A deep model with combined losses for person re-identification

Person re-identification (PReID), which aims to re-identity a pedestrian from multiple non-overlapping cameras, has been significantly improved by deep learning system. There exist two popular deep frameworks used for PReID, i.e., identification and triplet models. Since these two frameworks have different loss functions, they have their own advantages and disadvantages. To combine the both advantages of two frameworks, in this paper, we propose using the triplet and Online Instance Matching (OIM) losses to train the carefully designed network. Given a triplet input images, the combined model can output the identities of the input images and learn a corresponding similarity measurement simultaneously. Experiments on CUHK01, CUHK03, Market-1501, and DukeMTMC-reID datasets demonstrate that the proposed model outperforms the compared state-of-the-art methods in most cases.     

Hemispheric specialization and independence for word recognition: a comparison of three computational models

Two findings serve as the hallmark for hemispheric specialization during lateralized lexical decision. First is an overall word advantage, with words being recognized more quickly and accurately than non-words (the effect being stronger in response latency). Second, a right visual field advantage is observed for words, with little or no hemispheric differences in the ability to identify non-words. Several theories have been proposed to account for this difference in word and non-word recognition, some by suggesting dual routes of lexical access and others by incorporating separate, and potentially independent, word and non-word detection mechanisms. We compare three previously proposed cognitive theories of hemispheric interactions (callosal relay, direct access, and cooperative hemispheres) through neural network modeling, with each network incorporating different means of interhemispheric communication. When parameters were varied to simulate left hemisphere specialization for lexical decision, only the cooperative hemispheres model showed both a consistent left hemisphere advantage for word recognition but not non-word recognition, as well as an overall word advantage. These results support the theory that neural representations of words are more strongly established in the left hemisphere through prior learning, despite open communication between the hemispheres during both learning and recall.     

Category-specificity can emerge from bottom-up visual characteristics: evidence from a modular neural network

The role of bottom-up visual processes in category-specific object recognition has been largely unexplored. We examined the role of low-level visual characteristics in category specific recognition using a modular neural network comprising both unsupervised and supervised components. One hundred standardised pictures from ten different categories (five living and five nonliving, including body parts and musical instruments) were presented to a Kohonen self-organising map (SOM) which re-represents the visual stimuli by clustering them within a smaller number of dimensions. The SOM representations were then used to train an attractor network to learn the superordinate category of each item. The ease with which the model acquired the category mappings was investigated with respect to emerging category effects. We found that the superordinates could be separated by very low-level visual factors (as extracted by the SOM). The model also accounted for the well documented atypicality of body parts and musical instrument superordinates. The model has clear relevance to human object recognition since the model was quicker to learn more typical category exemplars and finally the model also accounted for more than 20% of the naming variance in a sample of 57 brain injured subjects. We conclude that purely bottom-up visual characteristics can explain some important features of category-specific phenomena.     

Using relations within conceptual systems to translate across conceptual systems

According to an "external grounding" theory of meaning, a concept's meaning depends on its connection to the external world. By a "conceptual web" account, a concept's meaning depends on its relations to other concepts within the same system. We explore one aspect of meaning, the identification of matching concepts across systems (e.g. people, theories, or cultures). We present a computational algorithm called ABSURDIST (Aligning Between Systems Using Relations Derived Inside Systems for Translation) that uses only within-system similarity relations to find between-system translations. While illustrating the sufficiency of a conceptual web account for translating between systems, simulations of ABSURDIST also indicate powerful synergistic interactions between intrinsic, within-system information and extrinsic information.     

Explaining modulation of reasoning by belief

Although deductive reasoning is a closed system, one's beliefs about the world can influence validity judgements. To understand the associated functional neuroanatomy of this belief-bias we studied 14 volunteers using event-related fMRI, as they performed reasoning tasks under neutral, facilitatory and inhibitory belief conditions. We found evidence for the engagement of a left temporal lobe system during belief-based reasoning and a bilateral parietal lobe system during belief-neutral reasoning. Activation of right lateral prefrontal cortex was evident when subjects inhibited a prepotent response associated with belief-bias and correctly completed a logical task, a finding consistent with its putative role in cognitive monitoring. By contrast, when logical reasoning was overcome by belief-bias, there was engagement of ventral medial prefrontal cortex, a region implicated in affective processing. This latter involvement suggests that belief-bias effects in reasoning may be mediated through an influence of emotional processes on reasoning.     

