Many deep learning approaches make extensive use of backbone networks pretrained on
large datasets like ImageNet, which are then fine-tuned. In remote sensing, the lack of …

Cameras in modern devices such as smartphones, satellites and medical equipment are
capable of capturing very high resolution images and videos. Such high-resolution data …

This paper strives for repetitive activity counting in videos. Different from existing works,
which all analyze the visual video content only, we incorporate for the first time the …

Crowd estimation is a very challenging problem. The most recent study tries to exploit
auditory information to aid the visual models, however, the performance is limited due to the …

The notion of self and cross-attention learning has been found to substantially boost the
performance of remote sensing (RS) image fusion. However, while the self-attention models …

Deploying deep learning models in time-critical applications with limited computational
resources, for instance in edge computing systems and IoT networks, is a challenging task …

Abstract Machine learning advances in the last decade have relied significantly on large-
scale datasets that continue to grow in size. Increasingly, those datasets also contain …

Automatically estimating the number of people in unconstrained scenes is a crucial yet
challenging task in different real-world applications, including video surveillance, public …

Deep neural networks can be converted to multi-exit architectures by inserting early exit
branches after some of their intermediate layers. This allows their inference process to …

Crowd counting is recently becoming a hot research topic, which aims to count the number
of the people in different crowded scenes. Existing methods are mainly based on training …