Collecting cross-modal presence-absence evidence for weakly-supervised audio-visual event perception
With only video-level event labels, this paper targets at the task of weakly-supervised audio-
visual event perception (WS-AVEP), which aims to temporally localize and categorize events …
visual event perception (WS-AVEP), which aims to temporally localize and categorize events …
A survey on uncertainty reasoning and quantification in belief theory and its application to deep learning
An in-depth understanding of uncertainty is the first step to making effective decisions under
uncertainty. Machine/deep learning (ML/DL) has been hugely leveraged to solve complex …
uncertainty. Machine/deep learning (ML/DL) has been hugely leveraged to solve complex …
Towards trustworthy multi-label sewer defect classification via evidential deep learning
An automatic vision-based sewer inspection plays a key role of sewage system in a modern
city. Recent advances focus on utilizing deep learning model to realize the sewer inspection …
city. Recent advances focus on utilizing deep learning model to realize the sewer inspection …
Multi-Label Temporal Evidential Neural Networks for Early Event Detection
Early event detection aims to detect events even before the event is complete. However,
most of the existing methods focus on an event with a single label but fail to be applied to …
most of the existing methods focus on an event with a single label but fail to be applied to …
2nd Workshop on Uncertainty Reasoning and Quantification in Decision Making
Uncertainty reasoning and quantification play a critical role in decision making across
various domains, prompting increased attention from both academia and industry. As real …
various domains, prompting increased attention from both academia and industry. As real …
ConvDTW-ACS: Audio Segmentation for Track Type Detection During Car Manufacturing
Á López-Chilet, Z Liu, JA Gómez, C Alvarez… - arXiv preprint arXiv …, 2024 - arxiv.org
This paper proposes a method for Acoustic Constrained Segmentation (ACS) in audio
recordings of vehicles driven through a production test track, delimiting the boundaries of …
recordings of vehicles driven through a production test track, delimiting the boundaries of …
How out-of-distribution data hurts semi-supervised learning
Recent semi-supervised learning algorithms have demonstrated greater success with higher
overall performance due to the use of better-unlabeled data representations. Nonetheless …
overall performance due to the use of better-unlabeled data representations. Nonetheless …
Multidimensional Uncertainty Quantification for Deep Neural Networks
X Zhao - arXiv preprint arXiv:2304.10527, 2023 - arxiv.org
Deep neural networks (DNNs) have received tremendous attention and achieved great
success in various applications, such as image and video analysis, natural language …
success in various applications, such as image and video analysis, natural language …
Active Genetic Learning with Evidential Uncertainty for Identifying Mushroom Toxicity
Mushroom's classification as edible or poisonous is an important problem that can have a
direct impact on hu-man life. However, most of the existing works do not in-clude model …
direct impact on hu-man life. However, most of the existing works do not in-clude model …
[图书][B] Deep Active Genetic Learning with Evidential Uncertainty for Agriculture Crops and Lake Water Quality Assessment
OM Aranay - 2022 - search.proquest.com
Despite significant advancements in the field of machine learning, there are two issues that
still require further exploration. First, how to learn from a small dataset; and second, how to …
still require further exploration. First, how to learn from a small dataset; and second, how to …