 2D image data input and the morphed standard 3D model, and applying the optical flow to said morphed standard 3D model, thereby providing a fine tuned 3D standard model.

Abstract: Method for adapting a 3D model (m) of an object, said method comprising the steps of performing at least one projection of said 3D model to obtain at least one 2D image model projection (p1) with associated depth information (d1), performing at least one state extraction operation on said at least one 2D image model projection (p1), thereby obtaining at least one state (s1) adapting said at least one 2D image model projection (p1) and said associated depth information (d1) in accordance with said at least one state (s1) and with a target state (s), thereby obtaining at least one adapted 2D image model (p1?) and an associated adapted depth (d1?) back-projecting said at least one adapted 2D image model (p1?) to 3D, based on said associated adapted depth (d1?) for thereby obtaining an adapted 3D model (m?).

Abstract: A method for constructing an image model (M1; M) from at least one image data input (IV1; IV1-IVn), comprises the steps of, in an iterative way, determining at least one state (PS1; PS1-PSn) of said at least one image data input (IV1; IV1-IVn), and a state (PSMF) of an intermediate learning model (MF; MIF) determining a target state (TSP) from said at least one state (PS1; PS1-PSn) of said at least one image data input, and from the state (PSMF) of said intermediate learning model (MF; MIF), performing at least one transformation in accordance with the determined target state (TSP) on said at least one image data input (IV1; IV1-IVn), thereby generating at least one transformed image (IV1T; IV1T-IVnT), aggregating said at least one transformed image (Iv1T; IV1T-IVnt) with intermediate learning model (MF; MIF; MIT; MFT) information, thereby generating an updated estimate of said image model (M1; M), providing said updated estimate of said image model (M1; M) as said image model (M1; M) while also providing