A Ali, G Gaikov, D Rybalchenko… - Proceedings of the …, 2024 - openaccess.thecvf.com
Image and video analysis requires not only accurate object but also the understanding of relationships among detected objects. Common solutions to relation modeling typically …
In recent research significant attention has been devoted to the open-vocabulary object detection task aiming to generalize beyond the limited number of classes labeled during …
Z Chen, J Yang, Z Feng, H Zhu - Scientific Data, 2024 - nature.com
Artificial intelligence models play a crucial role in monitoring and maintaining railroad infrastructure by analyzing image data of foreign objects on power transmission lines …
T Yao, Y Li, Y Pan, T Mei - IEEE Transactions on Pattern …, 2024 - ieeexplore.ieee.org
The hybrid deep models of Vision Transformer (ViT) and Convolution Neural Network (CNN) have emerged as a powerful class of backbones for vision tasks. Scaling up the input …
L Liang, H Ma, L Zhao, X Xie, C Hua, M Zhang… - Sensors, 2024 - mdpi.com
Autonomous driving, as a pivotal technology in modern transportation, is progressively transforming the modalities of human mobility. In this domain, vehicle detection is a …
Video instance segmentation on mobile devices is an important yet very challenging edge AI problem. It mainly suffers from (1) heavy computation and memory costs for frame-by-frame …
J Hu, Y Lu, S Zhang, L Cao - IEEE Transactions on Image …, 2024 - ieeexplore.ieee.org
Transformer-based instance-level recognition has attracted increasing research attention recently due to the superior performance. However, although attempts have been made to …
C Dong, Y Tang, L Zhang - Multimedia Tools and Applications, 2024 - Springer
Compared to the remarkable progress within the discipline of object detection in recent years, real-time detection of non-salient objects remains a challenging research task …
Q Song, Y Guan, X Guo, X Guo, Y Chen, H Wang… - Ecological …, 2024 - Elsevier
Camera traps are widely used for wildlife monitoring and making informed conservation and land-management decisions, but the resulting 'big data'are laborious to process. Deep …