Related papers: SIGNL: A Label-Efficient Audio Deepfake Detection …

Collecting labeled data for the task of semantic segmentation is expensive and time-consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural Network (CNN) based semantic segmentation approaches have…

Audio plays a crucial role in applications like speaker verification, voice-enabled smart devices, and audio conferencing. However, audio manipulations, such as deepfakes, pose significant risks by enabling the spread of misinformation. Our…

The lack of strong labels has severely limited the state-of-the-art fully supervised audio tagging systems to be scaled to larger dataset. Meanwhile, audio-visual learning models based on unlabeled videos have been successfully applied to…

Deepfake (DF) audio detectors still struggle to generalize to out of distribution inputs. A central reason is spectral bias, the tendency of neural networks to learn low-frequency structure before high-frequency (HF) details, which both…

In many applications, training machine learning models involves using large amounts of human-annotated data. Obtaining precise labels for the data is expensive. Instead, training with weak supervision provides a low-cost alternative. We…

Deepfake audio presents a growing threat to digital security, due to its potential for social engineering, fraud, and identity misuse. However, existing detection models suffer from poor generalization across datasets, due to implicit…

Graph classification is a critical research problem in many applications from different domains. In order to learn a graph classification model, the most widely used supervision component is an output layer together with classification loss…

Label estimation is an important component in an unsupervised person re-identification (re-ID) system. This paper focuses on cross-camera label estimation, which can be subsequently used in feature learning to learn robust re-ID models.…

Large language models (LLMs) are being increasingly tuned to power complex generation tasks such as writing, fact-seeking, querying and reasoning. Traditionally, human or model feedback for evaluating and further tuning LLM performance has…

Research on multi-modal contrastive learning strategies for audio and text has rapidly gained interest. Contrastively trained Audio-Language Models (ALMs), such as CLAP, which establish a unified representation across audio and language…

Data collected from the real world typically exhibit long-tailed distributions, where frequent classes contain abundant data while rare ones have only a limited number of samples. While existing supervised learning approaches have been…

Video self-supervised learning is a challenging task, which requires significant expressive power from the model to leverage rich spatial-temporal knowledge and generate effective supervisory signals from large amounts of unlabeled videos.…

In this paper, we present a simple and efficient method for training deep neural networks in a semi-supervised setting where only a small portion of training data is labeled. We introduce self-ensembling, where we form a consensus…

Node classification is one of the core tasks on attributed graphs, but successful graph learning solutions require sufficiently labeled data. To keep annotation costs low, active graph learning focuses on selecting the most qualitative…

Continual learning (CL) has shown promising results and comparable performance to learning at once in a fully supervised manner. However, CL strategies typically require a large number of labeled samples, making their real-life deployment…

Retinal vessel segmentation from retinal images is an essential task for developing the computer-aided diagnosis system for retinal diseases. Efforts have been made on high-performance deep learning-based approaches to segment the retinal…

In this paper, we propose an enhanced audio-visual deep detection method. Recent methods in audio-visual deepfake detection mostly assess the synchronization between audio and visual features. Although they have shown promising results,…

Environmental audio tagging is a newly proposed task to predict the presence or absence of a specific audio event in a chunk. Deep neural network (DNN) based methods have been successfully adopted for predicting the audio tags in the…

Graph Neural Networks (GNNs) have become widely-used models for semi-supervised learning. However, the robustness of GNNs in the presence of label noise remains a largely under-explored problem. In this paper, we consider an important yet…

Human action understanding is crucial for the advancement of multimodal systems. While recent developments, driven by powerful large language models (LLMs), aim to be general enough to cover a wide range of categories, they often overlook…