Related papers: Explicit and Implicit Data Augmentation for Social…
Social media has become an important information source for crisis management and provides quick access to ongoing developments and critical information. However, classification models suffer from event-related biases and highly imbalanced…
Sound Event Early Detection (SEED) is an essential task in recognizing the acoustic environments and soundscapes. However, most of the existing methods focus on the offline sound event detection, which suffers from the over-confidence issue…
With the rapid rise of social media and Internet culture, memes have become a popular medium for expressing emotional tendencies. This has sparked growing interest in Meme Emotion Understanding (MEU), which aims to classify the emotional…
This paper focuses on few-shot Sound Event Detection (SED), which aims to automatically recognize and classify sound events with limited samples. However, prevailing methods methods in few-shot SED predominantly rely on segment-level…
Data augmentation methods are commonly integrated into the training of anomaly detection models. Previous approaches have primarily focused on replicating real-world anomalies or enhancing diversity, without considering that the standard of…
Recently, SpecAugment, an augmentation scheme for automatic speech recognition that acts directly on the spectrogram of input utterances, has shown to be highly effective in enhancing the performance of end-to-end networks on public…
Transformer-based models have consistently produced substantial performance gains across a variety of NLP tasks, compared to shallow models. However, deep models are orders of magnitude more computationally expensive than shallow models,…
Most sound event detection (SED) systems perform well on clean datasets but degrade significantly in noisy environments. Language-queried audio source separation (LASS) models show promise for robust SED by separating target events;…
This paper proposes a simple yet effective interpolation-based data augmentation approach termed DoubleMix, to improve the robustness of models in text classification. DoubleMix first leverages a couple of simple augmentation operations to…
Data augmentation has become a standard component of vision pre-trained models to capture the invariance between augmented views. In practice, augmentation techniques that mask regions of a sample with zero/mean values or patches from other…
The rapid advancement of generative models in creating highly realistic images poses substantial risks for misinformation dissemination. For instance, a synthetic image, when shared on social media, can mislead extensive audiences and erode…
In this contribution, we develop an accurate and effective event detection method to detect events from a Twitter stream, which uses visual and textual information to improve the performance of the mining process. The method monitors a…
Scene text recognition (STR) is a challenging task in computer vision due to the large number of possible text appearances in natural scenes. Most STR models rely on synthetic datasets for training since there are no sufficiently big and…
Hateful content detection is one of the areas where deep learning can and should make a significant difference. The Hateful Memes Challenge from Facebook helps fulfill such potential by challenging the contestants to detect hateful speech…
Nowadays, many platforms on the Web offer organized events, allowing users to be organizers or participants. For such platforms, it is beneficial to predict potential event participants. Existing work on this problem tends to borrow…
We propose a novel data augmentation method for labeled sentences called conditional BERT contextual augmentation. Data augmentation methods are often applied to prevent overfitting and improve generalization of deep neural network models.…
Data augmentation is commonly used for generating additional data from the available training data to achieve a robust estimation of the parameters of complex models like the one for speaker verification (SV), especially for under-resourced…
In recent years, social media has become one of the most popular platforms for communication. These platforms allow users to report real-world incidents that might swiftly and widely circulate throughout the whole social network. A social…
Data scarcity remains a fundamental bottleneck in applying deep learning to wireless communication problems, particularly in scenarios where collecting labeled Radio Frequency (RF) data is expensive, time-consuming, or operationally…
Event-based semantic segmentation (ESS) is a fundamental yet challenging task for event camera sensing. The difficulties in interpreting and annotating event data limit its scalability. While domain adaptation from images to event data can…