相关论文: Visually Exploring Multi-Purpose Audio Data

Clustering algorithms are one of the main analytical methods to detect patterns in unlabeled data. Existing clustering methods typically treat samples in a dataset as points in a metric space and compute distances to group together similar…

State-of-the-art computer vision models are mostly trained with supervised learning using human-labeled images, which limits their scalability due to the expensive annotation cost. While self-supervised representation learning has achieved…

Existing multi-stage clustering methods independently learn the salient features from multiple views and then perform the clustering task. Particularly, multi-view clustering (MVC) has attracted a lot of attention in multi-view or…

Clustering is viewed as an unsupervised technique, but in practice it requires guidance to uncover meaningful structures. We formalize this with guided clustering, a paradigm that uses a guiding variable to steer the discovery process, and…

The application of unsupervised learning approaches, and in particular of clustering techniques, represents a powerful exploration means for the analysis of network measurements. Discovering underlying data characteristics, grouping similar…

Machine listening systems often rely on fixed taxonomies to organize and label audio data, key for training and evaluating deep neural networks (DNNs) and other supervised algorithms. However, such taxonomies face significant constraints:…

Recently, variational autoencoders have been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement. However, variational autoencoders are trained on clean speech only, which…

Self-supervision has shown great potential for audio-visual speech recognition by vastly reducing the amount of labeled data required to build good systems. However, existing methods are either not entirely end-to-end or do not train joint…

Foundation vision, audio, and language models enable zero-shot performance on downstream tasks via their latent representations. Recently, unsupervised learning of data group structure with deep learning methods has gained popularity.…

To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like…

Weakly supervised Audio-Visual Video Parsing (AVVP) aims to recognize and temporally localize audio, visual, and audio-visual events in videos using only coarse-grained labels. Faced with the challenging task settings, existing research…

Temporal Action Localization (TAL) has garnered significant attention in information retrieval. Existing supervised or weakly supervised methods heavily rely on labeled temporal boundaries and action categories, which are labor-intensive…

Visual events are usually accompanied by sounds in our daily lives. We pose the question: Can the machine learn the correspondence between visual scene and the sound, and localize the sound source only by observing sound and visual scene…

The ability to both recognize and discover terrain characteristics is an important function required for many autonomous ground robots such as social robots, assistive robots, autonomous vehicles, and ground exploration robots. Recognizing…

We tackle the task of environmental event classification by drawing inspiration from the transformer neural network architecture used in machine translation. We modify this attention-based feedforward structure in such a way that allows the…

Significant progress has been witnessed in learning-based Multi-view Stereo (MVS) under supervised and unsupervised settings. To combine their respective merits in accuracy and completeness, meantime reducing the demand for expensive…

We address the task of weakly-supervised few-shot image classification and segmentation, by leveraging a Vision Transformer (ViT) pretrained with self-supervision. Our proposed method takes token representations from the self-supervised ViT…

The large size of nowadays' online multimedia databases makes retrieving their content a difficult and time-consuming task. Users of online sound collections typically submit search queries that express a broad intent, often making the…

Access to high-quality labeled data remains a limiting factor in applied supervised learning. While label variation (LV), i.e., differing labels for the same instance, is common, especially in natural language processing, annotation…

Reliably labelling data typically requires annotations from multiple human workers. However, humans are far from being perfect. Hence, it is a common practice to aggregate labels gathered from multiple annotators to make a more confident…