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.
We present a novel deep learning framework for crowd counting by learning a perspective-embedded deconvolution network. Perspective is an inherent property of most surveillance scenes. Unlike the traditional approaches that exploit the perspective as a separate normalization, we propose to fuse the perspective into a deconvolution network, aiming to obtain a robust, accurate and consistent crowd density...
Visual attention is a dynamic search process of acquiring information. However, most previous studies have focused on the prediction of static attended locations. Without considering the temporal relationship of fixations, these models usually cannot explain the dynamic saccadic behavior well. In this paper, an iterative representation learning framework is proposed to predict the saccadic scanpath...
With the increasing number of public available training data for face alignment, the regression-based methods attracted much attention and have become the dominant methods to solve this problem. There are two main factors, the variance of the regression target and the capacity of the regression model, affecting the performance of the regression task. In this paper, we present a Stacked Hourglass Network...
In this paper we utilize the first large-scale "in-the-wild" (Aff-Wild) database, which is annotated in terms of the valence-arousal dimensions, to train and test an end-to-end deep neural architecture for the estimation of continuous emotion dimensions based on visual cues. The proposed architecture is based on jointly training convolutional (CNN) and recurrent neural network (RNN) layers,...
This paper presents a framework for saliency estimation and fixation prediction in videos. The proposed framework is based on a hierarchical feature representation obtained by stacking convolutional layers of independent subspace analysis (ISA) filters. The feature learning is thus unsupervised and independent of the task. To compute the saliency, we then employ a multiresolution saliency architecture...
Automated affective computing in the wild is a challenging task in the field of computer vision. This paper presents three neural network-based methods proposed for the task of facial affect estimation submitted to the First Affect-in-the-Wild challenge. These methods are based on Inception-ResNet modules redesigned specifically for the task of facial affect estimation. These methods are: Shallow...
In multi-label image classification, each image is always associated with multiple labels and labels are usually correlated with each other. The intrinsic relation among labels can definitely contribute to classifier training. However, most previous studies on active learning for multi-label image classification purely mine label correlation based on observed label distribution. They ignore the mapping...
This paper presents the proposed solution to the "affect in the wild" challenge, which aims to estimate the affective level, i.e. the valence and arousal values, of every frame in a video. A carefully designed deep convolutional neural network (a variation of residual network) for affective level estimation of facial expressions is first implemented as a baseline. Next we use multiple memory...
Blind deblurring consists a long studied task, however the outcomes of generic methods are not effective in real world blurred images. Domain-specific methods for deblurring targeted object categories, e.g. text or faces, frequently outperform their generic counterparts, hence they are attracting an increasing amount of attention. In this work, we develop such a domain-specific method to tackle deblurring...
This paper investigates direct beamformer estimation in dynamic time division duplexing (TDD) system with the objective of weighted sum rate maximization. For a given TDD frame, base stations (BS) are allocated to either uplink or downlink based on the instantaneous traffic state. The weighted sum mean-squared error minimization framework is used to obtain the decentralized iterative solution for...
This paper presents a novel two-stage regularized moving-horizon algorithm for PieceWise Affine (PWA) regression. At the first stage, the training samples are processed iteratively, and a Mixed-Integer Quadratic-Programming (MIQP) problem is solved to find the sequence of active modes and the model parameters which best match the training data, within a relatively short time window in the past. According...
In a multi-user millimeter (mm) wave communication system, we consider the problem of estimating the channel response between the central node (base station) and each of the user equipments (UE). We propose three different strategies: 1) Each UE estimates its channel separately, 2) Base station estimates all the UEs' channels jointly, and 3) Two stage process with estimation done at both UE and base...
In this paper, we propose a new technique for synchronization and channel estimation in M-QAM OFDM radio over fiber (RoF) system by using constant amplitude zero auto-correlation (CAZAC) sequence based training preamble. Delay and correlate method is used to identify the training sequence in the received signal vector and to correct the symbol timing offset. For an optimum demodulation of OFDM signal,...
Many noninvasive continuous blood pressure measurements using photoplethysmography (PPG) are still inadequate in terms of accuracy and stability, which hinders the practical application of this method. This paper proposes a model based on ensemble method for BP estimation using PPG. A number of blood pressure calculation base-models is built on the same training data. These base-models are used to...
In database-driven spectrum sharing, despite the spectrum sharing policy given by a database, harmful interference can occur between a primary user (PU) and a secondary user (SU) due to the unexpected propagation paths. In a previous study, a primary exclusive region (PER) centered at a PU, wherein the SUs are forbidden to use the spectrum, has been proposed. However, the PER figure that efficiently...
The knowledge of driver distraction will be important for self driving cars in the near future to determine the handoff time to the driver. Driver's gaze direction has been previously shown as an important cue in understanding distraction. While there has been a significant improvement in personalized driver gaze zone estimation systems, a generalized gaze zone estimation system which is invariant...
Fully autonomous landing on moving platforms poses a problem of importance for Unmanned Aerial Vehicles (UAVs). Current approaches are usually based on tracking and following the moving platform by means of several techniques, which frequently lack performance in real applications. The aim of this paper is to prove a simple landing strategy is able to provide practical results. The presented approach...
We consider the problem of time-series prediction with missing observations. We consider the autoregressive model (AR model) and cast the problem as a regression problem. On the basic of sampling methods and the online gradient descent (OGD), we propose efficient any-time methods to solve this problem. We show that our algorithm can learn the underlying model efficiently, meanwhile, is robust to the...
One of the orthogonal frequency division multiplexing (OFDM) schemes is the Time Domain Synchronous OFDM (TDS-OFDM) scheme, in which, the guard intervals between consecutive OFDM symbols contain Pseudo Noise (PN) sequences which are known to the receiver and are used for channel estimation and synchronization. In this paper, a joint channel estimation algorithm is proposed for TDS-OFDM scheme, the...
One of the most fundamental tasks in autonomous driving is the recognition of the road ahead. Using radar data, this is usually done via rule based algorithms. This paper proposes a deep learning approach to estimate the course of the ego lane based on occupancy grids generated by radar sensors. The method is also able to simultaneously give a reliability measurement of the predicted driving path...
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.