Deep neural network models for IMU sensor-based human activity recognition (HAR) that are trained from controlled, well-curated datasets suffer from poor generalizability in practical deployments. However, data collected from naturalistic settings often contains significant label noise. In this work, we examine two in-the-wild HAR datasets and DivideMix, a state-of-the-art learning with noise labels (LNL) method to understand the extent and impacts of noisy labels in training data. Our empirical analysis reveals that the substantial domain gaps among diverse subjects cause LNL methods to violate a key underlying assumption, namely, neural networks tend to fit simpler (and thus clean) data in early training epochs. Motivated by the insights, we design VALERIAN, an invariant feature learning method for in-the-wild wearable sensor-based HAR. By training a multi-task model with separate task-specific layers for each subject, VALERIAN allows noisy labels to be dealt with individually while benefiting from shared feature representation across subjects. We evaluated VALERIAN on four datasets, two collected in a controlled environment and two in the wild.

It can be hard to predict which films will triumph at the box office and which will completely bomb. Just ask the people who made the recently released sci-fi thriller Valerian, which cost a shade under $200 million to make--and after one weekend, has made back just $23.5 million in total ticket sales. Perhaps in the future, forecasting audience enjoyment won't be such an inexact science. Disney and the California Institute of Technology have teamed up to build an artificial intelligence system that they say can measure moviegoers' facial reactions to determine just how much they're really liking a film. According to a paper published collaboratively by the two institutions last week and first spotted by Digital Trends, the team of researchers had test audiences watch Disney movies and used an infrared high-definition camera to capture their reactions.

Valerian and the City of a Thousand Planets flopped. At least that's the way things look after the opening weekend of the Luc Besson-written and -directed sci-fi film: It headed into Monday with just about $17 million in receipts and a splattery 54 percent on Rotten Tomatoes (and a better audience score of 60 percent, to be fair). Now, I spent bits and pieces of the last two years working on a print feature about Besson and Valerian. But it wasn't exactly about the film itself; by the time I had put my story to bed, I'd only seen about 20 minutes of the actual movie. This is a not-so-secret secret of print magazine features: The lead time of monthly magazines like WIRED means that the journalism is often done before the film.

We'll take a look back at some of the big stories from earlier this week, plus key updates like NASA's tips for viewing a solar eclipse. Getting the weekend started early.DC security robot says everything is fine, throws itself into pool Don't read too much into this, but a security robot face-planted into an indoor fountain inside of a Washington, DC office building. Important information.NASA doesn't want you to go blind during the solar eclipse Please, for the love of god (and your eyesight), do not try to make your own eclipse glasses. Buy a pair, and make sure they're less than three years old with lenses that are in good shape. The much-celebrated full solar eclipse is just one month away for those in the continental United States, and NASA really does not want you to go blind when it finally happens.

Worry not, because our Five to Try column is here to spotlight the Play Store's most enticing new picks. Minecraft: Story Mode's second season leads the week's offerings, as Telltale's episodic affair builds a fun narrative from the block-building sensation. Elsewhere, the official Shake Shack app is finally on Android for mobile ordering, Hinge puts a different spin on the familiar dating app, The Lion's Song is an intriguing indie adventure, and freemium game Valerian: City of Alpha can get you ready for the upcoming sci-fi flick. Give these a look, and if you need even more recent picks, then loop back on last week's column as well. Minecraft is beloved for its open-ended design, letting players build their own adventures in blocky worlds--but last year's Minecraft: Story Mode handled most of the heavy lifting with a five-part episodic adventure series.

Reviews for the Luc Besson-directed sci-fi flick "Valerian and the City of a Thousand Planets" filed in Tuesday, with most critics describing the film as a beautiful and expensive disaster. Adapted from the French comic "Valerian et Laureline," Dane Dehaan and Cara Delevinge star in the STX-EuraCorp production slated to premiere July 21. "Valerian" has earned a range of polarized reactions from "simply childish" to "mind-meltingly beautiful and strange" from top critics, making it hard to pin down as a viable contender for the summer box office. The sci-fi project currently holds 74 percent on Rotten Tomatoes' aggregator scale. The Hollywood Reporter claimed that "Valerian" is a potential Razzie contender, saying: "The Razzies don't need to wait until the end of the year to anoint a winner for 2017. The Golden Turkey Awards should be republished with a new cover."