WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects under Occlusion

K Vuong, ND Reddy, R Tamburo… - Proceedings of the …, 2024 - openaccess.thecvf.com
Current methods for 2D and 3D object understanding struggle with severe occlusions in
busy urban environments partly due to the lack of large-scale labeled ground-truth …

Listen as you wish: Fusion of audio and text for cross-modal event detection in smart cities

H Tang, Y Hu, Y Wang, S Zhang, M Xu, J Zhu… - Information Fusion, 2024 - Elsevier
In the era of smart cities, the advent of the Internet of Things technology has catalyzed the
proliferation of multimodal sensor data, presenting new challenges in cross-modal event …

Recycling of generic ImageNet-trained models for smart-city applications

K Filus, J Domańska - … on Data Science and Advanced Analytics …, 2023 - ieeexplore.ieee.org
Convolutional Neural Networks (CNNs) enabled breakthroughs in computer vision. They are
also used in different domains of smart cities to process and analyze large amounts of image …

[引用][C] 深度学习图像描述方法分析与展望

赵永强, 金芝, 张峰, 赵海燕, 陶政为, 豆乘风, 徐新海… - 中国图象图形学报, 2023