An integrated system for human action recognition from video using hidden Markov model

In this paper, we present an integrated system for real-time automatic detection of human actions from video. The proposed approach uses the boundary of humans as the main feature for recognizing actions. Background subtraction is performed using Gaussian mixture model. Then, features are extracted from silhouettes and Vector Quantization is used to map features into symbols (bag of words approach). Finally, actions are detected using the Hidden Markov Model. The proposed system was validated using a newly collected real- world dataset. The obtained results show that the system is capable of achieving robust human detection, in both indoor and outdoor environments. Moreover, promising classification results were achieved when detecting two basic human actions: walking and sitting.

Noradrenergic stimulation enhances human action monitoring

Noradrenergic neurotransmission has been associated with the modulation of higher cognitive functions mediated by the prefrontal cortex. In the present study, the impact of noradrenergic stimulation on the human action-monitoring system, as indexed by eventrelated brain potentials, was examined. After the administration of a placebo or the selective 2 -adrenoceptor antagonist yohimbine, which stimulates firing in the locus ceruleus and noradrenaline release, electroencephalograpic recordings were obtained from healthy volunteers performing a letter flanker task. Yohimbine led to an increase in the amplitude of the error-related negativity in conjunction with a significant reduction of action errors. Reaction times were unchanged, and the drug did not modify the N2 in congruent versus incongruent trials, a measure of preresponse conflict, or posterror adjustments as measured by posterror slowing of reaction time. The present findings suggest that the locus ceruleusnoradrenaline system exerts a rather specific effect on human action monitoring.

Nucleus accumbens is involved in human action monitoring: evidence from invasive electrophysiological recordings

The Nucleus accumbens (Nacc) has been proposed to act as a limbic-motor interface. Here, using invasive intraoperative recordings in an awake patient suffering from obsessive-compulsive disease (OCD), we demonstrate that its activity is modulated by the quality of performance of the subject in a choice reaction time task designed to tap action monitoring processes. Action monitoring, that is, error detection and correction, is thought to be supported by a system involving the dopaminergic midbrain, the basal ganglia, and the medial prefrontal cortex. In surface electrophysiological recordings, action monitoring is indexed by an error-related negativity (ERN) appearing time-locked to the erroneous responses and emanating from the medial frontal cortex. In preoperative scalp recordings the patient's ERN was found to be signifi cantly increased compared to a large (n = 83) normal sample, suggesting enhanced action monitoring processes. Intraoperatively, error-related modulations were obtained from the Nacc but not from a site 5 mm above. Importantly, crosscorrelation analysis showed that error-related activity in the Nacc preceded surface activity by 40 ms. We propose that the Nacc is involved in action monitoring, possibly by using error signals from the dopaminergic midbrain to adjust the relative impact of limbic and prefrontal inputs on frontal control systems in order to optimize goal-directed behavior.

A framework to understand human action

This paper consists in an analysis of two explanatory models of human behaviour which play a prominent role in the contemporary literature on human action. The first model - the causalist - aims at explaining action in terms of causes and general laws. The second model - the intentionalist - explains human action in terms of intentions and practical syllogism. The difficulties of both models are presented and in the last part of the essay we propose one alternative model, based on the notion of retroduction.

ReadingAct RGB-D action dataset and human action recognition from local features

For general home monitoring, a system should automatically interpret people’s actions. The system should be non-intrusive, and able to deal with a cluttered background, and loose clothes. An approach based on spatio-temporal local features and a Bag-of-Words (BoW) model is proposed for single-person action recognition from combined intensity and depth images. To restore the temporal structure lost in the traditional BoW method, a dynamic time alignment technique with temporal binning is applied in this work, which has not been previously implemented in the literature for human action recognition on depth imagery. A novel human action dataset with depth data has been created using two Microsoft Kinect sensors. The ReadingAct dataset contains 20 subjects and 19 actions for a total of 2340 videos. To investigate the effect of using depth images and the proposed method, testing was conducted on three depth datasets, and the proposed method was compared to traditional Bag-of-Words methods. Results showed that the proposed method improves recognition accuracy when adding depth to the conventional intensity data, and has advantages when dealing with long actions.

