Abstract: The performances of Sign Language Recognition (SLR) systems have improved considerably in recent years. However, several open challenges still need to be solved to allow SLR to be useful in practice. The research in the field is in its infancy in regards to the robustness of the models to a large diversity of signs and signers, and to fairness of the models to performers from different demographics. This work summarises the ChaLearn LAP Large Scale Signer Independent Isolated SLR Challenge, organised at CVPR 2021 with the goal of overcoming some of the aforementioned challenges. We analyse and discuss the challenge design, top winning solutions and suggestions for future research. The challenge attracted 132 participants in the RGB track and 59 in the RGB+Depth track, receiving more than 1.5K submissions in total. Participants were evaluated using a new large-scale multi-modal Turkish Sign Language (AUTSL) dataset, consisting of 226 sign labels and 36,302 isolated sign video samples performed by 43 different signers. Winning teams achieved more than 96% recognition rate, and their approaches benefited from pose/hand/face estimation, transfer learning, external data, fusion/ensemble of modalities and different strategies to model spatio-temporal information. However, methods still fail to distinguish among very similar signs, in particular those sharing similar hand trajectories.

Abstract: The present study examines the use of Kahoot! as a gamification tool to explore mixed learning strategies. We analyze its use in two different groups of a theoretical subject of the third course of the Degree in Chemistry. An empirical-analytical methodology was used using Kahoot! in two different groups of students, with different frequencies. The academic results of these two group of students were compared between them and with those obtained in the previous course, in which Kahoot! was not employed, with the aim of measuring the evolution in the students´ knowledge. The results showed, in all cases, that the use of Kahoot! has led to a significant increase in the overall marks, and in the number of students who passed the subject. Moreover, some differences were also observed in students´ academic performance according to the group. Finally, it can be concluded that the use of a gamification tool (Kahoot!) in a university classroom had generally improved students´ learning and marks, and that this improvement is more prevalent in those students who have achieved a better Kahoot! performance.

Abstract: The problem of dealing with missing or incomplete data in machine learning and computer vision arises in many applications. Recent strategies make use of generative models to impute missing or corrupted data. Advances in computer vision using deep generative models have found applications in image/video processing, such as denoising, restoration, super-resolution, or inpainting.
Inpainting and Denoising Challenges comprises recent efforts dealing with image and video inpainting tasks. This includes winning solutions to the ChaLearn Looking at People inpainting and denoising challenges: human pose recovery, video de-captioning and fingerprint restoration.
This volume starts with a wide review on image denoising, retracing and comparing various methods from the pioneer signal processing methods, to machine learning approaches with sparse and low-rank models, and recent deep learning architectures with autoencoders and variants. The following chapters present results from the Challenge, including three competition tasks at WCCI and ECML 2018. The top best approaches submitted by participants are described, showing interesting contributions and innovating methods. The last two chapters propose novel contributions and highlight new applications that benefit from image/video inpainting.

Abstract: The problem of removing illuminant variations to preserve the colours of objects (colour constancy) has already been solved by the human brain using mechanisms that rely largely on centre-surround computations of local contrast. In this paper we adopt some of these biological solutions described by long known physiological findings into a simple, fully automatic, functional model (termed Adaptive Surround Modulation or ASM). In ASM, the size of a visual neuron's receptive field (RF) as well as the relationship with its surround varies according to the local contrast within the stimulus, which in turn determines the nature of the centre-surround normalisation of cortical neurons higher up in the processing chain. We modelled colour constancy by means of two overlapping asymmetric Gaussian kernels whose sizes are adapted based on the contrast of the surround pixels, resembling the change of RF size. We simulated the contrast-dependent surround modulation by weighting the contribution of each Gaussian according to the centre-surround contrast. In the end, we obtained an estimation of the illuminant from the set of the most activated RFs' outputs. Our results on three single-illuminant and one multi-illuminant benchmark datasets show that ASM is highly competitive against the state-of-the-art and it even outperforms learning-based algorithms in one case. Moreover, the robustness of our model is more tangible if we consider that our results were obtained using the same parameters for all datasets, that is, mimicking how the human visual system operates. These results might provide an insight on how dynamical adaptation mechanisms contribute to make object's colours appear constant to us.

