As the 400 employees of GSC Game World, creators of the hit video game Stalker, filtered into their Kyiv office in January 2022, most didn't even notice the strange buses parked around the corner. While tensions were growing with their neighbours across the border, the frost-coated shlep to the office felt almost normal. Or so they told themselves. As whispers of war spread throughout the country, regular reassurances from their business partners – and President Zelenskiy – made it seem foolish to worry. Life, they were told, would carry on as usual.

Law enforcement's use of facial recognition technology was always controversial. Amazon's surprise announcement that it would put a moratorium on police use of its facial recognition software for the next year underscores the big questions surrounding the technology as protests spark a nationwide debate about police brutality and surveillance tactics. Amazon's brief news release never mentioned the words George Floyd, but my Post colleague Jay Greene notes the company hinted that recent events drove this decision. "We've advocated that governments should put in place stronger regulations to govern the ethical use of facial recognition technology, and in recent days, Congress appears ready to take on this challenge," the company said in a statement. "We hope this one-year moratorium might give Congress enough time to implement appropriate rules, and we stand ready to help if requested."

Robust and computationally efficient anomaly detection in videos is a problem in video surveillance systems. We propose a technique to increase robustness and reduce computational complexity in a Convolutional Neural Network (CNN) based anomaly detector that utilizes the optical flow information of video data. We reduce the complexity of the network by denoising the intermediate layer outputs of the CNN and by using powers-of-two weights, which replaces the computationally expensive multiplication operations with bit-shift operations. Denoising operation during inference forces small valued intermediate layer outputs to zero. The number of zeros in the network significantly increases as a result of denoising, we can implement the CNN about 10% faster than a comparable network while detecting all the anomalies in the testing set. It turns out that denoising operation also provides robustness because the contribution of small intermediate values to the final result is negligible. During training we also generate motion vector images by a Generative Adversarial Network (GAN) to improve the robustness of the overall system. We experimentally observe that the resulting system is robust to background motion.

During winter when the nights are long and days short, getting up for work in the dark and coming home in the dark can be grim. Some of us succumb to the January blues, leading to increased illness, reduced productivity and a general feeling of melancholy. But can clever lighting improve our sleep patterns and lift our moods? "I only feel like I start to breathe properly again after the solstice," says Jacqueline Hazelton, a professor at the US Naval War College in Rhode Island. She's referring to the winter solstice - usually 21 December - the point after which the days start lengthening again following the longest night of the year.