Efficient Human Violence Recognition for Surveillance in Real Time.

Human violence recognition is an area of great interest in the scientific community due to its broad spectrum of applications, especially in video surveillance systems, because detecting violence in real time can prevent criminal acts and save lives. The majority of existing proposals and studies focus on result precision, neglecting efficiency and practical implementations. Thus, in this work, we propose a model that is effective and efficient in recognizing human violence in real time. The proposed model consists of three modules: the Spatial Motion Extractor (SME) module, which extracts regions of interest from a frame; the Short Temporal Extractor (STE) module, which extracts temporal characteristics of rapid movements; and the Global Temporal Extractor (GTE) module, which is responsible for identifying long-lasting temporal features and fine-tuning the model. The proposal was evaluated for its efficiency, effectiveness, and ability to operate in real time. The results obtained on the Hockey, Movies, and RWF-2000 datasets demonstrated that this approach is highly efficient compared to various alternatives. In addition, the VioPeru dataset was created, which contains violent and non-violent videos captured by real video surveillance cameras in Peru, to validate the real-time applicability of the model. When tested on this dataset, the effectiveness of our model was superior to the best existing models.

A blinking focal pattern of re-entrant activity in the avian tectum.

Re-entrant connections are inherent to nervous system organization; however, a comprehensive understanding of their operation is still lacking. In birds, topographically organized re-entrant signals, carried by axons from the nucleus-isthmi-parvocellularis (Ipc), are distinctly recorded as bursting discharges across the optic tectum (TeO). Here, we used up to 48 microelectrodes regularly spaced on the superficial tectal layers of anesthetized pigeons to characterize the spatial-temporal pattern of this axonal re-entrant activity in response to different visual stimulation. We found that a brief luminous spot triggered repetitive waves of bursting discharges that, appearing from initial sources, propagated horizontally to areas representing up to 28° of visual space, widely exceeding the area activated by the retinal fibers. In response to visual motion, successive burst waves started along and around the stimulated tectal path, tracking the stimulus in discontinuous steps. When two stimuli were presented, the burst-wave sources alternated between the activated tectal loci, as if only one source could be active at any given time. Because these re-entrant signals boost the retinal input to higher visual areas, their peculiar dynamics mimic a blinking "spotlight," similar to the internal searching mechanism classically used to explain spatial attention. Tectal re-entry from Ipc is thus highly structured and intrinsically discontinuous, and higher tectofugal areas, which lack retinotopic organization, will thus receive incoming visual activity in a sequential and piecemeal fashion. We anticipate that analogous re-entrant patterns, perhaps hidden in less bi-dimensionally organized topographies, may organize the flow of neural activity in other parts of the brain as well.

Prestimulus alpha power is related to the strength of stimulus representation.

Spatial attention can modulate behavioural performance and is associated with several electrophysiological markers. In this study, we used multivariate pattern analysis in electrophysiology data to investigate the effects of covert spatial attention on the quality of stimulus processing and its underlying mechanisms. Our results show that covert spatial attention led to (i) an anticipatory alpha power desynchronization; (ii) enhanced stimuli identity information. Moreover, we found that alpha power fluctuations in anticipation of the relevant stimuli boosted and prolonged the coding of stimulus identity.

"Shepherd's crook" neurons drive and synchronize the enhancing and suppressive mechanisms of the midbrain stimulus selection network.

The optic tectum (TeO), or superior colliculus, is a multisensory midbrain center that organizes spatially orienting responses to relevant stimuli. To define the stimulus with the highest priority at each moment, a network of reciprocal connections between the TeO and the isthmi promotes competition between concurrent tectal inputs. In the avian midbrain, the neurons mediating enhancement and suppression of tectal inputs are located in separate isthmic nuclei, facilitating the analysis of the neural processes that mediate competition. A specific subset of radial neurons in the intermediate tectal layers relay retinal inputs to the isthmi, but at present it is unclear whether separate neurons innervate individual nuclei or a single neural type sends a common input to several of them. In this study, we used in vitro neural tracing and cell-filling experiments in chickens to show that single neurons innervate, via axon collaterals, the three nuclei that comprise the isthmotectal network. This demonstrates that the input signals representing the strength of the incoming stimuli are simultaneously relayed to the mechanisms promoting both enhancement and suppression of the input signals. By performing in vivo recordings in anesthetized chicks, we also show that this common input generates synchrony between both antagonistic mechanisms, demonstrating that activity enhancement and suppression are closely coordinated. From a computational point of view, these results suggest that these tectal neurons constitute integrative nodes that combine inputs from different sources to drive in parallel several concurrent neural processes, each performing complementary functions within the network through different firing patterns and connectivity.

The isthmic nuclei providing parallel feedback connections to the avian tectum have different neurochemical identities: Expression of glutamatergic and cholinergic markers in the chick (Gallus gallus).

