Recently released depth cameras provide effective estimation of 3D positions of skeletal joints in temporal sequences of depth maps. In this work, we propose an efficient yet effective method to recognize human actions based on the positions of joints. First, the body skeleton is decomposed in a set of kinematic chains, and the position of each joint is expressed in a locally defined reference system which makes the coordinates invariant to body translations and rotations. A multi-part bag-of-poses approach is then defined, which permits the separate alignment of body parts through a nearest-neighbor classification. Experiments conducted on the Florence 3D Action dataset and the MSR Daily Activity dataset show promising results.

Image compression is a need that arises in many circumstances. Unfortunately, whenever a lossy compression algorithm is used, artifacts will manifest. Image artifacts, caused by compression tend to eliminate higher frequency details and in certain cases may add noise or small image structures. There are two main drawbacks of this phenomenon. First, images appear much less pleasant to the human eye. Second, computer vision algorithms such as object detectors may be hindered and their performance reduced. Removing such artifacts means recovering the original image from a perturbed version of it. This means that one ideally should invert the compression process through a complicated non-linear image transformation. We propose an image transformation approach based on a feed-forward fully convolutional residual network model. We show that this model can be optimized either traditionally, directly optimizing an image similarity loss (SSIM), or using a generative adversarial approach (GAN). Our GAN is able to produce images with more photorealistic details than SSIM based networks. We describe a novel training procedure based on sub-patches and devise a novel testing protocol to evaluate restored images quantitatively. We show that our approach can be used as a pre-processing step for different computer vision tasks in case images are degraded by compression to a point that state-of-the art algorithms fail. In this case, our GAN-based approach obtains better performance than MSE or SSIM trained networks. Differently from previously proposed approaches we are able to remove artifacts generated at any QF by inferring the image quality directly from data.

Pedestrians and drivers are expected to safely navigate complex urban environments along with several non cooperating agents. Autonomous vehicles will soon replicate this capability. Each agent acquires a representation of the world from an egocentric perspective and must make decisions ensuring safety for itself and others. This requires to predict motion patterns of observed agents for a far enough future. In this paper we propose MANTRA, a model that exploits memory augmented networks to effectively predict multiple trajectories of other agents, observed from an egocentric perspective. Our model stores observations in memory and uses trained controllers to write meaningful pattern encodings and read trajectories that are most likely to occur in future. We show that our method is able to natively perform multi-modal trajectory prediction obtaining state-of-the art results on four datasets. Moreover, thanks to the non-parametric nature of the memory module, we show how once trained our system can continuously improve by ingesting novel patterns.

Effective modeling of human interactions is of utmost importance when forecasting behaviors such as future trajectories. Each individual, with its motion, influences surrounding agents since everyone obeys to social non-written rules such as collision avoidance or group following. In this paper we model such interactions, which constantly evolve through time, by looking at the problem from an algorithmic point of view, i.e., as a data manipulation task. We present a neural network based on an end-to-end trainable working memory, which acts as an external storage where information about each agent can be continuously written, updated and recalled. We show that our method is capable of learning explainable cause-effect relationships between motions of different agents, obtaining state-of-the-art results on multiple trajectory forecasting datasets.