The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Human action recognition is a hot issue in the field of machine vision. It plays a pivotal role in human-centered computing. There are challenges mainly from the complexity of human actions and and high-noise data. Here we need to solve problems such as high intra-class variance with low inter-class variance, variable movement speed, and high computational costs. Based on the above points, we use...
We propose a novel method for temporally pooling frames in a video for the task of human action recognition. The method is motivated by the observation that there are only a small number of frames which, together, contain sufficient information to discriminate an action class present in a video, from the rest. The proposed method learns to pool such discriminative and informative frames, while discarding...
Aiming at realizing the effective fault diagnosis for aviation bearing, a method based on coupled hidden semi Markov model is proposed. Firstly, according to the aviation dynamic components of transmission structure, the monitoring network is designed for monitoring radial and axial vibration data of bearings; Secondly, the nonlinear feature extraction method is applied for obtaining a few key features...
Recognition of human actions by using wearable sensors has become an important research field. Segmentation to sensor data is a vital issue in reconstructing and understanding human daily actions, and strongly affects the accuracy of human actions recognition. Traditional online segmentation approaches are mostly designed for one-dimensional sensor data, which greatly limits these approaches to multi-dimensional...
Tme series polarimetric SAR image classification relies on learned understanding of how the set of pixels in an image relate by relative position and how the information of different dates in a time series change as time goes on. In this paper, we firstly integrate the incoherent information in the spatial scale and the coherent information in the temporal scale to form the feature for time series...
Opinion target extraction aims to find the object to which an opinion is expressed. It is helpful in getting a comprehensive understanding about public opinions on hot spot social events. In Chinese microblog posts analysis, due to the absence of words with emotional tendency (opinion words), traditional approaches relying on opinion words are not suitable. In this paper, we propose an unsupervised...
Fall is one of the major health challenges facing the elderly adults, especially the adults with high fall risk factors. In this paper, we aim to build a video-based model to mitigate the consequences of fall of the elderly at two application scenarios: (1) predict the fall risk caused by unbalanced gait and (2) detect a fall event as soon as it happens. In the first stage, we use a common camera...
In this paper, we made the emotion recognition for Romanian language using EMO-IIT database with seven emotions (joy, sadness, fury, neutral tone, anxiety, disgust and boredom). Compared to our previous studies we introduced two new emotions: disgust and boredom and a new set of sentences in order to express better the emotional states. The best recognition rate of emotions is around 75% and was obtained...
Given a pre-registered 3D mesh sequence and accompanying phoneme-labeled audio, our system creates an animatable face model and a mapping procedure to produce realistic speech animations for arbitrary speech input. Mapping of speech features to model parameters is done using random forests for regression. We propose a new speech feature based on phonemic labels and acoustic features. The novel feature...
In Japan, which has become a very aged society, the increasing burden of nursing care is an issue. Services and systems related to automatic recording of healthcare management of elderly people have been proposed in order to reduce the burden of nursing care. Water intake is one of the items necessary for healthcare management of elderly people. However, it is not currently automated, which is a burden...
In the physical world, cause and effect are inseparable: ambient conditions trigger humans to perform actions, thereby driving status changes of objects. In video, these actions and statuses may be hidden due to ambiguity, occlusion, or because they are otherwise unobservable, but humans nevertheless perceive them. In this paper, we extend the Causal And-Or Graph (C-AOG) to a sequential model representing...
For a safety critical task like driving, it is very important for the driver to be vigilant at all times. In this study, we explore a driver drowsiness monitoring and early warning system, which uses machine learning techniques based on vehicle telemetry data. The proposed system can ensure safe driving by real time monitoring of driving pattern. This proves to be a very cost effective technique over...
We introduce a long short-term memory recurrent neural network (LSTM-RNN) approach for real-time facial animation, which automatically estimates head rotation and facial action unit activations of a speaker from just her speech. Specifically, the time-varying contextual non-linear mapping between audio stream and visual facial movements is realized by training a LSTM neural network on a large audio-visual...
The work presented in this paper deals with the challenging task of learning an activity class representation using a single sequence for training. Recently, Simplex-HMM framework has been shown to be an efficient representation for activity classes, however, it presents high computational costs making it impractical in several situations. A dimensionality reduction of the features spaces based on...
This paper deals with random forest regression based acoustic event detection (AED) by combining acoustic features with bottleneck features (BN). The bottleneck features have a good reputation of being inherently discriminative in acoustic signal processing. To deal with the unstructured and complex real-world acoustic events, an acoustic event detection system is constructed using bottleneck features...
Reliable visual features that encode the articulator movements of speakers can dramatically improve the decoding accuracy of automatic speech recognition systems when combined with the corresponding acoustic signals. In this paper, a novel framework is proposed to utilize audio-visual speech not only during decoding but also for training better acoustic models. In this framework, a multi-stream hidden...
Action recognition from video streams is among the active research topics in computer vision. The challenge is on the identification of the actions robustly regardless of the variations imposed by appearances of actions performed by different people. The challenge increases when the data is gathered from an outdoor environment, i.e. background and illumination variations. This paper proposes a Hidden...
Household audience ratings are the currency of the television broadcasting business. Information communication technology has rapidly changed television viewing since the beginning of this century, and the reproducibility of audience ratings as media indicators is beginning to be questioned. This is because television viewing through various devices must be considered, due to the decline of simultaneous...
The ability to proactively monitor business processes is one of the main differentiators for firms to remain competitive. Process execution logs generated by Process Aware Information Systems (PAIS) help to make various business process specific predictions. This enables a proactive situational awareness related to the execution of business processes. The goal of the approach proposed in the current...
In this paper we present a novel method for predicting individual fingers movements from surface electromyography (EMG). The method is intended for real-time dexterous control of a multifunctional prosthetic hand device. The EMG data was recorded using 16 single-ended channels positioned on the forearm of healthy participants. Synchronously with the EMG recording, the subjects performed consecutive...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.