Retinal inputs to the optic tectum (TeO) triggered by moving stimuli elicit synchronized feedback signals from two isthmic nuclei: the isthmi parvocelullaris (Ipc) and isthmi semilunaris (SLu). Both of these nuclei send columnar axon terminals back to the same tectal position receiving the retinal input. The feedback signals from the Ipc seem to act as an attentional spotlight by selectively boosting the propagation of retinal inputs from the tectum to higher visual areas. Although Ipc and SLu nuclei are widely considered cholinergic because of their immunoreactivity for choline acetyltransferase (ChAT), contradictory findings, including the expression of the vesicular glutamate transporter 2 (VGluT2) mRNA in Ipc neurons, have raised doubts about the purely cholinergic nature of this nucleus. In this study, in chicks, we revise the neurochemical identity of the isthmic nuclei by using in situ hybridization assays for VGluT2 along with three cholinergic markers: the vesicular acetylcholine transporter (VAChT), the high-affinity choline transporter (CHT1) and ChAT. We found that neurons in the SLu showed strong mRNA expression of all three cholinergic markers, whereas the expression of VAChT mRNA in the Ipc was undetectable in our essays. Instead, Ipc neurons exhibited a strong expression of VGluT2 mRNA. Immunohistochemistry assays showed VGluT2 immunoreactivity in the TeO codistributing with anterogradely labeled Ipc axon-terminal boutons, further supporting a glutamatergic function for the Ipc nucleus. Therefore, our results strongly suggest that, in the chick, whereas the feedback from the SLu to the TeO is indeed cholinergic, the feedback from the Ipc has a marked glutamatergic component.

Monitoramento do Tempo de Reação como estratégia de avaliação cognitiva e acompanhamento psicológico de judocas / Reaction Time monitoring as a cognitive assessment strategy and psychologicalaccompaniment of judokas

Medidas do tempo de reação manual têm sido extensivamente empregadas pela neurociência cognitiva para o estudo de funções psicomotoras em diferentes circunstâncias, incluindo modelos aplicados ao contexto do esporte de alto rendimento. O presente estudo teve a finalidade de investigar possíveis aplicações de um teste de reação manual específico - protocolo de Simon - como estratégia de avaliação cognitiva e acompanhamento de atletas na área da psicologia do esporte. Para isso, dois atletas de judô foram testados semanalmente, durante o período de um mês, com o teste de Simon. As análises demonstraram que é possível identificar variações no desempenho individual entre as diferentes sessões realizadas. O atleta 1 apresentou diferenças significativas entre as sessões de avaliação, reduzindo progressivamente seu tempo de reação ao longo das três primeiras sessões,mas lentificando novamente suas respostas na última sessão de avaliação. Por sua vez, o atleta 2, apresentou um perfil diferente, oscilando mais seu desempenho ao longo do acompanhamento mensal (lentificou suas respostas da primeira para a terceira sessão e reduziu seus tempos de resposta na quarta avaliação). Esses resultados trazem evidências a favor da utilização do teste de Simon como mais uma estratégia de avaliação cognitiva no esporte, apresentando sensibilidade às variações individuais de desempenho e também obedecendo ao princípio da individualidade biológica, permitindo a distinção dos padrões de resposta entre os indivíduos. Os resultados obtidos fortalecem o potencial das medidas psicofísicas ao revelarem uma forma alternativa de avaliação em comparação aos tradicionais métodos explícitos da psicologia do esporte, além de propiciarem uma abordagem informatizada para avaliação situacional de capacidades de integração sensório-motora, tomada de decisão e atenção espacial.

Manual reaction measures have been extensively employed by cognitive neuroscience to psychomotor studies in different circumstances, including applied methods to the high performance sportive context. The present study aimed to studypossible applications of a specific reaction time procedure (Simon task) as a cognitive assessment strategy and accompaniment in the sport psychology area. In this study, two judo athletes were weekly evaluated with the Simon task during a period of one month. Analyses have shown that is possible to identify variations in individual performance between the different practiced sessions. The Athlete 1 showed significant differences between the assessment sessions, progressively reducing your reaction time over the first three sessions, but slowing the responses at the last session. The athlete 2, showed a different profile, varying his performance over the monthly monitoring (slowed your responses from the first to the third session and reduced the reaction time on fourth assessment). These results provide evidences in favour for the use of the Simon test as more one cognitive assessment strategy in sport, showing sensitivity to individual performance variations and also obeying the principle of biological individuality, allowing the distinction of response patterns between the individuals. The results strengthen the potential use of psychophysics measures revealing an alternative way for assessment compared totraditional explicit methods of sport psychology, providing a computerized approach for situational assessment of sensorimotor integration, decision making and spatial attention abilities (AU)

Monitoramento do tempo de reação como estratégia de avaliação cognitiva e acompanhamento psicológico de judocas / Reaction time monitoring as a cognitive assessment strategy and psychological accompaniment of judokas

