To examine the agreement of a novel computer program measuring retinal vessel tortuosity with subjective assessment of tortuosity in school-aged children. Cross-sectional study of 387 retinal vessels (193 arterioles, 194 veins) from 28 eyes of 14 children (aged 10 years). Retinal digital images were analyzed using the Computer Assisted Image Analysis of the Retina (CAIAR) program, including 14 measures of tortuosity. Vessels were graded (from 0 = none; to 5 = tortuous) independently by two observers. Interobserver agreement was assessed by using kappa statistics. Agreement with all 14 objective measures was assessed with correlation/regression analyses. Intersession repeatability (comparing morning and afternoon sessions) of tortuosity indices was calculated. Interobserver agreement of vessel tortuosity within one grade was high (kappa = 0.97), with total agreement in 56% of grades and 42% differing by +/-1 grade. Tortuosity indices based on subdivided chord length methods showed strong log-linear associations with agreed subjective grades (typically r > 0.6; P < 0.001). An approach that averages the distance from the vessel to chord length along the length of the vessel showed best agreement (r = 0.8; P < 0.0001). Tortuosity measures based on curvature performed less well. Intersession repeatability of the vessel to chord technique was good, differing by values equivalent to <1 in subjective grade. Tortuosity indices based on changes in subdivided chord lengths showed optimal agreement with subjective assessment. The relation of these indices to ethnicity and cardiovascular risk factors in childhood should be examined further, as these indices may be a useful indicator of early vascular function.

Visual tracking has attracted a significant attention in the last few decades. The recent surge in the number of publications on tracking-related problems have made it almost impossible to follow the developments in the field. One of the reasons is that there is a lack of commonly accepted annotated data-sets and standardized evaluation protocols that would allow objective comparison of different tracking methods. To address this issue, the Visual Object Tracking (VOT) workshop was organized in conjunction with ICCV2013. Researchers from academia as well as industry were invited to participate in the first VOT2013 challenge which aimed at single-object visual trackers that do not apply pre-learned models of object appearance (model-free). Presented here is the VOT2013 benchmark dataset for evaluation of single-object visual trackers as well as the results obtained by the trackers competing in the challenge. In contrast to related attempts in tracker benchmarking, the dataset is labeled per-frame by visual attributes that indicate occlusion, illumination change, motion change, size change and camera motion, offering a more systematic comparison of the trackers. Furthermore, we have designed an automated system for performing and evaluating the experiments. We present the evaluation protocol of the VOT2013 challenge and the results of a comparison of 27 trackers on the benchmark dataset. The dataset, the evaluation tools and the tracker rankings are publicly available from the challenge website (http://votchallenge.net).

In this paper we present the design and evaluation of an end-to-end trainable, deep neural network with a visual attention mechanism for memorability estimation in still images. We analyze the suitability of transfer learning of deep models from image classification to the memorability task. Further on we study the impact of the attention mechanism on the memorability estimation and evaluate our network on the SUN Memorability and the LaMem datasets. Our network outperforms the existing state of the art models on both datasets in terms of the Spearman's rank correlation as well as the mean squared error, closely matching human consistency.