Related papers: Semi-Supervised Contrastive Learning for Controlla…

Graph classification is a widely studied problem and has broad applications. In many real-world problems, the number of labeled graphs available for training classification models is limited, which renders these models prone to overfitting.…

We propose a self-supervised visual learning method by predicting the variable playback speeds of a video. Without semantic labels, we learn the spatio-temporal visual representation of the video by leveraging the variations in the visual…

The objective of this paper is self-supervised representation learning, with the goal of solving semi-supervised video object segmentation (a.k.a. dense tracking). We make the following contributions: (i) we propose to improve the existing…

Contrastive learning of auditory and visual perception has been extremely successful when investigated individually. However, there are still major questions on how we could integrate principles learned from both domains to attain effective…

While deep learning has enabled great advances in many areas of music, labeled music datasets remain especially hard, expensive, and time-consuming to create. In this work, we introduce SimCLR to the music domain and contribute a large…

Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature learning from unlabeled…

The lack of labeled data is a key challenge for learning useful representation from time series data. However, an unsupervised representation framework that is capable of producing high quality representations could be of great value. It is…

We have built a music similarity search engine that lets video producers search by listenable music excerpts, as a complement to traditional full-text search. Our system suggests similar sounding track segments in a large music catalog by…

As an algorithmic framework for learning to learn, meta-learning provides a promising solution for few-shot text classification. However, most existing research fail to give enough attention to class labels. Traditional basic framework…

Music recommender systems frequently utilize network-based models to capture relationships between music pieces, artists, and users. Although these relationships provide valuable insights for predictions, new music pieces or artists often…

Consistency regularization on label predictions becomes a fundamental technique in semi-supervised learning, but it still requires a large number of training iterations for high performance. In this study, we analyze that the consistency…

We present a framework for learning to generate background music from video inputs. Unlike existing works that rely on symbolic musical annotations, which are limited in quantity and diversity, our method leverages large-scale web videos…

Despite significant progress in semi-supervised learning for image object detection, several key issues are yet to be addressed for video object detection: (1) Achieving good performance for supervised video object detection greatly depends…

We present a self-supervised Contrastive Video Representation Learning (CVRL) method to learn spatiotemporal visual representations from unlabeled videos. Our representations are learned using a contrastive loss, where two augmented clips…

Semi-supervised learning methods have shown promising results in solving many practical problems when only a few labels are available. The existing methods assume that the class distributions of labeled and unlabeled data are equal;…

In semi-supervised learning, the paradigm of self-training refers to the idea of learning from pseudo-labels suggested by the learner itself. Across various domains, corresponding methods have proven effective and achieve state-of-the-art…

We tackle the cross-modal retrieval problem, where learning is only supervised by relevant multi-modal pairs in the data. Although the contrastive learning is the most popular approach for this task, it makes potentially wrong assumption…

Self-supervised methods have emerged as a promising avenue for representation learning in the recent years since they alleviate the need for labeled datasets, which are scarce and expensive to acquire. Contrastive methods are a popular…

We propose a supervised contrastive learning framework for video representation learning that leverages temporally global context. We introduce a video to image aggregation strategy that spatially arranges multiple frames from each video…

Learning transferable and domain adaptive feature representations from videos is important for video-relevant tasks such as action recognition. Existing video domain adaptation methods mainly rely on adversarial feature alignment, which has…