Applied Sports Science newsletter – July 7, 2020

… Fishlock has been unable to kick a ball for the longest period of her career after suffering an anterior cruciate ligament injury on club duty for Reign in a National Women’s Soccer League (NWSL) game against Utah Royals more than a year ago.

The 33-year-old had a loan spell with Champions League winners Lyon earlier in the season and believes differences in training methods and player rehabilitation during her time in France played a part in the serious knee injury she suffered last year.

“Being injured is not nice but it’s given me a little bit of time to get my body right and my mind right.

Were it not for the global pandemic, this would have marked the middle weekend of Wimbledon, the peak of the tennis season. It might also have provided Rafael Nadal, now 34, a chance to eclipse Roger Federer for most Major singles titles in history. Whenever it is Nadal plays next, he will be trying to add to his credentials as the greatest player of all time. But Nadal doesn’t play tennis so much as he works it, blistering the ball with annihilating force, lacing it with somersaulting topspin, and imposing his will on the opponent. His relentless approach is strikingly effective and, as we first told you last January, strikingly at odds with the vibe on the Spanish island where he was born, lives now and vows never to leave. Nadal invited us to his hometown last December, during what passes for an off-season in tennis, five weeks most players use to rest up before the start of a new season. [video, 14:00]

… “There’s supreme confidence and belief in myself and in my game,” former Marquette star Markus Howard said. “In this process, I just know all it takes is one team. I’m not sitting here thinking all 32 teams are going to love me. I’m realistic.”

CBS Sports checked in with Howard from his family home in Chandler, Arizona, on June 25 — what would have been the day of the draft had it not been postponed. Howard’s been home all but three days since mid-March. The one break in his schedule came in the middle of April when he flew back to Milwaukee to lonesomely clean out his things and pack up what he couldn’t take before. In mid-March Howard flew home within 48 hours of the cancellation of the Big East Tournament.

… In a typical set of spring organized team activities, Bills coach Sean McDermott said about 500 practice reps take place.

With all of those lost, McDermott and his staff are busier than usual at this time of year. With training camp scheduled to begin July 28, one of the top priorities for the Bills’ fourth-year coach is figuring out how to safely ramp up physical activity for 91 players who might not be in tip-top shape.

Postponing the Tokyo Olympics by a full year has thrown a huge wrench in the lives of Canada’s elite athletes in ways that transcend their sports careers, according to a former Olympic champion.

“To suddenly say, ‘one more year,’ sucks all of the oxygen out of the room … because all of a sudden, the plans they had were garbage,” said Marnie McBean, a three-time Olympic gold medallist in rowing and Canada’s chef de mission for the Tokyo Games.

For champion-calibre athletes, an event as major as the Olympics is more than just a date on a calendar. They’ve been training their bodies and minds to prepare, often for years in advance. [audio, 7:37]

… Speaking with ESPN’s Stefano Fusaro, Gonzalez said, “The priority is getting guys healthy, feeling safe, so that we can be strong in the long term, which I know we’re going to accomplish.”

Based on data provided by MLS, as well as reports elsewhere, Dallas has been by far the hardest hit team in MLS in terms positive tests. Dallas had three players test positive before the team even left for Orlando. That has since been followed by 10 players and one coach testing positive. Gonzalez said that the FCD players and staff have been quarantined in their rooms for six days, only able to meet via Zoom.

It has been hypothesized that the central nervous system simplifies the production of movement by limiting motor commands to a small set of modules known as muscle synergies. Recently, investigators have questioned whether a low-dimensional controller can produce the rich and flexible behaviours seen in everyday movements. To study this issue, we implemented muscle synergies in a biomechanically realistic model of the human upper extremity and performed computational experiments to determine whether synergies introduced task performance deficits, facilitated the learning of movements, and generalized to different movements. We derived sets of synergies from the muscle excitations our dynamic optimizations computed for a nominal task (reaching in a plane). Then we compared the performance and learning rates of a controller that activated all muscles independently to controllers that activated the synergies derived from the nominal reaching task. We found that a controller based on synergies had errors within 1 cm of a full-dimensional controller and achieved faster learning rates (as estimated from computational time to converge). The synergy-based controllers could also accomplish new tasks—such as reaching to targets on a higher or lower plane, and starting from alternative initial poses—with average errors similar to a full-dimensional controller. [full text]

Computer vision summit CVPR has just (virtually) taken place, and like other CV-focused conferences, there are quite a few interesting papers. More than I could possibly write up individually, in fact, so I’ve collected the most promising ones from major companies here.

Facebook, Google, Amazon and Microsoft all shared papers at the conference — and others too, I’m sure — but I’m sticking to the big hitters for this column.

