Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

Self-supervised representation learning (SSRL) methods aim to provide powerful, deep
feature learning without the requirement of large annotated data sets, thus alleviating the …

Scale is the primary factor for building a powerful foundation model that could well
generalize to a variety of downstream tasks. However, it is still challenging to train video …

Pre-training video transformers on extra large-scale datasets is generally required to
achieve premier performance on relatively small datasets. In this paper, we show that video …

Real-world data typically follow a long-tailed distribution, where a few majority categories
occupy most of the data while most minority categories contain a limited number of samples …

Self-supervised learning in vision--language processing (VLP) exploits semantic alignment
between imaging and text modalities. Prior work in biomedical VLP has mostly relied on the …

Recent advancements of sequential deep learning models such as Transformer and BERT
have significantly facilitated the sequential recommendation. However, according to our …

Self-supervised learning algorithms based on instance discrimination train encoders to be
invariant to pre-defined transformations of the same instance. While most methods treat …

The remarkable success of deep learning in various domains relies on the availability of
large-scale annotated datasets. However, obtaining annotations is expensive and requires …

To date, most existing self-supervised learning methods are designed and optimized for
image classification. These pre-trained models can be sub-optimal for dense prediction …