In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

Measuring Physical Activity and Energy Expenditure

In this paper we present a framework that allows a human and a robot to perform simultaneous manipulation tasks safely in close proximity. The proposed framework is based on early prediction of the human's motion. The prediction system, which builds on previous work in the area of gesture recognition, generates a prediction of human workspace occupancy by computing the swept volume of learned human motion trajectories. The motion planner then plans robot trajectories that minimize a penetration cost in the human workspace occupancy while interleaving planning and execution. Multiple plans are computed in parallel, one for each robot task available at the current time, and the trajectory with the least cost is selected for execution. We test our framework in simulation using recorded human motions and a simulated PR2 robot. Our results show that our framework enables the robot to avoid the human while still accomplishing the robot's task, even in cases where the initial prediction of the human's motion is incorrect. We also show that taking into account the predicted human workspace occupancy in the robot's motion planner leads to safer and more efficient interactions between the user and the robot than only considering the human's current configuration.

/pdf/human-robot-collaborative-manipulation-planning-using-early-x76m4nvv5f.pdf

Human-robot collaborative manipulation planning using early prediction of human motion

Over the years, techniques for the study of human movement have ranged in complexity and precision from direct observation of the subject through activity diaries, questionnaires, and recordings of body movement, to the measurement of physiological responses, studies of metabolism and indirect and direct calorimetry. This article reviews developments in each of these domains. Particular reference is made to their impact upon the continuing search for valid field estimates of activity patterns and energy expenditures, as required by the applied physiologist, ergonomist, sports scientist, nutritionist and epidemiologist. Early observers sought to improve productivity in demanding employment. Direct observation and filming of workers were supplemented by monitoring of heart rates, ventilation and oxygen consumption. Such methods still find application in ergonomics and sport, but many investigators are now interested in relationships between habitual physical activity and chronic disease. Even sophisticated questionnaires still do not provide valid information on the absolute energy expenditures associated with good health. Emphasis has thus shifted to use of sophisticated pedometer/accelerometers, sometimes combining their output with GPS and other data. Some modern pedometer/accelerometers perform well in the laboratory, but show substantial systematic errors relative to laboratory reference criteria such as the metabolism of doubly labeled water when assessing the varied activities of daily life. The challenge remains to develop activity monitors that are sufficiently inexpensive for field use, yet meet required accuracy standards. Possibly, measurements of oxygen consumption by portable respirometers may soon satisfy part of this need, although a need for valid longer term monitoring will remain.

Measurement of human energy expenditure, with particular reference to field studies: an historical perspective.

In the last years, several studies have been focused on understanding how the central nervous system controls muscles to perform a specific motor task. Although it still remains an open question, muscle synergies have come to be an appealing theory to explain the modular organization of the central nervous system. Even though the neural encoding of muscle synergies remains controversial, a large number of papers demonstrated that muscle synergies are robust across different tested conditions, which are within a day, between days, within a single subject, and between subjects that have similar demographic characteristics. Thus, muscle synergy theory has been largely used in several research fields, such as clinics, robotics, and sports. The present systematical review aims at providing an overview on the applications of muscle synergy theory in clinics, robotics, and sports; in particular, the review is focused on the papers that provide tangible information for (i) diagnosis or pathology assessment in clinics, (ii) robot-control design in robotics, and (iii) athletes' performance assessment or training guidelines in sports.

/pdf/feasibility-of-muscle-synergy-outcomes-in-clinics-robotics-20wj5c2msj.pdf

Feasibility of Muscle Synergy Outcomes in Clinics, Robotics, and Sports: A Systematic Review

The aim of this study is to compare the relation between ventilation (VE) and oxygen uptake (VO2) [VO2=ƒ(VE)] and between heart rate (HR) and VO2 [VO2=ƒ(HR)]. Each one of the subjects performed three types of activities of different intensities (walking without load, walking with load and intermittent work). VO2, VE, and HR were measured continuously by using indirect calorimetry and an electrocardiogram. Linear regressions and coefficients of determination (r(2)) were calculated to compare the relation VO2 =ƒ(VE) and VO2 =ƒ(HR) for two different regroupings: by session duration (r(2) session) and by subject (r(2) subject). Results showed that r(2) session of the relation VO2 =ƒ(VE) were significantly higher than those of the relation VO2 =ƒ(HR) for steady state activities (walking with or without load during 3 or 6 min, p < 0.01) and for activities without oxygen consumption steady state (walking with or without load during 1 min, p < 0.01 and intermittent work, p < 0.05). VE is more strongly correlated with VO2 than with HR. This is a very promising approach to develop a new method to estimate energy expenditure. Key pointsVentilation is more strongly correlated with oxygen uptake than heart rate during physical activities of different intensities.This study shows the interest to looking for ventilation to estimate energy expenditure.This study is a promising approach to develop a new method to estimate energy expenditureAn interesting perspective could be to develop a light and portable device to measure ventilation based on the coupling of four magnetometers.

https://www.jssm.org/hfpdf.php?volume=09&issue=1&page=110

A comparison between ventilation and heart rate as indicator of oxygen uptake during different intensities of exercise.

