Related papers: Heterogeneous Relational Complement for Vehicle Re…
This work addresses the problem of vehicle identification through non-overlapping cameras. As our main contribution, we introduce a novel dataset for vehicle identification, called Vehicle-Rear, that contains more than three hours of…
Encoding a driving scene into vector representations has been an essential task for autonomous driving that can benefit downstream tasks e.g. trajectory prediction. The driving scene often involves heterogeneous elements such as the…
Person re-identification aims at the maintenance of a global identity as a person moves among non-overlapping surveillance cameras. It is a hard task due to different illumination conditions, viewpoints and the small number of annotated…
Vehicle Re-Identification (V-ReID) is a critical task that associates the same vehicle across images from different camera viewpoints. Many works explore attribute clues to enhance V-ReID; however, there is usually a lack of effective…
Existing vehicle re-identification methods commonly use spatial pooling operations to aggregate feature maps extracted via off-the-shelf backbone networks. They ignore exploring the spatial significance of feature maps, eventually degrading…
In recent years, vehicle re-identification (Re-ID) has gained increasing importance in various applications such as assisted driving systems, traffic flow management, and vehicle tracking, due to the growth of intelligent transportation…
Transportation systems often rely on understanding the flow of vehicles or pedestrian. From traffic monitoring at the city scale, to commuters in train terminals, recent progress in sensing technology make it possible to use cameras to…
Vehicle re-identification (re-id) is a fundamental problem for modern surveillance camera networks. Existing approaches for vehicle re-id utilize global features and local features for re-id by combining multiple subnetworks and losses. In…
Graph neural networks for heterogeneous graph embedding is to project nodes into a low-dimensional space by exploring the heterogeneity and semantics of the heterogeneous graph. However, on the one hand, most of existing heterogeneous graph…
Cross-modality person re-identification is a challenging problem which retrieves a given pedestrian image in RGB modality among all the gallery images in infrared modality. The task can address the limitation of RGB-based person Re-ID in…
Robust and accurate planar tracking over a whole video sequence is vitally important for many vision applications. The key to planar object tracking is to find object correspondences, modeled by homography, between the reference image and…
Existing vehicle re-identification (re-id) evaluation benchmarks consider strongly artificial test scenarios by assuming the availability of high quality images and fine-grained appearance at an almost constant image scale, reminiscent to…
With the development of smart cities, urban surveillance video analysis will play a further significant role in intelligent transportation systems. Identifying the same target vehicle in large datasets from non-overlapping cameras should be…
Point cloud completion is essential for robotic perception, object reconstruction and supporting downstream tasks like grasp planning, obstacle avoidance, and manipulation. However, incomplete geometry caused by self-occlusion and sensor…
Image retrieval-based cross-view geo-localization (IRCVGL) aims to match images captured from significantly different viewpoints, such as satellite and street-level images. Existing methods predominantly rely on learning robust global…
Sharing collective perception messages (CPM) between vehicles is investigated to decrease occlusions so as to improve the perception accuracy and safety of autonomous driving. However, highly accurate data sharing and low communication…
This paper addresses the problem of matching pedestrians across multiple camera views, known as person re-identification. Variations in lighting conditions, environment and pose changes across camera views make re-identification a…
Visible-Infrared person re-identification (VI-ReID) is an important and challenging task in intelligent video surveillance. Existing methods mainly focus on learning a shared feature space to reduce the modality discrepancy between visible…
The construction of spatiotemporal networks using graph convolution networks (GCNs) has become one of the most popular methods for predicting traffic signals. However, when using a GCN for traffic speed prediction, the conventional approach…
Existing person re-identification (re-id) methods either assume the availability of well-aligned person bounding box images as model input or rely on constrained attention selection mechanisms to calibrate misaligned images. They are…