Results 231 to 240 of about 903,030 (265)
Some of the next articles are maybe not open access.
From Activity Recognition to Situation Recognition
2013Activity recognition is important to many critical human-centric applications. Despite success in activity recognition research, there seems to be a quest for a richer sentience that is more expressive than human activity. In particular, situation has received intense attention lately with a multitude of overlapping definitions motivated by a variety ...
Lee, D., Helal, Sumi
openaire +1 more source
Transinformation for active object recognition
Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271), 2002This article develops an analogy between object recognition and the transmission of information through a channel based on the statistical representation of the appearances of 3D objects. This analogy provides a means to quantitatively evaluate the contribution of individual receptive field vectors, and to predict the performance of the object ...
Bernt Schiele, James L. Crowley
openaire +2 more sources
Recognition of Continuous Activities
2002The recognition of continuous human activities performed with several limbs is still an open problem. We propose a novel approach for recognition of continuous activities, which considers the direction change between frames to track the motion of several limbs and uses a Bayesian network to recognize different activities.
Rocío Díaz de León +1 more
openaire +1 more source
Analyzing features for activity recognition
Proceedings of the 2005 joint conference on Smart objects and ambient intelligence: innovative context-aware services: usages and technologies, 2005Human activity is one of the most important ingredients of context information. In wearable computing scenarios, activities such as walking, standing and sitting can be inferred from data provided by body-worn acceleration sensors. In such settings, most approaches use a single set of features, regardless of which activity to be recognized.
Tâm Huynh, Bernt Schiele
openaire +2 more sources
Recognition of Activities of Daily Living
2012 IEEE 24th International Conference on Tools with Artificial Intelligence, 2012This paper presents a new method for human action recognition which exploits advantages of both trajectory and space-time based approaches in order to identify action patterns in given sequences. Videos with both a static and moving camera can be tackled, where camera motion effects are overcome via motion compensation.
Konstantinos Avgerinakis +2 more
openaire +1 more source
Continual Learning for Activity Recognition
2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2022The recent success of deep neural networks in prediction tasks on wearable sensor data is evident. However, in more practical online learning scenarios, where new data arrive sequentially, neural networks suffer severely from the "catastrophic forgetting" problem.
Ramesh Kumar Sah +2 more
openaire +2 more sources
Recognition of Human Activities
2011Computer Vision is the estimation of the three dimensional shape and other properties of objects based on their two dimensional (projection) images through the use of computers and cameras. It had its beginning in the early 1960s. At the time, it was thought to be an easy problem with a solution probably possible over a summer.
openaire +1 more source
Active Sensing in Human Activity Recognition
2017This work studies the problem of reducing the energy consumption of wearable sensors in a Human Activity Recognition (HAR) system. A HAR system is implemented using Hidden Markov Models, where decisions over the acquisition of new data are made based on the entropy of the posterior distribution of the activities. This problem is intractable in general,
Alfredo Nazábal +1 more
openaire +1 more source
Proceedings of the 2011 international workshop on Situation activity & goal awareness - SAGAware '11, 2011
Activity recognition is an emerging field that demands active research in ubiquitous computing for analyzing complex scenarios such as concurrent situation assessment and domination of major over the minor activities. In this paper, an evolutionary ensembles approach using Genetic Algorithm (GA) as a homogeneous learner has been proposed. This approach
Muhammad Fahim +3 more
openaire +1 more source
Activity recognition is an emerging field that demands active research in ubiquitous computing for analyzing complex scenarios such as concurrent situation assessment and domination of major over the minor activities. In this paper, an evolutionary ensembles approach using Genetic Algorithm (GA) as a homogeneous learner has been proposed. This approach
Muhammad Fahim +3 more
openaire +1 more source
A Factorization Approach for Activity Recognition
2003 Conference on Computer Vision and Pattern Recognition Workshop, 2003Understanding activities arising out of the interactions of a configuration of moving objects is an important problem in video understanding, with applications in surveillance and monitoring. A special situation is when the objects are small enough to be represented as points on a 2D plane. In this paper, we introduce a novel method of representing the
Amit K. Roy-Chowdhury, Rama Chellappa
openaire +1 more source