To validate a new device designed to measure ventilation \( \left( {\dot{V}_{\text{E}} } \right), \) tidal volume (VT), inspiratory time (TI), and expiratory time (TE) during daily life activities. The anteroposterior displacement of the rib cage and abdomen and the axial displacements of the chest wall and the spine were measured using two pairs of magnetometers. \( \dot{V}_{\text{E}} \) was estimated from these four signals, and was simultaneously measured using a spirometer. A total of 707, 732, and 1,138 breaths were analyzed in sitting, standing, and exercise conditions, respectively. We compared \( \dot{V}_{\text{E}} \), VT, TI, and, TE measured by magnetometers (\( \dot{V}_{{{\text{E}}\;{\text{mag}}}} \), VT mag, TI mag, and TE mag) with \( \dot{V}_{\text{E}} \), VT, TI, and TE measured by a spirometer (\( \dot{V}_{{{\text{E}}\;{\text{spiro}}}} \), VT spiro, TI spiro, and TE spiro, respectively). For pooled data \( \dot{V}_{{{\text{E}}\;{\text{mag}}}} \), VT mag, TI mag, and TE mag were significantly correlated (p < 0.001) with \( \dot{V}_{{{\text{E}}\;{\text{spiro}}}} \), VT spiro, TI spiro, and TE spiro in sitting and standing positions and during the walking exercise. The mean differences, between \( \dot{V}_{{{\text{E}}\;{\text{mag}}}} \), and \( \dot{V}_{{{\text{E}}\;{\text{spiro}}}} \) for the group, were 10.44, 10.74, and 12.06% in sitting, standing, and exercise conditions, respectively. These results demonstrate the capacity of this new device to measure \( \dot{V}_{\text{E}} \) with reasonable accuracy in sitting, standing, and exercise conditions.

Estimates of ventilation from measurements of rib cage and abdominal distances: a portable device

La reconnaissance de mouvements naturels est de toute premiere importance dans la mise en oeuvre d’Interfaces Homme-Machine intelligentes et efficaces, utilisables de maniere intuitive en environnement virtuel. En effet, elle permet a l’utilisateur d’agir de maniere naturelle et au systeme de reconnaitre les mouvements corporel effectues tels qu’ils seraient percu par un humain. Cette tâche est complexe, car elle demande de relever plusieurs defis : prendre en compte les specificites du dispositif d’acquisition des donnees de mouvement, gerer la variabilite cinematique dans l’execution du mouvement, et enfin gerer les differences morphologiques inter-individuelles, de sorte que les mouvements de tout nouvel utilisateur puissent etre reconnus. De plus, de part la nature interactive des environnements virtuels, cette reconnaissancedoit pouvoir se faire en temps-reel, sans devoir attendre la fin du mouvement. La litterature scientifique propose de nombreuses methodes pour repondre aux deux premiers defis mais la gestion de la variabilite morphologique est peu abordee. Dans cette these, nous proposons une description du mouvement permettant de repondre a cette problematique et evaluons sa capacite a reconnaitre les mouvements naturels d’un utilisateur inconnu. Enfin, nous proposons unenouvelle methode permettant de tirer partie de cette representation dans une reconnaissance precoce du mouvement

Gestion de la variabilité morphologique pour la reconnaissance de gestes naturels à partir de données 3D

The aim of this paper is to validate a new method of energy expenditure (EE) estimation stemming solely from the measurement of rib cage, abdominal and chest wall distances. We set out to prove that the variations of these distances, measured by two pairs of electromagnetic coils, lead to the estimation of the ventilation (VE) and the EE. Eleven subjects were recruited to take part in this study (27.6 ± 5.4 years; 73.7 ± 9.7 kg). Each subject participated in two tests. The objective of Test 1 was to determine the individual and group equations between the VE and EE during light to moderate activities while Test 2 compared the two pairs of electromagnetic coils with the indirect calorimetry so as to estimate EE in upright sitting and standing positions and during walking exercises. During Test 2, we compared EE measured by indirect calorimetry (EE(IC-Val-REF)) with EE estimated by the two pairs of electromagnetic coils through the application of: (1) the individual equation (EE(mag-Val-INDIV)) and (2) the group equation (EE(mag-val-GROUP)). The results show that there is no significant difference between EE(IC-Val-REF) and EE(mag-Val-INDIV) and between EE(IC-Val-REF) and EE(mag-val-GROUP) for each activity. Furthermore, the mean difference seems to show that the estimation of EE is better with the group equation. In conclusion, on the proven basis of this study we are able to validate this new method which permits the estimation of EE from abdominal and rib cage distances. This study also highlights the advantage of using a group equation to the estimate EE.

A new method to estimate energy expenditure from abdominal and rib cage distances.

Virtual reality using head-mounted displays (HMD) could provide enhanced physical load during active gaming (AG) compared to traditional displays. We aimed to compare the physical load elicited by conventional exercise and AG with an HMD. We measured energy expenditure (EE) and heart rate (HR) in nine healthy men (age: 27 ± 5 years) performing three testing components in a randomised order: walking at 6 km/h (W6), AG, and AG with an additional constraint (AGW; wrist-worn weights). Although we found that HR was not significantly different between W6 and the two modes of AG, actual energy expenditure was consistently lower in AG and AGW compared to W6. We observed that playing AG with wrist-worn weights could be used as a means of increasing energy expenditure only at maximum game level, but ineffective otherwise. Our findings indicate that AG in an HMD may not provide a sufficient stimulus to meet recommended physical activity levels despite increased psychophysiological load. The differential outcomes of measures of HR and EE indicates that HR should not be used as an indicator of EE in AG. Yet, adding a simple constraint (wrist-worn weights) proved to be a simple and effective measure to increase EE during AG.

https://www.mdpi.com/1660-4601/16/22/4406/pdf

Anthony Sorel

Papers

A comparison between ventilation and heart rate as indicator of oxygen uptake during different intensities of exercise.

Estimates of ventilation from measurements of rib cage and abdominal distances: a portable device

Gestion de la variabilité morphologique pour la reconnaissance de gestes naturels à partir de données 3D

A new method to estimate energy expenditure from abdominal and rib cage distances.

Virtual Reality Gaming Elevates Heart Rate but Not Energy Expenditure Compared to Conventional Exercise in Adult Males