Abstract: The problem of training classifiers only with target data arises in many applications where non-target data are too costly, difficult to obtain, or not available at all. Several one-class classification methods have been presented to solve this problem, but most of the methods are highly sensitive to the presence of outliers in the target class. Ensemble methods have therefore been proposed as a powerful way to improve the classification performance of binary/multi-class learning algorithms by introducing diversity into classifiers.
However, their application to one-class classification has been rather limited. In
this paper, we present a new ensemble method based on a non-parametric weighted bagging strategy for one-class classification, to improve accuracy in the presence of outliers. While the standard bagging strategy assumes a uniform data distribution, the method we propose here estimates a probability density based on a forest structure of the data. This assumption allows the estimation of data distribution from the computation of simple univariate and bivariate kernel densities. Experiments using original and noisy versions of 20 different datasets show that bagging ensemble methods applied to different one-class classifiers outperform base one-class classification methods. Moreover, we show that, in noisy versions of the datasets, the non-parametric weighted bagging strategy we propose outperforms the classical bagging strategy in a statistically significant way.

Abstract: The proportions of L, M and S photoreceptors in the primate retina are arguably determined by evolutionary pressure and the statistics of the visual environment. Two information theory-based approaches have been recently proposed for explaining the asymmetrical spatial densities of photoreceptors in humans. In the first approach Garrigan et al (2010 PLoS ONE 6 e1000677), a model for computing the information transmitted by cone arrays which considers the differential blurring produced by the long-wavelength accommodation of the eye’s lens is proposed. Their results explain the sparsity of S-cones but the optimum depends weakly on the L:M cone ratio. In the second approach (Penacchio et al, 2010 Perception 39 ECVP Supplement, 101), we show that human cone arrays make the visual representation scale-invariant, allowing the total entropy of the signal to be preserved while decreasing individual neurons’ entropy in further retinotopic representations. This criterion provides a thorough description of the distribution of L:M cone ratios and does not depend on differential blurring of the signal by the lens. Here, we investigate the similarities and differences of both approaches when applied to the same database. Our results support a 2-criteria optimization in the space of cone ratios whose components are arguably important and mostly unrelated.
[This work was partially funded by projects TIN2010-21771-C02-1 and Consolider-Ingenio 2010-CSD2007-00018 from the Spanish MICINN. CAP was funded by grant RYC-2007-00484]

Abstract: The Quantitative Coronary Angiography (QCA) is a methodology used to evaluate the arterial diseases and, in particular, the degree of stenosis. In this paper we propose AQCA, a fully automatic method for vessel segmentation based on graph cut theory. Vesselness, geodesic paths and a new multi-scale edgeness map are used to compute a globally optimal artery segmentation. We evaluate the method performance in a rigorous numerical way on two datasets. The method can detect an artery with precision 92.9 +/- 5% and sensitivity 94.2 +/- 6%. The average absolute distance error between detected and ground truth centerline is 1.13 +/- 0.11 pixels (about 0.27 +/- 0.025 mm) and the absolute relative error in the vessel caliber estimation is 2.93% with almost no bias. Moreover, the method can discriminate between arteries and catheter with an accuracy of 96.4%.

Abstract: The recognition of abnormal behaviors in video sequences has raised as a hot topic in video understanding research. Particularly, an important challenge resides on automatically detecting abnormality. However, there is no convention about the types of anomalies that training data should derive. In surveillance, these are typically detected when new observations differ substantially from observed, previously learned behavior models, which represent normality. This paper focuses on properly defining anomalies within trajectory analysis: we propose a hierarchical representation conformed by Soft, Intermediate, and Hard Anomaly, which are identified from the extent and nature of deviation from learned models. Towards this end, a novel Gaussian Mixture Model representation of learned route patterns creates a probabilistic map of the image plane, which is applied to detect and classify anomalies in real-time. Our method overcomes limitations of similar existing approaches, and performs correctly even when the tracking is affected by different sources of noise. The reliability of our approach is demonstrated experimentally.