-
Convolutional neural networks have achieved state-of-the-art results in numerous tasks such as objection detection and face verification. Recent works explore the development of architectures, which is a key point for improving the performance in convolutional neural networks. It has been demonstrated that deeper architectures achieve better results. However, they are computationally expensive, present a large number of parameters and consume considerable memory. To handle this problem, recent approaches have proposed pruning methods, which consist of finding and removing unimportant filters in these networks.
-
Human activity recognition based on wearable sensors has received great attention in areas such as healthcare, homeland security and smart environments, mainly because it enables easy data acquisition and processing. This task consists of assigning a category of activity to signals provided by wearable sensors such as accelerometers, gyroscopes and magnetometers.
-
Unlike fixed cameras, which are limited to a static view of the scene, active cameras are capable of changing their view by means of, for instance, rotation (pan and tilt) and zoom. Cameras with these particular capabilities are known as PTZ (pan-tilt-zoom) cameras, and are widely employed in surveillance for viewing and tracking under dynamic conditions. By shifting to and zooming on a target, PTZ cameras can capture fine-grained detail, such as face and hands.
-
Based on perceptual, compositional and contextual features employed to assign importance to elements in a scene, we investigate approaches to model how humans attribute importance to elements in a scene.
-
Activity Recognition is a challenging problem that has attracted the attention of the research community due to its practical applications, such as human computer interfaces, content based video indexing, video surveillance and robotics, among others. A definition for such task can be described as labeling video segments containing human motion with activity classes. For instance, we can define an activity as a composition of one or more actions organized temporally.
-
Convolutional neural networks have achieved state-of-the-art results in numerous tasks such as objection detection and face verification. Recent works explore the development of architectures, which is a key point for improving the performance in convolutional neural networks. It has been demonstrated that deeper architectures achieve better results. However, they are computationally expensive, present a large number of parameters and consume considerable memory. To handle this problem, recent approaches have proposed pruning methods, which consist of finding and removing unimportant filters in these networks.
-
Human activity recognition based on wearable sensors has received great attention in areas such as healthcare, homeland security and smart environments, mainly because it enables easy data acquisition and processing. This task consists of assigning a category of activity to signals provided by wearable sensors such as accelerometers, gyroscopes and magnetometers.
-
Unlike fixed cameras, which are limited to a static view of the scene, active cameras are capable of changing their view by means of, for instance, rotation (pan and tilt) and zoom. Cameras with these particular capabilities are known as PTZ (pan-tilt-zoom) cameras, and are widely employed in surveillance for viewing and tracking under dynamic conditions. By shifting to and zooming on a target, PTZ cameras can capture fine-grained detail, such as face and hands.
-
Based on perceptual, compositional and contextual features employed to assign importance to elements in a scene, we investigate approaches to model how humans attribute importance to elements in a scene.
-
Activity Recognition is a challenging problem that has attracted the attention of the research community due to its practical applications, such as human computer interfaces, content based video indexing, video surveillance and robotics, among others. A definition for such task can be described as labeling video segments containing human motion with activity classes. For instance, we can define an activity as a composition of one or more actions organized temporally.