Abstract: A device and a method for recognizing person activity in a sequence of frames (100) comprising: obtaining a set of consecutives 3D poses (103), obtaining a feature map (102), obtaining a vector of spatiotemporal features, obtaining a matrix of spatial attention weights, obtaining a matrix of temporal attention weights (110), modulating (106) the feature map using the matrix of spatial attention weights to obtain a spatially modulated feature map, modulating (111) the feature map using the vector of temporal attention weights to obtain a temporally modulated feature map, performing a convolution (114) of the spatially modulated feature map and of the temporally modulated feature map to obtain a convoluted feature map, performing a classification (115) using the convoluted feature map so as to determine the activity of the person in the video.

Abstract: A grasping points determination method including: S10) receiving a scene image showing an object to be grasped; S20) in the scene image, determine the object and its features, and local descriptors and 2D-locations of these features; S30) based on database local descriptors of features of the object and 2D- and 3D-location(s) of grasping points of the object, determined in a previous position of the object, identifying a best-fit combination which transforms previously defined local descriptors into the determined local descriptors; S40) determining the registration corresponding to the combination; S50) determining in the scene image 2D-location(s) of grasping points by applying registration to previously defined 3D-location(s) of the grasping points; S60) determining 3D information relative to the object; S70) determining 3D-location(s) of the grasping points. Grasping points database creation method for creating the database. Systems for implementing the above methods.

Abstract: A computer-implemented method of estimating a 6D pose and shape of one or more objects from a 2D image, comprises the steps of: detecting, within the 2D image, one or more 2D regions of interest, each 2D region of interest containing a corresponding object among the one of more objects; cropping out a corresponding pixel value array, coordinate tensor , and feature map for each 2D region of interest; concatenating the corresponding pixel value array, coordinate tensor, and feature map for each 2D region of interest; and inferring, for each 2D region of interest, a 4D quaternion describing a rotation of the corresponding object in the 3D rotation group, a 2D centroid, which is a projection of a 3D translation of the corresponding object onto a plane of the 2D image given a camera matrix associated to the 2D, image, a distance from a viewpoint of the 2D image to the corresponding object a size and a class-specific latent shape vector of the corresponding object.