A-WDL: An Improved Recommendation Algorithm for WDL based on Attentional Mechanism Adaptation

CTR prediction is one of the main research directions of recommendation algorithm, which is widely used in e-commerce advertising recommendation and other fields. Wide&Deep Learning (WDL) model is a CTR prediction and recommendation algorithm that combine linear model with deep neural network. To solve the problem that WDL is prone to over-fitting and the proportion of Wide and Deep learning part needs to be adjusted manually in practical application, Attentional WDL(A-WDL) algorithm is based on residual network to improve the Deep part. And use the attention mechanism to automate the learning of the Wide part and the Deep learning part of the proportion. Experiments on the public dataset Criteo on Kaggle show that the A-WDL algorithm improves the performance of AUC compared with other algorithms such as WDL, and effectively avoids the problem of overfitting. In addition, the performance improvement of A-WDL is explainable.

Auto-attentional mechanism in multi-domain convolutional neural networks for improving object tracking

PurposeMulti-domain convolutional neural network (MDCNN) model has been widely used in object recognition and tracking in the field of computer vision. However, if the objects to be tracked move rapid or the appearances of moving objects vary dramatically, the conventional MDCNN model will suffer from the model drift problem. To solve such problem in tracking rapid objects under limiting environment for MDCNN model, this paper proposed an auto-attentional mechanism-based MDCNN (AA-MDCNN) model for the rapid moving and changing objects tracking under limiting environment.Design/methodology/approachFirst, to distinguish the foreground object between background and other similar objects, the auto-attentional mechanism is used to selectively aggregate the weighted summation of all feature maps to make the similar features related to each other. Then, the bidirectional gated recurrent unit (Bi-GRU) architecture is used to integrate all the feature maps to selectively emphasize the importance of the correlated feature maps. Finally, the final feature map is obtained by fusion the above two feature maps for object tracking. In addition, a composite loss function is constructed to solve the similar but different attribute sequences tracking using conventional MDCNN model.FindingsIn order to validate the effectiveness and feasibility of the proposed AA-MDCNN model, this paper used ImageNet-Vid dataset to train the object tracking model, and the OTB-50 dataset is used to validate the AA-MDCNN tracking model. Experimental results have shown that the augmentation of auto-attentional mechanism will improve the accuracy rate 2.75% and success rate 2.41%, respectively. In addition, the authors also selected six complex tracking scenarios in OTB-50 dataset; over eleven attributes have been validated that the proposed AA-MDCNN model outperformed than the comparative models over nine attributes. In addition, except for the scenario of multi-objects moving with each other, the proposed AA-MDCNN model solved the majority rapid moving objects tracking scenarios and outperformed than the comparative models on such complex scenarios.Originality/valueThis paper introduced the auto-attentional mechanism into MDCNN model and adopted Bi-GRU architecture to extract key features. By using the proposed AA-MDCNN model, rapid object tracking under complex background, motion blur and occlusion objects has better effect, and such model is expected to be further applied to the rapid object tracking in the real world.

Attentional capture by signals of food and drink reward persists following outcome devaluation

Attention, the mechanism that prioritises stimuli in the environment for further processing, plays an important role in behavioural choice. In the current study we investigated the automatic orienting of attention to cues that signal reward. Such attentional capture occurs despite negative consequences, but the sensitivity of this counterproductive and reflexive behaviour to shifts in outcome value has not yet been investigated. Thirsty participants completed a visual-search task, in which the colour of a distractor stimulus in the search display signalled whether participants would earn water or potato chips for making a rapid eye movement to a diamond target, but looking at the coloured distractor was punished by omission of the signalled reward. Nevertheless, participants looked at the water-signalling distractor more frequently than the chips-signalling distractor. Half the participants then drank water ad libitum before continuing with the visual-search task. Although the water was now significantly less desirable for half of the participants, there was no difference between groups in the tendency for the water-signalling distractor to capture attention. These findings suggest that once established, attentional bias to signals of food and drink rewards persists, even when those outcomes are no longer valuable. This suggests a ‘habit-like’ attentional mechanism which prioritises reward stimuli in the environment for further action, regardless of whether those stimuli are aligned with current goals, or currently desired.

