Road traffic accidents caused by fatigue driving are common causes of human casualties. In this paper, we present a driver fatigue detection algorithm using two-stream network models with multi-facial features. The algorithm consists of four parts: (1) Positioning mouth and eye with multi-task cascaded convolutional neural networks (MTCNNs). (2) Extracting the static features from a partial facial image. (3) Extracting the dynamic features from a partial facial optical flow. (4) Combining both static and dynamic features using a two-stream neural network to make the classification. The main contribution of this paper is the combination of a two-stream network and multi-facial features for driver fatigue detection. Two-stream networks can combine static and dynamic image information, while partial facial images as network inputs can focus on fatigue-related information, which brings better performance. Moreover, we applied gamma correction to enhance image contrast, which can help our method achieve better results, noted by an increased accuracy of 2% in night environments. Finally, an accuracy of 97.06% was achieved on the National Tsing Hua University Driver Drowsiness Detection (NTHU-DDD) dataset.

Foreground segmentation is a fundamental problem in computer vision, which includes salient object detection, forgery detection, defocus blur detection, shadow detection, and camouflage object detection. Previous works have typically relied on domain-specific solutions to address accuracy and robustness issues in those applications. In this paper, we present a unified framework for a number of foreground segmentation tasks without any task-specific designs. We take inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and propose a new visual prompting model, named Explicit Visual Prompting (EVP). Different from the previous visual prompting which is typically a dataset-level implicit embedding, our key insight is to enforce the tunable parameters focusing on the explicit visual content from each individual image, i.e., the features from frozen patch embeddings and high-frequency components. Our method freezes a pre-trained model and then learns task-specific knowledge using a few extra parameters. Despite introducing only a small number of tunable parameters, EVP achieves superior performance than full fine-tuning and other parameter-efficient fine-tuning methods. Experiments in fourteen datasets across five tasks show the proposed method outperforms other task-specific methods while being considerably simple. The proposed method demonstrates the scalability in different architectures, pre-trained weights, and tasks.

Peripheral nerve injury is a serious health problem and repairing long nerve deficits remains a clinical challenge nowadays. Nerve guidance conduit (NGC) serves as the most promising alternative therapy strategy to autografts but its repairing efficiency needs improvement. In this study, we investigated whether modulating the immune microenvironment by Interleukin-17F (IL-17F) could promote NGC mediated peripheral nerve repair. Chitosan conduits were used to bridge sciatic nerve defect in IL-17F knockout mice and wild-type mice with autografts as controls. Our data revealed that IL-17F knockout mice had improved functional recovery and axonal regeneration of sciatic nerve bridged by chitosan conduits comparing to the wild-type mice. Notably, IL-17F knockout mice had enhanced anti-inflammatory macrophages in the NGC repairing microenvironment. In vitro data revealed that IL-17F knockout peritoneal and bone marrow derived macrophages had increased anti-inflammatory markers after treatment with the extracts from chitosan conduits, while higher pro-inflammatory markers were detected in the Raw264.7 macrophage cell line, wild-type peritoneal and bone marrow derived macrophages after the same treatment. The biased anti-inflammatory phenotype of macrophages by IL-17F knockout probably contributed to the improved chitosan conduit guided sciatic nerve regeneration. Additionally, IL-17F could enhance pro-inflammatory factors production in Raw264.7 cells and wild-type peritoneal macrophages. Altogether, IL-17F may partially mediate chitosan conduit induced pro-inflammatory polarization of macrophages during nerve repair. These results not only revealed a role of IL-17F in macrophage function, but also provided a unique and promising target, IL-17F, to modulate the microenvironment and enhance the peripheral nerve regeneration.