Related papers: A Two-Stream Siamese Neural Network for Vehicle Re…
Visual tracking is one of the most challenging computer vision problems. In order to achieve high performance visual tracking in various negative scenarios, a novel cascaded Siamese network is proposed and developed based on two different…
The inability of state-of-the-art semantic segmentation methods to detect anomaly instances hinders them from being deployed in safety-critical and complex applications, such as autonomous driving. Recent approaches have focused on either…
Thermal infrared (TIR) images typically lack detailed features and have low contrast, making it challenging for conventional feature extraction models to capture discriminative target characteristics. As a result, trackers are often…
This paper presents Dense Siamese Network (DenseSiam), a simple unsupervised learning framework for dense prediction tasks. It learns visual representations by maximizing the similarity between two views of one image with two types of…
In recent years, building change detection methods have made great progress by introducing deep learning, but they still suffer from the problem of the extracted features not being discriminative enough, resulting in incomplete regions and…
Re-identification (ReID) is to identify the same instance across different cameras. Existing ReID methods mostly utilize alignment-based or attention-based strategies to generate effective feature representations. However, most of these…
Due to the recent increase in the number of connected devices, the need to promptly detect security issues is emerging. Moreover, the high number of communication flows creates the necessity of processing huge amounts of data. Furthermore,…
One fundamental challenge of vehicle re-identification (re-id) is to learn robust and discriminative visual representation, given the significant intra-class vehicle variations across different camera views. As the existing vehicle datasets…
Surround-view cameras are a primary sensor for automated driving, used for near-field perception. It is one of the most commonly used sensors in commercial vehicles primarily used for parking visualization and automated parking. Four…
We propose a novel network that learns a part-aligned representation for person re-identification. It handles the body part misalignment problem, that is, body parts are misaligned across human detections due to pose/viewpoint change and…
Automatically detecting violence from surveillance footage is a subset of activity recognition that deserves special attention because of its wide applicability in unmanned security monitoring systems, internet video filtration, etc. In…
Resampling detection plays an important role in identifying image tampering, such as image splicing. Currently, the resampling detection is still difficult in recompressed images, which are yielded by applying resampling followed by…
Remote sensing image change detection aims to identify the differences between images acquired at different times in the same area. It is widely used in land management, environmental monitoring, disaster assessment and other fields.…
Recently spiking neural networks (SNNs), the third-generation of neural networks has shown remarkable capabilities of energy-efficient computing, which is a promising alternative for deep neural networks (DNNs) with high energy consumption.…
Acquiring the road surface conditions in advance based on visual technologies provides effective information for the planning and control system of autonomous vehicles, thus improving the safety and driving comfort of the vehicles.…
Automotive telemetry data exhibits slow drifts and fast spikes, often within the same sequence, making reliable anomaly detection challenging. Standard reconstruction-based methods, including sequence variational autoencoders (VAEs), use a…
Vehicle theft is arguably one of the fastest-growing types of crime in India. In some of the urban areas, vehicle theft cases are believed to be around 100 each day. Identification of stolen vehicles in such precarious scenarios is not…
Over the past years, images generated by artificial intelligence have become more prevalent and more realistic. Their advent raises ethical questions relating to misinformation, artistic expression, and identity theft, among others. The…
Least-squares reverse time migration (LSRTM) is an inversion-based imaging method rooted in optimization theory, which iteratively updates the reflectivity model to minimize the difference between observed and simulated data. However, in…
Deep neural networks have been investigated in learning latent representations of medical images, yet most of the studies limit their approach in a single supervised convolutional neural network (CNN), which usually rely heavily on a large…