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.
This paper investigates the robustness of two state-of-theart action recognition algorithms: a pixel domain approach based on 3D convolutional neural networks (C3D) and a compressed domain approach requiring only partial decoding of the video, based on feature description using motion vectors and Fisher vector encoding (MV-FV). We study the robustness of the two algorithms against: (i) quality variations,...
We are concerned with the issue of discovering behavioral patterns on the web. When a large amount of web access logs are given, we are interested in how they are categorized and how they are related to activities in real life. In order to conduct that analysis, we develop a novel algorithm for sparse non-negative matrix factorization (SNMF), which can discover patterns of web behaviors. Although...
Although High Dynamic Range (HDR) content can provide an enhanced immersive experience for end-users, the impact of channel errors on its perception is unclear due to the lack of a standardized HDR video distribution framework. This paper presents an assessment of the robustness of the two main HDR video distribution architectures, the single-layer 10-bit scheme and the two-layer 8-bit backward-compatible...
Episodic memory can store time sequential events and retrieve them anytime with specific cues. However, if the episodic memory only stores events comprised of actions and objects, execution of episodes may fail if current situation is different from the settings it learned in. As a solution, we propose Deep C-ART (Context-Adaptive Resonance Theory) which considers not only time sequential events but...
This work revisits the stochastic computation paradigm as a way to implement architectures dedicated to Bayesian computation. It is assumed that Stochastic Bayesian Machines (SMBs) are intrinsically tolerant to the effects of radiation. However, practical assessment is mandatory before considering SBMs in hazardous environments. Results of fault-injection campaigns performed at the RTL level provide...
In this paper, we present a novel Bayesian approach to recover simultaneously block sparse signals in the presence of outliers. The key advantage of our proposed method is the ability to handle non-stationary outliers, i.e. outliers which have time varying support. We validate our approach with empirical results showing the superiority of the proposed method over competing approaches in synthetic...
In this paper, we propose a new texture descriptor, completed local derivative pattern (CLDP). In contrast to completed local binary pattern (CLBP), which involves only local differences at each scale, CLDP encodes the directional variation of the local differences of two scales as a complementary component to local patterns in CLBP. The new component in CLDP, with regarded as the directional derivative...
This paper presents a novel local surface descriptor called rotational contour signatures (RCS) for 3D rigid objects. RCS comprises several signatures that characterize the 2D contour information derived from 3D-to-2D projection of the local surface. The inspiration of our encoding technique comes from that, viewing towards an object, its contour is an effective and robust cue for representing its...
Color brings extra data capacity for QR codes, but it also brings tremendous challenges to the decoding because of color interference and illumination variation, especially for high-density QR codes. In this paper, we put forth a framework for high-capacity QR codes, HiQ, which optimizes the decoding algorithm for high-density QR codes to achieve robust and fast decoding on mobile devices, and adopts...
Adaptive sparse representation has been heavily exploited in signal processing and computer vision. Recently, sparsifying transform learning received interest for its cheap computation and optimal updates in the alternating algorithms. In this work, we develop a methodology for learning a Flipping and Rotation Invariant Sparsifying Transform, dubbed FRIST, to better represent natural images that contain...
This paper reviews the main features of chipless RFID tags realized with High-Impedance Surfaces. These tags, which comprise a periodic surface printed on top of a grounded dielectric slab, can be exploited in a number of encoding and decoding schemes. Several encoding methods have been investigated and the results are here analyzed and organized into a broad overview. In particular, the attention...
This paper presents the use of JANUS in operationally-relevant underwater applications. JANUS is an open, simple and robust digital coding technology currently in process to become a NATO standard. Two underwater scenarios have been considered: 1) Broadcast of underwater AIS and situational awareness messages; 2) First contact and language switching. The JANUS physical coding scheme has been used...
Depth information improves skeleton detection, thus skeleton based methods are the most popular methods in RGB-D action recognition. But skeleton detection working range is limited in terms of distance and view-point. Most of the skeleton based action recognition methods ignore fact that skeleton may be missing. Local points-of-interest (POIs) do not require skeleton detection. But they fail if they...
The severe time-varying multipath effect of underwater acoustic (UWA) channels has posed a great challenge for shallow water communication system design. Although existing literature has demonstrated that multicarrier modulation in the form of orthogonal frequency division multiplexing(OFDM) is an effective technique to deal with severe multipath effect of UWA channels, the experiments of medium distance...
LBP operator shows good performance on rotation invariant while LGRPH is robust to multiplicative noise and gradient changes. In order to combine merits of both operators, an improved rotation invariant feature for SAR image is proposed in this paper. Experiments on SAR images demonstrate that the proposed feature has a good performance on targets recognition and image texture patches matching with...
In this paper, we propose a novel edge descriptor method for background modeling. In comparison to previous edge-based local-pattern methods, it is more robust to noise and illumination variations due to the use of principal gradient information in a local neighborhood. For the background modeling problem, we combined the proposed method with the Local Hybrid Pattern and experimented with an adaptive-dictionary-model...
Recently, steganography is frequently used for providing covert channel. There are two types of steganography, noisy and noiseless. Noisy steganography approach hides the message by altering the bit of cover. The alteration process produce noise such that it will raise suspicion. Desoky and Younis proposed a noiseless steganography method namely Graphstega that conceal the message as plotted data...
This work introduces a novel feature detection algorithm for the decoding of a binary encoded structured light pattern. To make the structure light pattern insensitive to surface color and texture, some geometrical shapes are used as the pattern elements. Grid-point between each two adjacent rhombic pattern element is defined as the feature points. Affected by the inner structure of pattern element,...
Smart video analysis is attracting increasing attention with the pervasive use of surveillance camera. In this paper, we address video anomaly detection by Uniform Local Gradient Pattern based Optical Flow (ULGP-OF) descriptor and one-class extreme learning machine (OCELM). Using the proposed ULGP-OF descriptor, we naturally combine the robust 2D image texture descriptor LGP with video optical flow...
The problem of network disintegration has broad applications and recently has received growing attention, such as network confrontation and disintegration of harmful networks. This paper presents an optimized disintegration strategy model for complex networks and introduces the GA optimization method into the network disintegration problem to identify the optimal disintegration strategy, which is...
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.