相关论文: Supervised contrastive learning from weakly-labele…

We present a self-supervised learning approach to learn audio-visual representations from video and audio. Our method uses contrastive learning for cross-modal discrimination of video from audio and vice-versa. We show that optimizing for…

Standard fine-tuning of pre-trained audio models couples representation learning with classifier training, which can obscure the true quality of the learned representations. In this work, we advocate for a disentangled two-stage framework…

Cross-modal retrieval (CMR) has been extensively applied in various domains, such as multimedia search engines and recommendation systems. Most existing CMR methods focus on image-to-text retrieval, whereas audio-to-text retrieval, a less…

Object Detection, a fundamental computer vision problem, has paramount importance in smart camera systems. However, a truly reliable camera system could be achieved if and only if the underlying object detection component is robust enough…

Supervised contrastive learning has achieved remarkable success by leveraging label information; however, determining positive samples in multi-label scenarios remains a critical challenge. In multi-label supervised contrastive learning…

In this work, we propose a novel supervised contrastive loss that enables the integration of taxonomic hierarchy information during the representation learning process. A supervised contrastive loss operates by enforcing that images with…

Learning an effective representation in multi-label text classification (MLTC) is a significant challenge in NLP. This challenge arises from the inherent complexity of the task, which is shaped by two key factors: the intricate connections…

Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e. they perform…

Medical image segmentation methods typically rely on numerous dense annotated images for model training, which are notoriously expensive and time-consuming to collect. To alleviate this burden, weakly supervised techniques have been…

Music structure analysis (MSA) methods traditionally search for musically meaningful patterns in audio: homogeneity, repetition, novelty, and segment-length regularity. Hand-crafted audio features such as MFCCs or chromagrams are often used…

In this article, we aim to provide a review of the key ideas and approaches proposed in 20 years of scientific literature around musical version identification (VI) research and connect them to current practice. For more than a decade, VI…

Robust radio signal recognition is fundamental to spectrum management, electromagnetic space security, and intelligent wireless applications, yet existing deep-learning methods rely heavily on large labeled datasets and struggle to capture…

Video object detection is a challenging task because videos often suffer from image deterioration such as motion blur, occlusion, and deformable shapes, making it significantly more difficult than detecting objects in still images. Prior…

Self-supervised representation learning can mitigate the limitations in recognition tasks with few manually labeled data but abundant unlabeled data---a common scenario in sound event research. In this work, we explore unsupervised…

In the realm of music information retrieval, similarity-based retrieval and auto-tagging serve as essential components. Given the limitations and non-scalability of human supervision signals, it becomes crucial for models to learn from…

We focus on the problem of segmenting a certain object referred by a natural language sentence in video content, at the core of formulating a pinpoint vision-language relation. While existing attempts mainly construct such relation in an…

The performance of the state-of-the-art image segmentation methods heavily relies on the high-quality annotations, which are not easily affordable, particularly for medical data. To alleviate this limitation, in this study, we propose a…

We propose Corder, a self-supervised contrastive learning framework for source code model. Corder is designed to alleviate the need of labeled data for code retrieval and code summarization tasks. The pre-trained model of Corder can be used…

Contrastive learning has emerged as an essential approach for self-supervised learning in visual representation learning. The central objective of contrastive learning is to maximize the similarities between two augmented versions of an…

Weakly supervised phrase grounding aims at learning region-phrase correspondences using only image-sentence pairs. A major challenge thus lies in the missing links between image regions and sentence phrases during training. To address this…