Multiple object video object segmentation is a challenging task, specially for the zero-shot case, when no object mask is given at the initial frame and the model has to find the objects to be segmented along the sequence. In our work, we propose a Recurrent network for multiple object Video Object Segmentation (RVOS) that is fully end-to-end trainable. Our model incorporates recurrence on two different domains: (i) the spatial, which allows to discover the different object instances within a frame, and (ii) the temporal, which allows to keep the coherence of the segmented objects along time. We train RVOS for zero-shot video object segmentation and are the first ones to report quantitative results for DAVIS-2017 and YouTube-VOS benchmarks. Further, we adapt RVOS for one-shot video object segmentation by using the masks obtained in previous time steps as inputs to be processed by the recurrent module. Our model reaches comparable results to state-of-the-art techniques in YouTube-VOS benchmark and outperforms all previous video object segmentation methods not using online learning in the DAVIS-2017 benchmark. Moreover, our model achieves faster inference runtimes than previous methods, reaching 44ms/frame on a P100 GPU.
We determined the prevalence of eating disorder (ED) symptoms among elite Spanish athletes from a broad range of sports and levels of competition and examined the associations between the presence of symptoms and perceived sport-specific weight pressures. We surveyed 646 elite athletes (16.7 ± 4.4 years; 51.08% females) representing 33 sports from top-division teams and two elite athlete training centers in Catalonia. Based on the results of the Eating Attitudes Test-26 responses, 5.1% of athletes (7.6% of females and 2.5% of males) were at risk of EDs. The highest rates of ED symptoms were observed in male endurance athletes and female esthetic athletes. Competition level was not a risk factor. The only gender differences in the presence of ED symptoms by competing level were observed in athletes competing at the national level. Female athletes with ED symptoms scored higher on the two subscales of the Spanish version of the Weight Pressures in Sport (WPS) tool: coach and sport-specific pressures and pressures from teammates and due to uniform. Male athletes with ED symptoms scored higher on the pressures due to uniform subscale. Finally, symptomatic female but not male athletes competing at international and national levels also perceived greater sport-specific weight pressures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.