Wangpeng An

TL;DR: In this paper, the authors proposed the use of a high precision, high recall and widely applicable Faster R-CNN method to detect construction workers' non-hardhat-use (NHU) detection.

TL;DR: In this paper, the authors investigated the use of nonnegative representation (NR) for pattern classification, which is largely ignored by previous work, and showed that NR can boost the representation power of homogeneous samples while limiting the represent power of heterogeneous samples, making the representation sparse and discriminative simultaneously and thus providing a more effective solution to representation based classification than SR/CR.

TL;DR: In this paper, the authors proposed a novel framework to check whether a site worker is working within the constraints of their certification, which comprises key video clips extraction, trade recognition and worker competency evaluation.

TL;DR: The proposed PID method reduces much the overshoot phenomena of SGD-Momentum, and it achieves up to 50% acceleration on popular deep network architectures with competitive accuracy, as verified by the experiments on the benchmark datasets including CIFar10, CIFAR100, and Tiny-ImageNet.

TL;DR: This paper proposes a simple yet effective exponential decay sine wave like learning rate technique for SGD to improve its convergence speed, accelerating neural network training tremendously.