Group activity detection in soccer can be done by using either video data or player and ball trajectory data. In current soccer activity datasets, activities are labelled as atomic events without a duration. Given that the state-of-the-art activity detection methods are not well-defined for atomic actions, these methods cannot be used. In this work, we evaluated the effectiveness of activity recognition models for detecting such events, by using an intuitive non-maximum suppression process and evaluation metrics. We also considered the problem of explicitly modeling interactions between players and ball. For this, we propose self-attention models to learn and extract relevant information from a group of soccer players for activity detection from both trajectory and video data. We conducted an extensive study on the use of visual features and trajectory data for group activity detection in sports using a large scale soccer dataset provided by Sportlogiq. Our results show that most events can be detected using either vision or trajectory-based approaches with a temporal resolution of less than 0.5 seconds, and that each approach has unique challenges.

This paper strives to recognize individual actions and group activities from videos. While existing solutions for this challenging problem explicitly model spatial and temporal relationships based on location of individual actors, we propose an actor-transformer model able to learn and selectively extract information relevant for group activity recognition. We feed the transformer with rich actor-specific static and dynamic representations expressed by features from a 2D pose network and 3D CNN, respectively. We empirically study different ways to combine these representations and show their complementary benefits. Experiments show what is important to transform and how it should be transformed. What is more, actor-transformers achieve state-of-the-art results on two publicly available benchmarks for group activity recognition, outperforming the previous best published results by a considerable margin.

FC Dallas has withdrawn from the MLS is Back tournament in Florida after 10 players tested positive for coronavirus.

The league said Monday that of the 557 players sequestered at a pair of Walt Disney World hotels, 13 have tested positive: 10 from Dallas, two from Nashville and one from Columbus. Additionally, a Dallas coach also tested positive.

“The decision to have them not participate in the tournament is in the best interests of everyone, of the Dallas players and the other 25 teams, and allows us to continue to manage the health and safety of our players while continuing to go forward with our plan,” MLS Commissioner Don Garber told The Associated Press in a telephone interview on Monday.

As youth sports return in some communities, there’s a greater need than ever for parents to identify the right sports to meet their child’s health needs. Different sports have different benefits, and different children have different needs.

Kids have been missing the physical, social and emotional benefits of playing sports for many months. A new study by the University of Wisconsin found that 65% of adolescent athletes in Wisconsin reported anxiety symptoms in May, with 25% suffering moderate or severe anxiety. Using historical data, the study found the rate of mild to severe depression in youth athletes increased from 31% to 68%. Physical activity was down 50% in May.

First and foremost, any return to play should follow advice from public health experts on whether it’s safe based on local transmission of COVID-19. Phased returns to sports are best. High-contact sports may carry different COVID-19 risks than low-contact sports. The Aspen Institute’s Return to Play risk assessment tool offers guidance on assessing sports based on the risks of contracting and transmitting the virus.

… To support the safe return to sport, a decision-making framework to provide structure and consistency when considering the risk of virus transmission for team sports, may be useful, even if the parameters (e.g., player proximity, duration of proximity breach) change with the emergence of sport specific evidence and guidance. As such, we propose the Team Sport Risk Exposure framework (Figure 1) to guide decisions around possible law change, non-law driven player behaviour change, training practice modifications, and discussions around the Public Health led sport-specific ‘test and trace’ process to determine individual risk for potential case contacts (should a squad or support staff member test positive with COVID-19). The framework considers proximity, accumulative proximity exposure and the frequency and duration of face-to-face exposure. It defines thresholds for fleeting and non-fleeting exposure and proposes an accumulative threshold of 15 minutes for medium risk activities that take place outdoors. It proposes that this threshold be reviewed for indoor / low ventilation environments based on risk assessments.

A historic Bundesliga season is in the books. As Germany’s top-flight managed to restart the season after the coronavirus-induced break sooner than the Premier League and La Liga, it experienced how the new environment affects the game earlier than others.

… The Rays are the Antiques Roadshow of baseball. They find Picassos in attics, Tiffany lamps in basements and pitchers with outlier stuff in the dumpsters of other organizations.

In [Peter] Fairbanks they saw not just velocity but also near-perfect backspin on his four-seamer, which they and other smart clubs know is the proven antidote against the launch-angle hitting revolution. To get Fairbanks they traded Nick Solak, a promising hitter without great defensive value.

Since joining the Rays, Fairbanks has improved his stuff even more, thanks to the wizardry of pitching coach Kyle Snyder and process and analytics coach Jonathan Erlichman, a former math major and club hockey player at Princeton.

“Our guys do a tremendous job looking for the guys they acquire as far as special, special stuff,” Rays manager Kevin Cash says. “[Fairbanks] is right at the top of the list. You don’t see many guys with that high average (velocity) and the type of carry that he gets and have the ability to land a really, really quality breaking ball.