Related papers: An approach to improving sound-based vehicle speed…

Distance-based supervised method, the minimal learning machine, constructs a predictive model from data by learning a mapping between input and output distance matrices. In this paper, we propose new methods and evaluate how their core…

This paper proposes a novel monitoring methodology for car-following control of automated vehicles that uses real-time measurements of spacing and velocity obtained through vehicle sensors. This study focuses on monitoring the time gap, a…

The labor-intensive annotation process of semantic segmentation datasets is often prone to errors, since humans struggle to label every pixel correctly. We study algorithms to automatically detect such annotation errors, in particular…

Most audio tagging models are trained with one-hot labels as supervised information. However, one-hot labels treat all sound events equally, ignoring the semantic hierarchy and proximity relationships between sound events. In contrast, the…

Given 2D point correspondences between an image pair, inferring the camera motion is a fundamental issue in the computer vision community. The existing works generally set out from the epipolar constraint and estimate the essential matrix,…

Weakly supervised semantic segmentation (WSSS) employing weak forms of labels has been actively studied to alleviate the annotation cost of acquiring pixel-level labels. However, classifiers trained on biased datasets tend to exploit…

Arbitrary, inconsistent, or faulty decision-making raises serious concerns, and preventing unfair models is an increasingly important challenge in Machine Learning. Data often reflect past discriminatory behavior, and models trained on such…

How can unlabeled video augment visual learning? Existing methods perform "slow" feature analysis, encouraging the representations of temporally close frames to exhibit only small differences. While this standard approach captures the fact…

Learning from corrupted labels is very common in real-world machine-learning applications. Memorizing such noisy labels could affect the learning of the model, leading to sub-optimal performances. In this work, we propose a novel framework…

Masked Autoencoders (MAEs) learn rich low-level representations from unlabeled data but require substantial labeled data to effectively adapt to downstream tasks. Conversely, Instance Discrimination (ID) emphasizes high-level semantics,…

Detecting and characterising vehicles is one of the purposes of embedded systems used in intelligent environments. An analysis of a vehicle characteristics can reveal inappropriate or dangerous behaviour. This detection makes it possible to…

Vehicle speed monitoring and management of highways is the critical problem of the road in this modern age of growing technology and population. A poor management results in frequent traffic jam, traffic rules violation and fatal road…

Audio-based equipment condition monitoring suffers from a lack of standardized methodologies for algorithm selection, hindering reproducible research. This paper addresses this gap by introducing a comprehensive framework for the systematic…

Visual anomaly detection in real-world industrial settings faces two major limitations. First, most existing methods are trained on purely normal data or on unlabeled datasets assumed to be predominantly normal, presuming the absence of…

In vision-enabled autonomous systems such as robots and autonomous cars, video object detection plays a crucial role, and both its speed and accuracy are important factors to provide reliable operation. The key insight we show in this paper…

Video-to-audio (V2A) generation aims to produce corresponding audio given silent video inputs. This task is particularly challenging due to the cross-modality and sequential nature of the audio-visual features involved. Recent works have…

We study the merit of transfer learning for two sound recognition problems, i.e., audio tagging and sound event detection. Employing feature fusion, we adapt a baseline system utilizing only spectral acoustic inputs to also make use of…

Most existing approaches to autonomous driving fall into one of two categories: modular pipelines, that build an extensive model of the environment, and imitation learning approaches, that map images directly to control outputs. A recently…

Inter prediction is a key technology to reduce the temporal redundancy in video coding. In natural videos, there are usually multiple moving objects with variable velocity, resulting in complex motion fields that are difficult to represent…

With the increasing availability of 2D and 3D data, significant advancements have been made in the field of cross-modal retrieval. Nevertheless, the existence of imperfect annotations presents considerable challenges, demanding robust…