Medidas do tempo de reação manual têm sido extensivamente empregadas pela neurociência cognitiva para o estudo de funções psicomotoras em diferentes circunstâncias, incluindo modelos aplicados ao contexto do esporte de alto rendimento. O presente estudo teve a finalidade de investigar possíveis aplicações de um teste de reação manual específico - protocolo de Simon - como estratégia de avaliação cognitiva e acompanhamento de atletas na área da psicologia do esporte. Para isso, dois atletas de judô foram testados semanalmente, durante o período de um mês, com o teste de Simon. As análises demonstraram que é possível identificar variações no desempenho individual entre as diferentes sessões realizadas. O atleta 1 apresentou diferenças significativas entre as sessões de avaliação, reduzindo progressivamente seu tempo de reação ao longo das três primeiras sessões,mas lentificando novamente suas respostas na última sessão de avaliação. Por sua vez, o atleta 2, apresentou um perfil diferente, oscilando mais seu desempenho ao longo do acompanhamento mensal (lentificou suas respostas da primeira para a terceira sessão e reduziu seus tempos de resposta na quarta avaliação). Esses resultados trazem evidências a favor da utilização do teste de Simon como mais uma estratégia de avaliação cognitiva no esporte, apresentando sensibilidade às variações individuais de desempenho e também obedecendo ao princípio da individualidade biológica, permitindo a distinção dos padrões de resposta entre os indivíduos. Os resultados obtidos fortalecem o potencial das medidas psicofísicas ao revelarem uma forma alternativa de avaliação em comparação aos tradicionais métodos explícitos da psicologia do esporte, além de propiciarem uma abordagem informatizada para avaliação situacional de capacidades de integração sensório-motora, tomada de decisão e atenção espacial.

Manual reaction measures have been extensively employed by cognitive neuroscience to psychomotor studies in different circumstances, including applied methods to the high performance sportive context. The present study aimed to studypossible applications of a specific reaction time procedure (Simon task) as a cognitive assessment strategy and accompaniment in the sport psychology area. In this study, two judo athletes were weekly evaluated with the Simon task during a period of one month. Analyses have shown that is possible to identify variations in individual performance between the different practiced sessions. The Athlete 1 showed significant differences between the assessment sessions, progressively reducing your reaction time over the first three sessions, but slowing the responses at the last session. The athlete 2, showed a different profile, varying his performance over the monthly monitoring (slowed your responses from the first to the third session and reduced the reaction time on fourth assessment). These results provide evidences in favour for the use of the Simon test as more one cognitive assessment strategy in sport, showing sensitivity to individual performance variations and also obeying the principle of biological individuality, allowing the distinction of response patterns between the individuals. The results strengthen the potential use of psychophysics measures revealing an alternative way for assessment compared totraditional explicit methods of sport psychology, providing a computerized approach for situational assessment of sensorimotor integration, decision making and spatial attention abilities

Non-invasive induction and cancellation of visuo-spatial deficits by repetitive Transcranial Magnetic Stimulation (rTMS): Lessons on “surgery-less” manipulation of complex visuo-spatial brain networks

Repetitive Magnetic Stimulation (rTMS) has shown to modify the excitability of targeted cortical regions in animals and humans, thus transiently altering the efficiency of neural projections within extended brain networks. Adequate processing and behavioral output depend on a given ‘state’ of functional interactions between cortical and subcortical nodes within this network. We applied rTMS trains targeted at the visuoparietal (VP) cortex, which is a crucial cortical node of an extended visuo-spatial neural network, in both, intact (n=2) and injured cats (n=2) with unilateral ablation of the VP region. All four intact cats were intensively trained in a set of visuo-spatial tasks consisting in the detection and localization of moving or static targets. In two of these cats, a 50 mm circular coil was centered on the left VP cortex and Sham or real rTMS was delivered during 20 minutes at 1 Hz. Real but not Sham rTMS significantly increased the number of errors in orienting responses towards static but not moving targets, presented at the contralateral visual hemifield (38±4%; and 48±3% p<0.05 vs. pre rTMS), whereas no increase respect to baseline was observed for ipsilateral targets (5±2%; 2±1%; n.s). Performance went back to baseline error levels 45 minutes after the end of the stimulation (4±2; 6±1%). In 2 other animals, the right or left parietal and primary visual cortex was surgically removed, generating a Daily stimulation with 1 Hz rTMS on the intact VP region resulted in a progressive reduction of detection¬orienting mistakes to moving but not static stimuli (down to 34±5% and 28±4% errors; p<0.05). We conclude that rTMS is able to interact with brain networks in both ways, transiently disrupting visuo-spatial processing in normal animals, and also canceling spatial neglect generated by lesions of the same areas. It constitutes, thus, a non-invasive ‘surgery-less’ method to manipulate brain activity and promote recovery after injuries.