In recent years, deep learning has garnered tremendous success in a variety of application
domains. This new field of machine learning has been growing rapidly and has been …

The foundation models have recently shown excellent performance on a variety of
downstream tasks in computer vision. However, most existing vision foundation models …

In a real-world scenario, human actions are typically out of the distribution from training data,
which requires a model to both recognize the known actions and reject the unknown …

Open-set action recognition (OSAR) aims to learn a recognition framework capable of both
classifying known classes and identifying unknown actions in open-set scenarios. Existing …

Deep models have the risk of utilizing spurious clues to make predictions, eg, recognizing
actions via classifying the background scene. This problem severely degrades the open-set …

Open-set Recognition (OSR) aims to identify test samples whose classes are not seen
during the training process. Recently, Unified Open-set Recognition (UOSR) has been …

In real-world scenarios, human actions often fall outside the distribution of training data,
making it crucial for models to recognize known actions and reject unknown ones. However …

Deep neural networks (DNNs) provide state-of-the-art results for a multitude of applications,
but the approaches using DNNs for multimodal audiovisual applications do not consider …

Stochastic variational inference for Bayesian deep neural network (DNN) requires specifying
priors and approximate posterior distributions over neural network weights. Specifying …

Open set action recognition (OSAR) is a rising research domain that simultaneously
identifies all videos from known classes and rejects videos from unknown classes. Existing …