Action recognition has improved dramatically with massive-scale video datasets. Yet, these
datasets are accompanied with issues related to curation cost, privacy, ethics, bias, and …

Human action recognition is a challenging problem, particularly when there is high
variability in factors such as subject appearance, backgrounds and viewpoint. While deep …

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

The ability to recognize human actions in a video is challenging due to the complex nature
of video data and the subtlety of human actions. Human activities often get associated with …

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 …

Spatial-temporal relation reasoning is a significant yet challenging problem for video action
recognition. Previous works typically apply local operations like 2D or 3D CNNs to conduct …

Action recognition plays a fundamental role in computer vision and video analysis.
Nevertheless, extracting effective spatial-temporal features remains a challenging task. This …

We present EgoACO, a deep neural architecture for video action recognition that learns to
pool action-context-object descriptors from frame level features by leveraging the verb-noun …

Human activities often occur in specific scene contexts, eg, playing basketball on a
basketball court. Training a model using existing video datasets thus inevitably captures and …

Efficient action recognition has become crucial to extend the success of action recognition to
many real-world applications. Contrary to most existing methods, which mainly focus on …