A framework to understand human action

O trabalho consiste numa análise de dois modelos explicativos do comportamento humano considerados fundamentais na literatura contemporânea sobre teoria da ação. O primeiro modelo, o causalista, tenta explicar as ações em termos de causas e leis gerais. O segundo explica a ação em termos de intenções e silogismos práticos. As dificuldades e problemas de ambos modelos são apresentadas e na última parte do ensaio propomos um modelo alternativo baseado na noção de retrodução.

Image summarisation: human action description from static images

Dissertação de Mestrado, Processamento de Linguagem Natural e Indústrias da Língua, Faculdade de Ciências Humanas e Sociais, Universidade do Algarve, 2014

Serviço social, educação e complexidade: um diálogo com o homo complexus professor

Pós-graduação em Serviço Social - FCHS

Attentional modulation of neural responses to action observation: Implications for models of the human 'mirror' system

In primates, the observation of meaningful, goaldirected actions engages a network of cortical areas located within the premotor and inferior parietal lobules. Current models suggest that activity within these regions arises relatively automatically during passive action observation without the need for topdown control. Here we used functional magnetic resonance imaging to determine whether cortical activit)' associated with action observation is modulated by the strategic allocation of selective attention. Normal observers viewed movie clips of reach-to-grasp actions while performing an easy or difficult visual discrimination at the fovea. A wholebrain analysis was performed to determine the effects of attentional load on neural responses to observed hand actions. Our results suggest that cortical areas involved in action observation are significantiy modulated by attentional load. These findings have important implications for recent attempts to link the human action-observation system to response properties of "mirror neurons" in monkeys.

From the human rights-based approach to an ecological approach on how to achieve successful inclusion in international disability education

The barriers that people with disabilities face around the world are not only inherent to the limitations resulting from the disability itself, but, more importantly, these barriers rest with the societal technologies of exclusion. Using a mixed methodology approach, I conduct a quest to revealing several societal factors that limit full participation of people with disabilities in their communities, which will contribute to understanding and developing a more comprehensive framework for full inclusion of people with disabilities into the society. First, I conduct a multiple regression analysis to seek whether there is a statistical relationship between the national level of development, the level of democratization, and the level of education within a country’s population on one hand, and expressed concern for and preparedness to improve the quality of life for people of disabilities on another hand. The results from the quantitative methodology reveal that people without disabilities are more prepared to take care of people with disabilities when the level of development of the country is higher, when the people have more freedom of expression and hold the government accountable for its actions, and when the level of corruption is under control. However, a greater concern for the well-being of people with disabilities is correlated with a high level of country development, a decreased value of political stability and absence of violence, a decreased level of government effectiveness, and a greater level of law enforcement. None of the dependent variables are significantly correlated with the level of education from a given country. Then, I delve into an interpretive analysis to understand multiple factors that contribute to the construction of attitudes and practices towards people with disabilities. In doing this, I build upon the four main principles outlined by the United Nations as strongly recommended to be embedded in all international programmes: (1) identification of claims of human rights and the corresponding obligations of governments, hence, I assess and analyze disability rights in education, looking at United Nation, United States, and European Union Perspectives Educational Rights Provisions for People with Disabilities (Ch. 3); (2) estimated capacity of individuals to claim their rights and of governments to fulfill their obligations, hence, I look at the people with disabilities as rights-holders and duty-bearers and discuss the importance of investing in special capital in the context of global development (Ch. 4); (3) programmes monitor and evaluate the outcomes and the processes under the auspices of human rights standards, hence, I look at the importance of evaluating the UN World Programme of Action Concerning People with Disabilities from multiple perspectives, as an example of why and how to monitor and evaluate educational human rights outcomes and processes (Ch. 5); and (4) programming should reflect the recommendations of international human rights bodies and mechanisms, hence, I focus on programming that fosters development of the capacity of people with disabilities, that is, planning for an ecology of disabilities and ecoducation for people with disabilities (Ch. 6). Results from both methodologies converge to a certain point, and they further complement each other. One common result for the two methodologies employed is that disability is an evolving concept when viewed in a broader context, which integrates the four spaces that the ecological framework incorporates. Another common result is that factors such as economic, social, legal, political, and natural resources and contexts contribute to the health, education and employment opportunities, and to the overall well-being of people with disabilities. The ecological framework sees all these factors from a meta-systemic perspective, where bi-directional interactions are expected and desired, and also from a human rights point of view, where the inherent value of people is upheld at its highest standard.