Assessment and significance of behavioral avoidance in agoraphobia

Two behavioral avoidance tests were administered, before and after in vivo exposure treatment, to 39 female patients with chronic and severe agoraphobia. The first test consisted of walking alone along a standard course covering several city blocks, and the second of entering and remaining in five different, individually selected phobic situations. Although significant improvement on the tests was observed in the sample as a whole, neither test had a high nosographic sensitivity (nearly two-thirds of the patients completed them initially) and subgroups of avoiders and nonavoiders, classified simultaneously on both tests, did not differ significantly in their clinical characteristics or response to treatment. The difficulty for the behavioral test to account for the majority of variance in phobic avoidance, and the severity of agoraphobia in general, is discussed with particular reference to the differences between the going to and the being in types of phobic situations and the essentially anticipatory nature of anxiety and fear.This research was supported by Grants MH40141 and MH34177 from the National Institute of Mental Health.     

Trait lasting alteration of the brain default mode network in experienced meditators and the experiential selfhood

Based on the finding in novices that four months of meditation training significantly increases frontal default mode network (DMN) module/subnet synchrony while decreasing left and right posterior DMN modules synchrony, the current study tested the prediction whether experienced meditators (those who are practising meditation intensively for several years) had a change in the DMN “trinity” of modules as a baseline trait characteristic and whether this change is in a similar direction as in the novice trainees who practised meditation for only four months. Comparison of functional connectivity within DMN subnets (measured by electroencephalogram operational synchrony in the three separate DMN modules) between five experienced meditators and 10 naïve participants (who were about to start the meditation training) fully support the prediction. Interpretation that links such DMN subnets changes to the three-dimensional components of the experiential selfhood was proposed.     

Human age classification using facial skin aging features and artificial neural network

In this paper a novel method based on facial skin aging features and Artificial Neural Network (ANN) is proposed to classify the human face images into four age groups. The facial skin aging features are extracted by using Local Gabor Binary Pattern Histogram (LGBPH) and wrinkle analysis. The ANN classifier is designed by using two layer feedforward backpropagation neural networks. The proposed age classification framework is trained and tested with face images from PAL face database and shown considerable improvement in the age classification accuracy up to 94.17% and 93.75% for male and female respectively.     

Neural implementation of probabilistic models of cognition

Bayesian models of cognition hypothesize that human brains make sense of data by representing probability distributions and applying Bayes’ rule to find the best explanation for available data. Understanding the neural mechanisms underlying probabilistic models remains important because Bayesian models provide a computational framework, rather than specifying mechanistic processes. Here, we propose a deterministic neural-network model which estimates and represents probability distributions from observable events—a phenomenon related to the concept of probability matching. Our model learns to represent probabilities without receiving any representation of them from the external world, but rather by experiencing the occurrence patterns of individual events. Our neural implementation of probability matching is paired with a neural module applying Bayes’ rule, forming a comprehensive neural scheme to simulate human Bayesian learning and inference. Our model also provides novel explanations of base-rate neglect, a notable deviation from Bayes.     

Concepts as Semantic Pointers: A Framework and Computational Model

The reconciliation of theories of concepts based on prototypes, exemplars, and theory‐like structures is a longstanding problem in cognitive science. In response to this problem, researchers have recently tended to adopt either hybrid theories that combine various kinds of representational structure, or eliminative theories that replace concepts with a more finely grained taxonomy of mental representations. In this paper, we describe an alternative approach involving a single class of mental representations called “semantic pointers.” Semantic pointers are symbol‐like representations that result from the compression and recursive binding of perceptual, lexical, and motor representations, effectively integrating traditional connectionist and symbolic approaches. We present a computational model using semantic pointers that replicates experimental data from categorization studies involving each prior paradigm. We argue that a framework involving semantic pointers can provide a unified account of conceptual phenomena, and we compare our framework to existing alternatives in accounting for the scope, content, recursive combination, and neural implementation of concepts.