Related papers: Spatio-temporal Graph Learning on Adaptive Mined K…
Many real-world ubiquitous applications, such as parking recommendations and air pollution monitoring, benefit significantly from accurate long-term spatio-temporal forecasting (LSTF). LSTF makes use of long-term dependency between spatial…
The goal of multi-object tracking (MOT) is to detect and track all objects in a scene across frames, while maintaining a unique identity for each object. Most existing methods rely on the spatial-temporal motion features and appearance…
The Detection Transformer (DETR) has revolutionized the design of CNN-based object detection systems, showcasing impressive performance. However, its potential in the domain of multi-frame 3D object detection remains largely unexplored. In…
Recent improvements in positioning technology has led to a much wider availability of massive moving object data. A crucial task is to find the moving objects that travel together. Usually, these object sets are called spatio-temporal…
This project aims to develop a robust video surveillance system, which can segment videos into smaller clips based on the detection of activities. It uses CCTV footage, for example, to record only major events-like the appearance of a…
Event cameras have the potential to capture continuous motion information over time and space, making them well-suited for optical flow estimation. However, most existing learning-based methods for event-based optical flow adopt frame-based…
Multi-modal image fusion (MMIF) integrates valuable information from different modality images into a fused one. However, the fusion of multiple visible images with different focal regions and infrared images is a unprecedented challenge in…
The integration of Unmanned Aerial Vehicles(UAVs) into Intelligent Transportation Systems (ITS) offers synoptic visibility for traffic monitoring, yet scalable deployment is hindered by trajectory fragmentation, where vehicle identity…
Recent research in time series forecasting has explored integrating multimodal features into models to improve accuracy. However, the accuracy of such methods is constrained by three key challenges: inadequate extraction of fine-grained…
Accurate and robust LiDAR 3D object detection is essential for comprehensive scene understanding in autonomous driving. Despite its importance, LiDAR detection performance is limited by inherent constraints of point cloud data, particularly…
Learning the embeddings for urban regions from human mobility data can reveal the functionality of regions, and then enables the correlated but distinct tasks such as crime prediction. Human mobility data contains rich but abundant…
Multi-object tracking (MOT) is a crucial component of situational awareness in military defense applications. With the growing use of unmanned aerial systems (UASs), MOT methods for aerial surveillance is in high demand. Application of MOT…
Video action recognition, a critical problem in video understanding, has been gaining increasing attention. To identify actions induced by complex object-object interactions, we need to consider not only spatial relations among objects in a…
Vision sensors are becoming more important in Intelligent Transportation Systems (ITS) for traffic monitoring, management, and optimization as the number of network cameras continues to rise. However, manual object tracking and matching…
Current multispectral object detection methods often retain extraneous background or noise during feature fusion, limiting perceptual performance. To address this, we propose an innovative feature fusion framework based on cross-modal…
High-dynamic scene optical flow is a challenging task, which suffers spatial blur and temporal discontinuous motion due to large displacement in frame imaging, thus deteriorating the spatiotemporal feature of optical flow. Typically,…
The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named TransSTAM, which leverages Transformer to effectively model…
Convolutional neural networks (CNNs) have demonstrated strong performance in visual recognition tasks, but their inherent reliance on regular grid structures limits their capacity to model complex topological relationships and non-local…
The detection of moving infrared dim-small targets has been a challenging and prevalent research topic. The current state-of-the-art methods are mainly based on ConvLSTM to aggregate information from adjacent frames to facilitate the…
Multi-frame human pose estimation in complicated situations is challenging. Although state-of-the-art human joints detectors have demonstrated remarkable results for static images, their performances come short when we apply these models to…