Related papers: Self-supervised Video Representation Learning with…

Contrastive learning is a powerful framework for learning self-supervised representations that generalize well to downstream supervised tasks. We show that multiple existing contrastive learning methods can be reinterpreted as learning…

High-quality representation of transactional sequences is vital for modern banking applications, including risk management, churn prediction, and personalized customer offers. Different tasks require distinct representation properties:…

Online continual learning, aimed at developing a neural network that continuously learns new data from a single pass over an online data stream, generally suffers from catastrophic forgetting. Existing replay-based methods alleviate…

In continual learning, a system learns from non-stationary data streams or batches without catastrophic forgetting. While this problem has been heavily studied in supervised image classification and reinforcement learning, continual…

Recognizing transformation types applied to a video clip (RecogTrans) is a long-established paradigm for self-supervised video representation learning, which achieves much inferior performance compared to instance discrimination approaches…

Given a query composed of a reference image and a relative caption, the Composed Image Retrieval goal is to retrieve images visually similar to the reference one that integrates the modifications expressed by the caption. Given that recent…

The pre-training of visual representations has enhanced the efficiency of robot learning. Due to the lack of large-scale in-domain robotic datasets, prior works utilize in-the-wild human videos to pre-train robotic visual representation.…

Deep learning models for Electrocardiogram (ECG) diagnosis have achieved remarkable accuracy but exhibit fragility against adversarial perturbations, particularly Smooth Adversarial Perturbations (SAP) that mimic biological morphology.…

We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlike existing visual pre-training methods, which solve a proxy…

Contrastive representation learning (CRL) underpins many modern foundation models. Despite recent theoretical progress, existing analyses suffer from several key limitations: (i) the statistical consistency of CRL remains poorly understood;…

Learning good representations involves capturing the diverse ways in which data samples relate. Contrastive loss - an objective matching related samples - underlies methods from self-supervised to multimodal learning. Contrastive losses,…

Continual relation extraction (CRE) aims to extract relations towards the continuous and iterative arrival of new data, of which the major challenge is the catastrophic forgetting of old tasks. In order to alleviate this critical problem…

The success of Transformer-based models has encouraged many researchers to learn CAD models using sequence-based approaches. However, learning CAD models is still a challenge, because they can be represented as complex shapes with long…

Contrastive representation learning has proven to be an effective self-supervised learning method. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as positives that should be…

Upscaled video detection is a helpful tool in multimedia forensics, but it is a challenging task that involves various upscaling and compression algorithms. There are many resolution-enhancement methods, including interpolation and…

Task-incremental continual learning refers to continually training a model in a sequence of tasks while overcoming the problem of catastrophic forgetting (CF). The issue arrives for the reason that the learned representations are forgotten…

Conventional representation learning methods learn a universal representation that primarily captures dominant semantics, which may not always align with customized downstream tasks. For instance, in animal habitat analysis, researchers…

Sequence-level learning objective has been widely used in captioning tasks to achieve the state-of-the-art performance for many models. In this objective, the model is trained by the reward on the quality of its generated captions…

We propose a self-supervised contrastive learning approach for facial expression recognition (FER) in videos. We propose a novel temporal sampling-based augmentation scheme to be utilized in addition to standard spatial augmentations used…

Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without…