The use of computer vision techniques to detect objects in images has grown in recent years. These techniques are especially useful to automatically extract and analyze …
Abstract The eighth AI City Challenge highlighted the convergence of computer vision and artificial intelligence in areas like retail warehouse settings and Intelligent Traffic Systems …
Although a significant progress has been witnessed in supervised person re-identification (re-id), it remains challenging to generalize re-id models to new domains due to the huge …
Abstract The AI City Challenge's seventh edition emphasizes two domains at the intersection of computer vision and artificial intelligence-retail business and Intelligent Traffic Systems …
X Ye, M Shu, H Li, Y Shi, Y Li… - Proceedings of the …, 2022 - openaccess.thecvf.com
Concurrent perception datasets for autonomous driving are mainly limited to frontal view with sensors mounted on the vehicle. None of them is designed for the overlooked roadside …
T Isobe, D Li, L Tian, W Chen… - Proceedings of the …, 2021 - openaccess.thecvf.com
In this work, we address the problem of unsupervised domain adaptation for person re-ID where annotations are available for the source domain but not for target. Previous methods …
This paper uses a graphic engine to simulate a large amount of training data with free annotations. Between synthetic and real data, there is a two-level domain gap, ie, content …
A Aboah - Proceedings of the IEEE/CVF Conference on …, 2021 - openaccess.thecvf.com
Any intelligent traffic monitoring system must be able to detect anomalies such as traffic accidents in real-time. In this paper, we propose a Decision-Tree enabled approach …
L Yuan, Y Ma, L Su, Z Wang - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Naturalistic driving action recognition (NDAR) has proven to be an effective method for detecting driver distraction and reducing the risk of traffic accidents. However, the intrusive …