<title>Effective object representation technique for recognition</title>

AbstractWe applied high-density EEG to examine steady-state visual evoked potentials (SSVEPs) during a perceptual/semantic stimulus repetition design. SSVEPs are evoked oscillatory cortical responses at the same frequency as visual stimuli flickered at this frequency. In repetition designs, stimuli are presented twice with the repetition being task irrelevant. The cortical processing of the second stimulus is commonly characterized by decreased neuronal activity (repetition suppression). The behavioral consequences of stimulus repetition were examined in a companion reaction time pre-study using the same experimental design as the EEG study. During the first presentation of a stimulus, we confronted participants with drawings of familiar object images or object words, respectively. The second stimulus was either a repetition of the same object image (perceptual repetition; PR) or an image depicting the word presented during the first presentation (semantic repetition; SR)—all flickered at 15 Hz to elicit SSVEPs. The behavioral study revealed priming effects in both experimental conditions (PR and SR). In the EEG, PR was associated with repetition suppression of SSVEP amplitudes at left occipital and repetition enhancement at left temporal electrodes. In contrast, SR was associated with SSVEP suppression at left occipital and central electrodes originating in bilateral postcentral and occipital gyri, right middle frontal and right temporal gyrus. The conclusion of the presented study is twofold. First, SSVEP amplitudes do not only index perceptual aspects of incoming sensory information but also semantic aspects of cortical object representation. Second, our electrophysiological findings can be interpreted as neuronal underpinnings of perceptual and semantic priming.

Download Full-text

Deep Multi-Stage Approach For Emotional Body Gesture Recognition In Job Interview

The Computer Journal ◽

10.1093/comjnl/bxab011 ◽

2021 ◽

Author(s):

Intissar Khalifa ◽

Ridha Ejbali ◽

Raimondo Schettini ◽

Mourad Zaied

Keyword(s):

Gesture Recognition ◽

Affective Computing ◽

Psychological State ◽

Sources Of Information ◽

Emotion Classification ◽

Convolutional Network ◽

Job Interview ◽

Multi Stage ◽

Representation Technique ◽

The Subject

Abstract Affective computing is a key research topic in artificial intelligence which is applied to psychology and machines. It consists of the estimation and measurement of human emotions. A person’s body language is one of the most significant sources of information during job interview, and it reflects a deep psychological state that is often missing from other data sources. In our work, we combine two tasks of pose estimation and emotion classification for emotional body gesture recognition to propose a deep multi-stage architecture that is able to deal with both tasks. Our deep pose decoding method detects and tracks the candidate’s skeleton in a video using a combination of depthwise convolutional network and detection-based method for 2D pose reconstruction. Moreover, we propose a representation technique based on the superposition of skeletons to generate for each video sequence a single image synthesizing the different poses of the subject. We call this image: ‘history pose image’, and it is used as input to the convolutional neural network model based on the Visual Geometry Group architecture. We demonstrate the effectiveness of our method in comparison with other methods in the state of the art on the standard Common Object in Context keypoint dataset and Face and Body gesture video database.

Download Full-text

Can we Beat the Square Root Bound for ECDLP over 𝔽p2 via Representation?

Journal of Mathematical Cryptology ◽

10.1515/jmc-2019-0025 ◽

2020 ◽

Vol 14 (1) ◽

pp. 293-306

Author(s):

Claire Delaplace ◽

Alexander May

Keyword(s):

Elliptic Curve ◽

Quadratic Field ◽

Discrete Logarithm ◽

Field Size ◽

Square Root ◽

Multivariate Polynomial ◽

Bivariate Polynomial ◽

Testing Problem ◽

Polynomial Zero ◽

Representation Technique

AbstractWe give a 4-list algorithm for solving the Elliptic Curve Discrete Logarithm (ECDLP) over some quadratic field 𝔽p2. Using the representation technique, we reduce ECDLP to a multivariate polynomial zero testing problem. Our solution of this problem using bivariate polynomial multi-evaluation yields a p1.314-algorithm for ECDLP. While this is inferior to Pollard’s Rho algorithm with square root (in the field size) complexity 𝓞(p), it still has the potential to open a path to an o(p)-algorithm for ECDLP, since all involved lists are of size as small as $\begin{array}{} p^{\frac 3 4}, \end{array}$ only their computation is yet too costly.

Download Full-text