No abstract

In real-world face recognition applications, there is a tremendous amount of data with two images for each person. One is an ID photo for face enrollment, and the other is a probe photo captured on spot. Most existing methods are designed for training data with limited breadth (a relatively small number of classes) and sufficient depth (many samples for each class). They would meet great challenges on ID versus Spot (IvS) data, including the under-represented intraclass variations and an excessive demand on computing devices. In this paper, we propose a deep learning based large-scale bisample learning (LBL) method for IvS face recognition. To tackle the bisample problem with only two samples for each class, a classification-verificationclassification (CVC) training strategy is proposed to progressively enhance the IvS performance. Besides, a dominant prototype softmax (DP-softmax) is incorporated to make the deep learning scalable on large-scale classes. We conduct LBL on a IvS face dataset with more than two million identities. Experimental results show the proposed method achieves superior performance to Fig. 1: The ID versus Spot (IvS) data, each identity has one ID photo and one spot photo. previous ones, validating the effectiveness of LBL on IvS face recognition.

BackgroundCourt shoe designs predominantly focus on reducing excessive vertical ground reaction force, but shear force cushioning has received little attention in the basketball population. We aimed to examine the effect of a novel shoe-cushioning design on both resultant horizontal ground reaction forces and comfort perception during two basketball-specific cutting movements.MethodsFifteen university team basketball players performed lateral shuffling and 45-degree sidestep cutting at maximum effort in basketball shoes with and without the shear-cushioning system (SCS). Paired t-tests were used to examine the differences in kinetics and comfort perception between two shoes.ResultsSCS shoe allowed for larger rotational material deformation compared with control shoes, but no significant shoe differences were found in braking phase kinetics during both cutting movements (P = 0.35). Interestingly, a greater horizontal propulsion impulse was found with the SCS during 45-degree cutting (P < 0.05), when compared with the control. In addition, players wearing SCS shoes perceived better forefoot comfort (P = 0.012). During lateral shuffling, there were no significant differences in horizontal GRF and comfort perception between shoe conditions (P > 0.05).DiscussionThe application of a rotational shear-cushioning structure allowed for better forefoot comfort and enhanced propulsion performance in cutting, but did not influence the shear impact. Understanding horizontal ground reaction force information may be useful in designing footwear to prevent shear-related injuries in sport populations.

No abstract

Existing methods of 3D dense face alignment mainly concentrate on accuracy, thus limiting the scope of their practical applications. In this paper, we propose a novel regression framework which makes a balance among speed, accuracy and stability. Firstly, on the basis of a lightweight backbone, we propose a meta-joint optimization strategy to dynamically regress a small set of 3DMM parameters, which greatly enhances speed and accuracy simultaneously. To further improve the stability on videos, we present a virtual synthesis method to transform one still image to a short-video which incorporates in-plane and out-of-plane face moving. On the premise of high accuracy and stability, our model runs at over 50fps on a single CPU core and outperforms other state-ofthe-art heavy models simultaneously. Experiments on several challenging datasets validate the efficiency of our method. Pre-trained models and code are available at https://github.com/cleardusk/3DDFA_V2.