We describe a novel cross-modal embedding space for actions, named Action2Vec, which
combines linguistic cues from class labels with spatio-temporal features derived from video …

Contrastive Language-Image Pretraining (CLIP) has shown remarkable open-vocabulary
abilities across various image understanding tasks. Building upon this impressive success …

Existing research on action recognition treats activities as monolithic events occurring in
videos. Recently, the benefits of formulating actions as a combination of atomic-actions have …

Existing methods for open set action recognition focus on novelty detection that assumes
video clips show a single action, which is unrealistic in the real world. We propose a new …

Action recognition models have achieved impressive results by incorporating scene-level
annotations, such as objects, their relations, 3D structure, and more. However, obtaining …

We address the problem of data augmentation for video action recognition. Standard
augmentation strategies in video are hand-designed and sample the space of possible …

Current state-of-the-art models for video action recognition are mostly based on expensive
3D ConvNets. This results in a need for large GPU clusters to train and evaluate such …

Current methods for action recognition primarily rely on deep convolutional networks to
derive feature embeddings of visual and motion features. While these methods have …

Current fully-supervised video datasets consist of only a few hundred thousand videos and
fewer than a thousand domain-specific labels. This hinders the progress towards advanced …

The canonical approach to video action recognition dictates a neural model to do a classic
and standard 1-of-N majority vote task. They are trained to predict a fixed set of predefined …