Prolonged school closure during the pandemic time in successive waves of COVID-19- vulnerability of children to sexual abuses - A case study in Tamil Nadu, India.

Objectives: The Tamil Nadu government mandated several stay-at-home orders, with restrictions of varying intensities, to contain the first two waves of the COVID-19 pandemic. This research investigates how such orders impacted child sexual abuse (CSA) by using counterfactual prediction to compare CSA statistics with those of other crimes. After adjusting for mobility, we investigate the relationship between situational factors and recorded levels of cases registered under the Protection of Children from Sexual Offences Act (POCSO). The situational factors include the victims' living environment, their access to relief agencies, and the competence and responsiveness of the police. Methods: We adopt an auto-regressive neural network method to make a counterfactual forecast of CSA cases that represents a scenario without stay-at-home orders, relying on the eight-year daily count data of POCSO cases in Tamil Nadu. Using the insights from Google's COVID-19 Community Mobility Reports, we measure changes in mobility across various community spaces during the various phases of stay-at-home orders in both waves in 2020 and 2021. Results: The steep falls in POCSO cases during strict stay-at-home periods, compared with the counterfactual estimates, were -72% (Cliff's delta -0.99) and -36% (Cliff's delta -0.65) during the first and second waves, respectively. However, in the post-lockdown phases, there were sharp increases of 68% (Cliff's delta 0.65) and 36% (Cliff's delta 0.56) in CSA cases during the first and second waves, with concomitantly quicker reporting of case registration. Conclusions: Considering that the median delay in filing CSA complaints was above 30 days in the mild and post-intervention periods, the upsurge of cases in the more relaxed phases indicates increased occurrences of CSA during strict lockdowns. Overall, higher victimization numbers were observed during the prolonged lockdown-induced school closures. Our findings highlight the time gap between the incidents and their registration during the strict lockdown phases.

SphereFace Revived: Unifying Hyperspherical Face Recognition.

This paper addresses the deep face recognition problem under an open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal inter-class distance under a suitably chosen metric space. To this end, hyperspherical face recognition, as a promising line of research, has attracted increasing attention and gradually become a major focus in face recognition research. As one of the earliest works in hyperspherical face recognition, SphereFace explicitly proposed to learn face embeddings with large inter-class angular margin. However, SphereFace still suffers from severe training instability which limits its application in practice. In order to address this problem, we introduce a unified framework to understand large angular margin in hyperspherical face recognition. Under this framework, we extend the study of SphereFace and propose an improved variant with substantially better training stability - SphereFace-R. Specifically, we propose two novel ways to implement the multiplicative margin, and study SphereFace-R under three different feature normalization schemes (no feature normalization, hard feature normalization and soft feature normalization). We also propose an implementation strategy - "characteristic gradient detachment" - to stabilize training. Extensive experiments on SphereFace-R show that it is consistently better than or competitive with state-of-the-art methods.

Discriminative Dictionary Learning for Autism Spectrum Disorder Identification.

Autism Spectrum Disorder (ASD) is a group of lifelong neurodevelopmental disorders with complicated causes. A key symptom of ASD patients is their impaired interpersonal communication ability. Recent study shows that face scanning patterns of individuals with ASD are often different from those of typical developing (TD) ones. Such abnormality motivates us to study the feasibility of identifying ASD children based on their face scanning patterns with machine learning methods. In this paper, we consider using the bag-of-words (BoW) model to encode the face scanning patterns, and propose a novel dictionary learning method based on dual mode seeking for better BoW representation. Unlike k-means which is broadly used in conventional BoW models to learn dictionaries, the proposed method captures discriminative information by finding atoms which maximizes both the purity and coverage of belonging samples within one class. Compared to the rich literature of ASD studies from psychology and neural science, our work marks one of the relatively few attempts to directly identify high-functioning ASD children with machine learning methods. Experiments demonstrate the superior performance of our method with considerable gain over several baselines. Although the proposed work is yet too preliminary to directly replace existing autism diagnostic observation schedules in the clinical practice, it shed light on future applications of machine learning methods in early screening of ASD.

Logsum using Garbled Circuits.

Secure multiparty computation allows for a set of users to evaluate a particular function over their inputs without revealing the information they possess to each other. Theoretically, this can be achieved using fully homomorphic encryption systems, but so far they remain in the realm of computational impracticability. An alternative is to consider secure function evaluation using homomorphic public-key cryptosystems or Garbled Circuits, the latter being a popular trend in recent times due to important breakthroughs. We propose a technique for computing the logsum operation using Garbled Circuits. This technique relies on replacing the logsum operation with an equivalent piecewise linear approximation, taking advantage of recent advances in efficient methods for both designing and implementing Garbled Circuits. We elaborate on how all the required blocks should be assembled in order to obtain small errors regarding the original logsum operation and very fast execution times.

Probabilistic latent variable models as nonnegative factorizations.

This paper presents a family of probabilistic latent variable models that can be used for analysis of nonnegative data. We show that there are strong ties between nonnegative matrix factorization and this family, and provide some straightforward extensions which can help in dealing with shift invariances, higher-order decompositions and sparsity constraints. We argue through these extensions that the use of this approach allows for rapid development of complex statistical models for analyzing nonnegative data.