A alfabetização/educação de surdos na história da educação do Espírito Santo

Este trabalho integra um grupo de pesquisas desenvolvidas pela linha de pesquisa Educação e Linguagens, do Programa de Pós-Graduação da Universidade Federal do Espírito Santo. Trata de uma pesquisa histórica que tem por objetivo investigar a história da alfabetização de surdos no Espírito Santo, nas décadas de 1950 a 1970, a partir da tese inicial de que a educação/alfabetização de crianças surdas, no Espírito Santo, nesse período, tinha por finalidade ensinar a língua nacional, por meio da oralização, tendo em vista o projeto desenvolvimentista adotado pelo então Presidente da República, Juscelino Kubistchek. Fundamenta-se nas concepções de Marc Bloch (2001), ao considerar a História como a ciência dos homens no tempo, com o objetivo de compreender a ação humana, de acordo com as condições históricas de sua época, e nas contribuições da concepção bakhtiniana de linguagem, em especial, no conceito de texto como enunciado, considerando que cada texto/documento traz em seu bojo uma história vivida por sujeitos em dado contexto social e histórico. Nessa direção, a partir da análise de documentos escolares, textos jornalísticos, cartilhas, materiais pedagógicos e documentos oficiais, o trabalho se estruturou no sentido de conhecer o contexto nacional que deu origem às primeiras iniciativas de descentralização na educação de surdos, culminando com a criação de salas especiais em vários Estados brasileiros, incluindo o Espírito Santo. As repercussões, em âmbito local, foram analisadas a partir de dois eixos. No primeiro, focalizaram os aspectos políticos, evidenciando que a desresponsabilização do Poder Público facilitou a parceria entre a esfera pública e a esfera privada na configuração das classes especiais, dentro das escolas comuns. No segundo, destacaram que o Método Oral e o Método Perdoncini, que fundamentaram o processo de alfabetização e que tinham como finalidade ensinar a língua oficial do País, na modalidade oral, dialogaram com as concepções pedagógicas e psicológicas da época, tornando o processo claramente escolar. Conclui que o período foi marcado por um projeto educacional consistente e coerente com os postulados da época, tendo na ação responsável e polifônica da professora Álpia Couto-Lenzi a sua principal interlocutora.

Addiction in Action

As human action, drinking alcohol or smoking cigarettes, for instance, are phenomena that are familiar to most people. We recognise when people use drugs or gamble whether that happens in the television or around us. Sometimes we call these actions addictions. Addictive actions are actions that puzzle us. This puzzlement has raised different kinds of views on addiction that describe the phenomenon in different ways. The proponents of the views pick features that they consider to be sufficient in capturing the phenomenon. The disease view emphasises that addicted individuals are not in control over their own actions, whereas the choice view highlights addicted individuals’ capacity to act according to their own preferences. Some see addiction as a defect of will and addictive action is a manifestation of that. Sometimes they all insist on referring to the same group of people and describing the same actions with seemingly contradictory terms. What happens when an addicted individual acts in accordance with his addiction? This thesis also tries to answer this question and make this kind of action and agency understandable. By showing that these three common views fall short of capturing the phenomenon, I will provide characteristics that jointly suffice for something to be labelled addiction, but which are not, however, individually necessary (or sufficient) for addiction. Those characteristics are strong desire, myopia, biased decision-making, and weakness of will. Furthermore, they should be understood in the framework of diachronic, active agency. They contribute to a view on addictive action that consists of different kinds of actions. Acknowledging the variety of nuanced human action, the understanding of addictive action is increased and this may also be utilised in addiction-related policies and treatment. The emphasis of my study lies specifically on understanding addiction as action by the means of analytical philosophy.

Mediated action, narratives of risk-taking, and identity formation in adolescents with a visual impairment

The purpose of this project was to discern the inherent tension present in narratives told by adolescents with a visual impairment as they attempted to make sense of their experiences, specifically those surrounding risk. Mediated action, based on the foundational work of Vygotsky and Bakhtin, was used as both a theoretical and methodological approach; it is the theory that there are two components that constitute any human action: the "agent," or the person who is doing the acting, and the "mediational means" that he or she is using to accomplish the action in question. Tension ensues as neither is able to fully explain human behaviour. Ten adolescents with a visual impairment participated in a narrative interview, revealing numerous counter-narratives surrounding risk-taking, including "experimentation undertaken using good judgment." Participants offered examples of how they engaged, appropriated, resisted and transformed the dominant narratives of disability and adolescence in their identity formation.