Related papers: A Global-local Attention Framework for Weakly Labe…
Universal source separation (USS) is a fundamental research task for computational auditory scene analysis, which aims to separate mono recordings into individual source tracks. There are three potential challenges awaiting the solution to…
Weakly-Supervised Temporal Action Localization (WS-TAL) task aims to recognize and localize temporal starts and ends of action instances in an untrimmed video with only video-level label supervision. Due to lack of negative samples of…
The performances of Sound Event Detection (SED) systems are greatly limited by the difficulty in generating large strongly labeled dataset. In this work, we used two main approaches to overcome the lack of strongly labeled data. First, we…
Weakly supervised data are widespread and have attracted much attention. However, since label quality is often difficult to guarantee, sometimes the use of weakly supervised data will lead to unsatisfactory performance, i.e., performance…
Many name tagging approaches use local contextual information with much success, but fail when the local context is ambiguous or limited. We present a new framework to improve name tagging by utilizing local, document-level, and…
Weakly supervised semantic segmentation (WSSS) aims at learning a semantic segmentation model with only image-level tags. Despite intensive research on deep learning approaches over a decade, there is still a significant performance gap…
In this paper, a high-speed online neural network classifier based on extreme learning machines for multi-label classification is proposed. In multi-label classification, each of the input data sample belongs to one or more than one of the…
Sound event detection (SED) is the task of tagging the absence or presence of audio events and their corresponding interval within a given audio clip. While SED can be done using supervised machine learning, where training data is fully…
We introduce Label-Combination Prototypical Networks (LC-Protonets) to address the problem of multi-label few-shot classification, where a model must generalize to new classes based on only a few available examples. Extending Prototypical…
Audio-visual learning has been a major pillar of multi-modal machine learning, where the community mostly focused on its modality-aligned setting, i.e., the audio and visual modality are both assumed to signal the prediction target. With…
We target the problem of developing new low-complexity networks for the sound event detection task. Our goal is to meticulously analyze the performance-complexity trade-off, aiming to be competitive with the large state-of-the-art models,…
We present Music Tagging Transformer that is trained with a semi-supervised approach. The proposed model captures local acoustic characteristics in shallow convolutional layers, then temporally summarizes the sequence of the extracted…
In this paper, we explore a weakly supervised method for anomaly detection. Since annotating videos is time-consuming, we only look at weak video-level labels during training. This means that given a video, we know that it is either normal…
We propose an adaptive change point detection method (A-CPD) for machine guided weak label annotation of audio recording segments. The goal is to maximize the amount of information gained about the temporal activations of the target sounds.…
Strong labels are a necessity for evaluation of sound event detection methods, but often scarcely available due to the high resources required by the annotation task. We present a method for estimating strong labels using crowdsourced weak…
Weakly-supervised temporal action localization aims to localize and recognize actions in untrimmed videos with only video-level category labels during training. Without instance-level annotations, most existing methods follow the…
Audio-Visual Source Localization (AVSL) aims to locate sounding objects within video frames given the paired audio clips. Existing methods predominantly rely on self-supervised contrastive learning of audio-visual correspondence. Without…
Environmental sound classification systems often do not perform robustly across different sound classification tasks and audio signals of varying temporal structures. We introduce a multi-stream convolutional neural network with temporal…
Long-tailed learning has attracted much attention recently, with the goal of improving generalisation for tail classes. Most existing works use supervised learning without considering the prevailing noise in the training dataset. To move…
Weakly labeled datasets such as AudioSet have driven recent progress in audio tagging. However, annotation quality varies across sound classes. Labels may be incomplete, ambiguous, or unreliable, which introduces class-dependent supervision…