Psychological functioning in survivors of COVID-19: Evidence from recognition of fearful facial expressions

Evidence about the psychological functioning in individuals who survived the COVID-19 infectious is still rare in the literature. In this paper, we investigated fearful facial expressions recognition, as a behavioural means to assess psychological functioning. From May 15th, 2020 to January 30th, 2021, we enrolled sixty Italian individuals admitted in multiple Italian COVID-19 post-intensive care units. The detection and recognition of fearful facial expressions were assessed through an experimental task grounded on an attentional mechanism (i.e., the redundant target effect). According to the results, our participants showed an altered behaviour in detecting and recognizing fearful expressions. Specifically, their performance was in disagreement with the expected behavioural effect. Our study suggested altered processing of fearful expressions in individuals who survived the COVID-19 infectious. Such a difficulty might represent a crucial sign of psychological distress and it should be addressed in tailored psychological interventions in rehabilitative settings and after discharge.

An egocentric straight-ahead bias in primate’s vision

As we plan to reach or manipulate objects, we generally orient our body so as to face them. Other objects occupying the same portion of space will likely represent potential obstacles for the intended action. Thus, either as targets or as obstacles, the objects located straight in front of us are often endowed with a special behavioral status. Here, we review a set of recent electrophysiological, imaging and behavioral studies bringing converging evidence that the objects which lie straight-ahead are subject to privileged visual processing. More precisely, these works collectively demonstrate that when gaze steers central vision away from the straight-ahead direction, the latter is still prioritized in peripheral vision. Straight-ahead objects evoke (1) stronger neuronal responses in macaque peripheral V1 neurons, (2) stronger EEG and fMRI activations across the human visual cortex and (3) faster reactive hand and eye movements. Here, we discuss the functional implications and underlying mechanisms behind this phenomenon. Notably, we propose that it can be considered as a new type of visuospatial attentional mechanism, distinct from the previously documented classes of endogenous and exogenous attention.

Decoding of EEG Signals Shows No Evidence of a Neural Signature for Subitizing in Sequential Numerosity

Numerosity perception is largely governed by two mechanisms. The first so-called subitizing system allows one to enumerate a small number of items (up to three or four) without error. The second system allows only an approximate estimation of larger numerosities. Here, we investigate the neural bases of the two systems using sequentially presented numerosity. Sequential numerosity (i.e., the number of events presented over time) starts as a subitizable set but may eventually transition into a larger numerosity in the approximate estimation range, thus offering a unique opportunity to investigate the neural signature of that transition point, or subitizing boundary. If sequential numerosity is encoded by two distinct perceptual mechanisms (i.e., for subitizing and approximate estimation), neural representations of the sequentially presented items crossing the subitizing boundary should be sharply distinguishable. In contrast, if sequential numerosity is encoded by a single perceptual mechanism for all numerosities and subitizing is achieved through an external postperceptual mechanism, no such differences in the neural representations should indicate the subitizing boundary. Using the high temporal resolution of the EEG technique incorporating a multivariate decoding analysis, we found results consistent with the latter hypothesis: No sharp representational distinctions were observed between items across the subitizing boundary, which is in contrast with the behavioral pattern of subitizing. The results support a single perceptual mechanism encoding sequential numerosities, whereas subitizing may be supported by a postperceptual attentional mechanism operating at a later processing stage.

EXPRESS: Evidence for two attentional mechanisms during learning

We sought to provide evidence for a combined effect of two attentional mechanisms during associative learning. Participants’ eye movements were recorded as they predicted the outcomes following different pairs of cues. Across the trials of an initial stage, a relevant cue in each pair was consistently followed by one of two outcomes, while an irrelevant cue was equally followed by either of them. Thus, the relevant cue should have been associated with small relative prediction errors, compared to the irrelevant cue. In a later stage, each pair came to be followed by one outcome on a random half of the trials and by the other outcome on the remaining half, and thus there should have been a rise in the overall prediction error. Consistent with an attentional mechanism based on relative prediction error, an attentional advantage for the relevant cue was evident in the first stage. On the other hand, in accordance with a mechanism linked to overall prediction error, the attention paid to both types of cues increased at the beginning of the second stage. These results showed up in both dwell times and within-trial patterns of fixations, and they were predicted by a hybrid model of attention.