Multi-PeopleTracking in an open-world setting requires a special effort in precise detection. Moreover, temporal continuity in the detection phase gains more importance when scene cluttering introduces the challenging problems of occluded targets. For the purpose, we propose a deep network architecture that jointly extracts people body parts and associates them across short temporal spans. Our model explicitly deals with occluded body parts, by hallucinating plausible solutions of not visible joints. We propose a new end-to-end architecture composed by four branches (visible heatmaps, occluded heatmaps, part affinity fields and temporal affinity fields) fed by a time linker feature extractor. To overcome the lack of surveillance data with tracking, body part and occlusion annotations we created the vastest Computer Graphics dataset for people tracking in urban scenarios by exploiting a photorealistic videogame. It is up to now the vastest dataset (about 500.000 frames, almost 10 million body poses) of human body parts for people tracking in urban scenarios. Our architecture trained on virtual data exhibits good generalization capabilities also on public real tracking benchmarks, when image resolution and sharpness are high enough, producing reliable tracklets useful for further batch data association or re-id modules.

Low health literacy is associated with increased risks of hospitalization and death in patients with HF. The clinical evaluation of health literacy could help design interventions individualized for patients with low health literacy.

BackgroundPerceived social isolation has been shown to have a negative impact on health outcomes, particularly among older adults. However, these relationships have not been fully examined among patients with heart failure.Methods and ResultsResidents from 11 southeast Minnesota counties with a first‐ever International Classification of Diseases, Ninth Revision (ICD‐9) code 428 for heart failure between January 1, 2013, and March 31, 2015 (N=3867), were prospectively surveyed to measure perceived social isolation. A total of 2003 patients returned the survey (response rate, 52%); 1681 patients completed all questions and were retained for analysis. Among these patients (53% men; mean age, 73 years), ≈19% (n=312) had moderate perceived social isolation and 6% (n=108) had high perceived social isolation. After adjustment, patients reporting moderate perceived social isolation did not have an increased risk of death, hospitalizations, or emergency department visits compared with patients reporting low perceived social isolation; however, patients reporting high perceived social isolation had >3.5 times increased risk of death (hazard ratio, 3.74; 95% confidence interval [CI], 1.82–7.70), 68% increased risk of hospitalization (hazard ratio, 1.68; 95% CI, 1.18–2.39), and 57% increased risk of emergency department visits (hazard ratio, 1.57; 95% CI, 1.09–2.27). Compared with patients who self‐reported low perceived social isolation, patients reporting moderate perceived social isolation had a 16% increased risk of outpatient visits (rate ratio, 1.16; 95% CI, 1.03–1.31), whereas those reporting high perceived social isolation had a 26% increased risk (rate ratio, 1.26; 95% CI, 1.04–1.53).ConclusionsIn patients with heart failure, greater perceived social isolation is associated with an increased risk of death and healthcare use. Assessing perceived social isolation during the clinical encounter with a brief screening tool may help identify patients with heart failure at greater risk of poor outcomes.

No abstract