Analysis of pedestrians’ motion is important to real-world applications in public scenes. Due to the complex temporal and spatial factors, trajectory prediction is a challenging task. With the development of attention mechanism recently, transformer network has been successfully applied in natural language processing, computer vision, and audio processing. We propose an end-to-end transformer network embedded with random deviation queries for pedestrian trajectory forecasting. The self-correcting scheme can enhance the robustness of the network. Moreover, we present a co-training strategy to improve the training effect. The whole scheme is trained collaboratively by the original loss and classification loss. Therefore, we also achieve more accurate prediction results. Experimental results on several datasets indicate the validity and robustness of the network. We achieve the best performance in individual forecasting and comparable results in social forecasting. Encouragingly, our approach achieves a new state of the art on the Hotel and Zara2 datasets compared with the social-based and individual-based approaches.

The outbreak of coronavirus disease 2019 (COVID-19) is spreading rapidly around the world, resulting in a global pandemic. Imaging techniques such as computed tomography (CT) play an essential role in the diagnosis and treatment of the disease since lung infection or pneumonia is a common complication. However, training a deep network to learn how to diagnose COVID-19 rapidly and accurately in CT images and segment the infected regions like a radiologist is challenging. Since the infectious area is difficult to distinguish manually annotation, the segmentation results are time-consuming. To tackle these problems, we propose an efficient method based on a deep adversarial network to segment the infection regions automatically. Then, the predicted segment results can assist the diagnostic network in identifying the COVID-19 samples from the CT images. On the other hand, a radiologist-like segmentation network provides detailed information of the infectious regions by separating areas of ground-glass, consolidation, and pleural effusion, respectively. Our method can accurately predict the COVID-19 infectious probability and provide lesion regions in CT images with limited training data. Additionally, we have established a public dataset for multitask learning. Extensive experiments on diagnosis and segmentation show superior performance over state-of-the-art methods.

Realistic image composition aims to composite new images by fusing a source object into a target image. It is a challenging problem due to the complex multi-task framework, including sensible object placement, appearance consistency, shadow generation, etc. Most existing researchers attempt to address one of the issues. Especially before compositing, there is no matching assignment between the source object and target image, which often leads to unreasonable results. To address the issues above, we consider image composition as an image generation problem and propose a deep adversarial learning network via spatial position analysis. We target the analysis network segment and classify the objects in target images. A spatial alignment network matches the segmented objects with the source objects, and predicts a sensible placement position, and an adversarial network generates a realistic composite image with the shadow and reflection of the source object. Furthermore, we use the classification information of target objects to filter out unreasonable image compositing. Moreover, we introduce a new test set to evaluate the network generalization for our multi-task image composition dataset. Extensive experimental results of the SHU (Shanghai University) dataset demonstrate that our deep spatial position analysis network remarkably enhances the compositing performance in realistic, shadow, and reflection generations.

Computer vision techniques have been used to produce accurate and generic crowd count estimators in recent years. Due to severe occlusions, appearance variations, perspective distortions and illumination conditions, crowd counting is a very challenging task. To this end, we propose a deep spatial regression model(DSRM) for counting the number of individuals present in a still image with arbitrary perspective and arbitrary resolution. Our proposed model is based on Convolutional Neural Network (CNN) and long short term memory (LSTM). First, we put the images into a pretrained CNN to extract a set of high-level features. Then the features in adjacent regions are used to regress the local counts with a LSTM structure which takes the spatial information into consideration. The final global count is obtained by a sum of the local patches. We apply our framework on several challenging crowd counting datasets, and the experiment results illustrate that our method on the crowd counting and density estimation problem outperforms state-of-the-art methods in terms of reliability and effectiveness.