相关论文: Skeleton-Based Human Action Recognition with Noisy…

Label noise in the sense of incorrect labels is present in many real-world data sets and is known to severely limit the generalizability of deep learning models. In the field of remote sensing, however, automated treatment of label noise in…

Skeleton data carries valuable motion information and is widely explored in human action recognition. However, not only the motion information but also the interaction with the environment provides discriminative cues to recognize the…

Recently, video recognition is emerging with the help of multi-modal learning, which focuses on integrating distinct modalities to improve the performance or robustness of the model. Although various multi-modal learning methods have been…

Label noise is ubiquitous in various machine learning scenarios such as self-labeling with model predictions and erroneous data annotation. Many existing approaches are based on heuristics such as sample losses, which might not be flexible…

Despite the success of deep learning methods in medical image segmentation tasks, the human-level performance relies on massive training data with high-quality annotations, which are expensive and time-consuming to collect. The fact is that…

To collect large scale annotated data, it is inevitable to introduce label noise, i.e., incorrect class labels. To be robust against label noise, many successful methods rely on the noisy classifiers (i.e., models trained on the noisy…

In human activity recognition (HAR), activity labels have typically been encoded in one-hot format, which has a recent shift towards using textual representations to provide contextual knowledge. Here, we argue that HAR should be anchored…

Understanding human actions is a crucial problem for service robots. However, the general trend in Action Recognition is developing and testing these systems on structured datasets. That's why this work presents a practical Skeleton-based…

In real-world scenarios, human actions often fall outside the distribution of training data, making it crucial for models to recognize known actions and reject unknown ones. However, using pure skeleton data in such open-set conditions…

Speech emotion recognition (SER) is an important aspect of effective human-robot collaboration and received a lot of attention from the research community. For example, many neural network-based architectures were proposed recently and…

Noise in data appears to be inevitable in most real-world machine learning applications and would cause severe overfitting problems. Not only can data features contain noise, but labels are also prone to be noisy due to human input. In this…

Distant and weak supervision allow to obtain large amounts of labeled training data quickly and cheaply, but these automatic annotations tend to contain a high amount of errors. A popular technique to overcome the negative effects of these…

Deep learning has achieved remarkable success in graph-related tasks, yet this accomplishment heavily relies on large-scale high-quality annotated datasets. However, acquiring such datasets can be cost-prohibitive, leading to the practical…

Medical image segmentation is crucial for clinical applications, but it is frequently disrupted by noisy annotations and ambiguous anatomical boundaries, limiting its application in real-world scenarios. Existing methods often directly…

Skeleton-based human action recognition has attracted a lot of research attention during the past few years. Recent works attempted to utilize recurrent neural networks to model the temporal dependencies between the 3D positional…

Noisy Labels are commonly present in data sets automatically collected from the internet, mislabeled by non-specialist annotators, or even specialists in a challenging task, such as in the medical field. Although deep learning models have…

Deep learning has achieved remarkable success in numerous domains with help from large amounts of big data. However, the quality of data labels is a concern because of the lack of high-quality labels in many real-world scenarios. As noisy…

Many state-of-the-art noisy-label learning methods rely on learning mechanisms that estimate the samples' clean labels during training and discard their original noisy labels. However, this approach prevents the learning of the relationship…

Current state-of-the-art deep learning systems for visual object recognition and detection use purely supervised training with regularization such as dropout to avoid overfitting. The performance depends critically on the amount of labeled…

Available training data for named entity recognition (NER) often contains a significant percentage of incorrect labels for entity types and entity boundaries. Such label noise poses challenges for supervised learning and may significantly…