712 research outputs found
Guest Editorial : Learning with Manifolds in Computer Vision
No full textEditorial of special issue of the IVC journa
Computer Vision in Human Analysis: From Face and Body to Clothes
No full textFor decades, researchers of different areas, ranging from artificial intelligence to computer vision, have intensively investigated human-centered data, i.e., data in which the human plays a significant role, acquired through a non-invasive approach, such as cameras. This interest has been largely supported by the highly informative nature of this kind of data, which provides a variety of information with which it is possible to understand many aspects including, for instance, the human body or the outward appearance. Some of the main tasks related to human analysis are focused on the body (e.g., human pose estimation and anthropocentric measurement estimation), the hands (e.g., gesture detection and recognition), the head (e.g., head pose estimation), or the face (e.g., emotion and expression recognition). Additional tasks are based on non-corporal elements, such as motion (e.g., action recognition and human behavior understanding) and clothes (e.g., garment-based virtual try-on and attribute recognition). Unfortunately, privacy issues severely limit the usage and the diffusion of this kind of data, making the exploitation of learning approaches challenging. In particular, privacy issues behind the acquisition and the use of human-centered data must be addressed by public and private institutions and companies.
Thirteen high-quality papers have been published in this Special Issue and are summarized in the following: four of them are focused on the human face (facial geometry, facial landmark detection, and emotion recognition), two on eye image analysis (eye status classification and 3D gaze estimation), five on the body (pose estimation, conversational gesture analysis, and action recognition), and two on the outward appearance (transferring clothing styles and fashion-oriented image captioning). These numbers confirm the high interest in human-centered data and, in particular, the variety of real-world applications that it is possible to develop
Joint ACM workshop on human gesture and behavior understanding (J-HGBU'11)
No full textThe ability to understand social signals of a person we are communicating with is the core of social intelligence. Social Intelligence is a facet of human intelligence that has been argued to be indispensable and perhaps the most important for success in life. At the same time, human-centric multimedia applications for humans and about humans are becoming increasingly important. 3D modeled human-objects, like bodies, heads and faces are exploited for animation, security, and human computer interaction, while three dimensional motion of arms, legs and local body features is used for more complete human gesture, activity and behavior analysis. The Joint Human Gesture and Behavior Understanding (J-HGBU) workshop event consists of two parts focusing on these complementary challenges: the Workshop on Multimedia Access to 3D Human Objects (MA3HO'11) and the Workshop on Social Signal Processing (SSPW'11). © 2011 ACM
Bonding in the CuCH4+ and FeCO+ cations
No full textThe electronic structures and geometrical parameters of the CuCH4+ and FeCO+ adducts as observed in mass spectroscopy experiments for instance, were determined by means of ab initio LCGO-SCF and perturbation CI calculations. These cations are predicted to be stable complexes in which the bonding between metal and ligand is mainly due to electrostatic factors, in accordance with previous results for the great majority of ML+ complexes
An Adaptation of E-learning Standards to M-learning
No full textThe exploitation of technological advances in learning has result in an exponential progress in this field through e-learning applications in the last decade, and currently through the emergence of a new concept called m-learning. M-learning is defined as the use of mobile technologies for learning; m-learning must benefit from e-learning technological advances in order to avoid reinventing the wheel. Nevertheless, m-learning, which is characterized by the use of mobile devices, permits, for example, the learners' mobility during their learning, and, as opposed to e-learning, allows a continuous change of the context. Moreover, m-learning faces some constraints caused by the use of its mobile technologies such as the limited screen size, reduced energy, resolution capacity and location change during an activity. Yet, there is an agreement among most research laboratories interested in e- and m- learning on the parallel use of these two learning environments. Therefore, it would be more sensible to allow communication and exchanges, to facilitate the sharing of learning subject matters and data between the two environments, and thereby to avoid the reproduction of contents that already exist. In other words, an educational heritage which is exploitable independently of the environment of its development must be created. The utilization of standards can offer pedagogical contents some structures which facilitate the interchangeability between e- and m- learning. In order to ensure the interoperability between e- and â??m learning platforms and to take into account the specificities of m-learning, we have adopted the already existing standard LOM and the specification IMS LD
SHREC 2010: robust feature detection and description benchmark
No full textFeature-based approaches have recently become very popular in computer vision and image analysis applications,and are becoming a promising direction in shape retrieval. SHREC’10 robust feature detection and descriptionbenchmark simulates the feature detection and description stages of feature-based shape retrieval algorithms.The benchmark tests the performance of shape feature detectors and descriptors under a wide variety of transformations.The benchmark allows evaluating how algorithms cope with certain classes of transformations andstrength of the transformations that can be dealt with. The present paper is a report of the SHREC’10 robustfeature detection and description benchmark results
- …
