It is widely recognized that deep learning models lack robustness to adversarial examples.
An intriguing property of adversarial examples is that they can transfer across different …

Fruit detection is crucial for yield estimation and fruit picking system performance. Many state-
of-the-art methods for fruit detection use convolutional neural networks (CNNs). This paper …

We present a new challenging dataset, CPPE-5 (Medical Personal Protective Equipment),
with the goal to allow the study of subordinate categorization of medical personal protective …

Urban environments are undergoing significant transformations, with pedestrian areas
emerging as complex hubs of diverse mobility modes. This shift demands a more nuanced …

The task of landslide recognition focuses on extracting the location and extent of landslides
over large areas, providing ample data support for subsequent landslide research. This …

This work uses sequence-to-sequence (seq2seq) models pre-trained on monolingual
corpora for machine translation. We pre-train two seq2seq models with monolingual corpora …

In many industries, analog gauges are monitored manually, thus posing problems,
especially in large facilities where gauges are often placed in hard-to-access or dangerous …

Downsampling is widely adopted to achieve a good trade-off between accuracy and latency
for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and …

In this paper we propose a vision-based two-stage parking detection module. The first stage
detects vehicles in images based on a deep neural network. Then, a rule-based system …

Vehicle detection in parking areas provides the spatial and temporal utilisation of parking
spaces. Parking observations are typically performed manually, limiting the temporal …