Related papers: Learning Representational Invariances for Data-Eff…

Evaluating the robustness of Video classification models is very challenging, specifically when compared to image-based models. With their increased temporal dimension, there is a significant increase in complexity and computational cost.…

A data augmentation module is utilized in contrastive learning to transform the given data example into two views, which is considered essential and irreplaceable. However, the predetermined composition of multiple data augmentations brings…

Data augmentation (DA) is an essential technique for training state-of-the-art deep learning systems. In this paper, we empirically show data augmentation might introduce noisy augmented examples and consequently hurt the performance on…

The recent success in human action recognition with deep learning methods mostly adopt the supervised learning paradigm, which requires significant amount of manually labeled data to achieve good performance. However, label collection is an…

Semi-supervised action recognition is a challenging but critical task due to the high cost of video annotations. Existing approaches mainly use convolutional neural networks, yet current revolutionary vision transformer models have been…

Deep learning models have a large number of freeparameters that need to be calculated by effective trainingof the models on a great deal of training data to improvetheir generalization performance. However, data obtaining andlabeling is…

Saliency prediction models are constrained by the limited diversity and quantity of labeled data. Standard data augmentation techniques such as rotating and cropping alter scene composition, affecting saliency. We propose a novel data…

Every hour, huge amounts of visual contents are posted on social media and user-generated content platforms. To find relevant videos by means of a natural language query, text-video retrieval methods have received increased attention over…

Recognizing actions from a limited set of labeled videos remains a challenge as annotating visual data is not only tedious but also can be expensive due to classified nature. Moreover, handling spatio-temporal data using deep $3$D…

Current training pipelines in object recognition neglect Hue Jittering when doing data augmentation as it not only brings appearance changes that are detrimental to classification, but also the implementation is inefficient in practice. In…

In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping,…

We explore spatiotemporal data augmentation using video foundation models to diversify both camera viewpoints and scene dynamics. Unlike existing approaches based on simple geometric transforms or appearance perturbations, our method…

Self-supervised representation learning has shown remarkable success in a number of domains. A common practice is to perform data augmentation via hand-crafted transformations intended to leave the semantics of the data invariant. We seek…

We propose a self-supervised training approach for learning view-invariant dense visual descriptors using image augmentations. Unlike existing works, which often require complex datasets, such as registered RGBD sequences, we train on an…

Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce. Common among recent approaches is the use of consistency training on a large amount of unlabeled data to constrain model…

Although data augmentation is a powerful technique for improving the performance of image classification tasks, it is difficult to identify the best augmentation policy. The optimal augmentation policy, which is the latent variable, cannot…

Semi-Supervised Learning can be more beneficial for the video domain compared to images because of its higher annotation cost and dimensionality. Besides, any video understanding task requires reasoning over both spatial and temporal…

Data augmentations are effective in improving the invariance of learning machines. We argue that the core challenge of data augmentations lies in designing data transformations that preserve labels. This is relatively straightforward for…

Action recognition is a well-established area of research in computer vision. In this paper, we propose S3Aug, a video data augmenatation for action recognition. Unlike conventional video data augmentation methods that involve cutting and…

We present a simple yet effective self-supervised framework for audio-visual representation learning, to localize the sound source in videos. To understand what enables to learn useful representations, we systematically investigate the…